Open Second Brain
Memory server
First committed by hermes-vps-agent
Published in itechmeat/open-second-brain. Publisher page
550 GitHub stars
What it is
Second brain for AI agents using Obsidian-compatible Markdown vaults. Works with Hermes, Claude Code, Codex, and OpenClaw.
AutoGineer overview, from the brain’s own files
Open Second Brain acts as a memory provider for AI agents, enabling them to read and write persistent knowledge directly into an Obsidian-compatible Markdown vault. It employs a deterministic 'dream' pass to convert repeated signals into actionable rules, while maintaining a hash-chained log for auditability. The system supports various agent clients through MCP servers, lifecycle hooks, and a dedicated CLI, ensuring that agent-learned information remains accessible, versioned, and searchable as standard Markdown files.
How it works
Memory model: Hybrid
AutoGineer overview, from the brain’s own files
The system organizes data into a Brain folder containing Markdown files. Agents interact with this vault via MCP servers, lifecycle hooks, or the o2b CLI. Signals from agents are stored in an inbox, processed through a dream pass to generate preferences, and stored as rules in active.md. A search index is maintained in a hidden directory and can be rebuilt from the source files. The system also supports truth ledgers, decision models, and staged review gates for agent writes.
| Folder | Role | Files |
|---|---|---|
| .github | agent-config | 7 |
| bin | scripts | 1 |
| docs | docs | 774 |
| hooks | hooks | 35 |
| scripts | scripts | 22 |
| skills | agent-instructions | 6 |
| src | source-code | 1496 |
| templates | templates | 23 |
| tests | tests | 2101 |
| .agents | folder | 1 |
| .ai-notes | folder | 1 |
| .apb | folder | 87 |
| .claude-plugin | folder | 2 |
| .codex-plugin | folder | 1 |
| .githooks | folder | 2 |
| install | folder | 16 |
| openclaw | folder | 1 |
| openspec | folder | 33 |
| plugins | folder | 21 |
| schemas | folder | 5 |
The agent reads
- install/codex.md evidence: README.md
- search_iterative_recall_enabled evidence: README.md
- search_pool_max_per_session evidence: README.md
- docs/decision-models.md evidence: README.md
The agent writes
- package.json evidence: CLAUDE.md
- CHANGELOG.md evidence: CLAUDE.md
- docs/brain-store.md evidence: README.md
- docs/updating.md evidence: README.md
Requirements
Runtimes: Node.js, Python >=3.11, Bun
Databases: SQLite
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Google Antigravity, Kiro, OpenCode, Amp, Roo Code, Cline, JetBrains Junie, Devin (ex-Windsurf)
Set it up
This brain runs code automatically: 54 hooks (codex), 3 scripts. Review .githooks/pre-commit, .githooks/pre-push, hooks/hooks.json, package.json, plugins/codex/hooks/hooks.json before opening the folder in Claude Code. No step below turns a hook on for you.
.githooks/pre-commit:runs on git pre-commit.githooks/pre-push:runs on git pre-pushhooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" post-write-reminder; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook post-write-reminder; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-agenda; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-agenda; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" backlog-nudge; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook backlog-nudge; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" log-catchup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook log-catchup; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" view-render; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook view-render; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" recall-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook recall-inject; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" nav-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook nav-inject; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" counterparty-brief; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook counterparty-brief; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-orient; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-orient; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-host-backup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-host-backup; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" stop-log-guardrail; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook stop-log-guardrail; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" answer-quote-check; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook answer-quote-check; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" hygiene-digest; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook hygiene-digest; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-promote; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-promote; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0package.json:bun scripts/prepare.ts || exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" post-write-reminder; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook post-write-reminder; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-agenda; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-agenda; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" backlog-nudge; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook backlog-nudge; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" log-catchup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook log-catchup; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" view-render; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook view-render; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" recall-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook recall-inject; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" nav-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook nav-inject; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" counterparty-brief; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook counterparty-brief; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-orient; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-orient; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-host-backup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-host-backup; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" stop-log-guardrail; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook stop-log-guardrail; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" answer-quote-check; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook answer-quote-check; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" hygiene-digest; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook hygiene-digest; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-promote; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-promote; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0plugins/codex/hooks/hooks.json:r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0
- Not scanned by AutoGineerThe author’s MCP configuration (.claude-plugin/plugin.json) also starts it in a way AutoGineer does not offer. Read that file: AutoGineer did not scan that path; what it runs is listed under “This brain runs”. https://github.com/itechmeat/open-second-brain/blob/233b91d1bdc7cf74c47ea1c1fd72e949887e1fc4/.claude-plugin/plugin.json
First committed by hermes-vps-agent. Published in itechmeat/open-second-brain. Licence: MIT License.
Usage
AutoGineer overview, from the brain’s own files
- Initialize a new vault for agent memory
- Connect agents like Claude Code or Codex via MCP
- Manage agent preferences and rules through automated dream passes
- Audit agent activity using hash-chained logs
- Perform semantic or keyword searches across agent-generated notes
- Enforce write-path integrity with staged review gates
- “o2b brain today”
- Displays the current day's view and active memory markers for the agent session.
- “o2b brain rollback”
- Restores the vault state from the last snapshot, reversing recent brain mutations.
Documentation by hermes-vps-agent
Open Second Brain
Image: Open Second Brain - your knowledge, amplified by AI
Open Second Brain is a memory layer for AI agents that lives in an Obsidian vault. Agents read and write it through MCP servers, lifecycle hooks and the o2b CLI. Everything the agent learns is a Markdown file under Brain/, so you can open, edit, grep and version it like any other note. A deterministic dream pass turns repeated signals into rules and retires the ones nothing uses; no model runs inside that algorithm.
How it fits
flowchart LR
subgraph Clients["Agent clients"]
Plug["Plugins: Claude Code, Codex,<br/>Hermes, opencode, Grok Build"]
Mcp["MCP config: Cursor, kiro, Copilot CLI,<br/>Gemini CLI, ZCode, any MCP host"]
Claw["OpenClaw<br/>in-process plugin"]
Cliu["Aider, Pi<br/>CLI and context file"]
end
subgraph Product["Open Second Brain"]
Srv["MCP servers<br/>open-second-brain, open-second-brain-writer"]
Hooks["Lifecycle hooks<br/>o2b-hook"]
Cli["CLI<br/>o2b"]
Core["Core"]
end
subgraph Vault["Your vault"]
Brain["Brain/<br/>Markdown the agent writes"]
Notes["Your notes"]
Index[(".open-second-brain/brain.sqlite<br/>rebuildable search index")]
end
Plug --> Srv
Plug --> Hooks
Mcp --> Srv
Claw --> Core
Cliu --> Cli
Srv --> Core
Hooks --> Core
Cli --> Core
Core --> Brain
Core --> Index
Core -. reads, writes a named note on request .-> NotesEach client reaches the same core through a plugin, an MCP registration or the CLI. The core keeps its own records under Brain/ and a generated search index under .open-second-brain/ that it can rebuild from the files. Your notes are read; the note tools write one only at a path the caller names.
flowchart LR
Agent["Agent"] -->|brain_feedback| Inbox["Brain/inbox/<br/>signal"]
Inbox -->|dream pass| Pref["Brain/preferences/<br/>rule"]
Pref -->|rendered into| Active["Brain/active.md"]
Active -->|read at session start| Agent
Agent -->|brain_apply_evidence| Log["Brain/log/"]
Log -->|next dream pass| PrefThe learning loop: signals become rules, rules reach the next session through Brain/active.md, and applied or violated evidence confirms, quarantines or retires them. Details: docs/how-it-works.md.
Install
Install Bun 1.1 or later:
install/prerequisites.md.Install the plugin for your client (guides below), or get the
o2bCLI:install/prerequisites.md.Create the vault files:
o2b init --vault /path/to/vault --name "My Second Brain" o2b brain init --vault /path/to/vaultConnect the client (table below), then check the result:
o2b doctor --vault /path/to/vault o2b install --check
The full router with readiness criteria is install.md; native Windows is covered in install/windows.md.
Supported clients
| Client | Integration | Guide |
|---|---|---|
| Claude Code | Marketplace plugin: MCP servers and hooks | install/claudecode.md |
| OpenAI Codex | Marketplace plugin, then o2b install --target codex --apply | install/codex.md |
| ChatGPT desktop | Reads the shared Codex config: o2b install --target codex --apply | install/codex.md |
| Hermes Agent | Plugin and memory provider | install/hermes.md |
| OpenClaw | Native plugin, no MCP | install/openclaw.md |
| opencode | o2b install --target opencode --apply: MCP servers and a native plugin | install/opencode.md |
| Grok Build | o2b install --target grok --apply: MCP servers and hooks | install/grok.md |
| Cursor | o2b install --target cursor --apply | install/cursor.md |
| kiro | o2b install --target kiro --apply | install/kiro.md |
| GitHub Copilot CLI | o2b install --target copilot-cli --apply | install/copilot-cli.md |
| Gemini CLI | o2b install --target gemini-cli --apply | install/gemini-cli.md |
| ZCode | MCP servers added to its config by hand | install/zcode.md |
| Aider | o2b install --target aider --apply: context file, no MCP | install/aider.md |
| Pi | o2b install --target pi --apply: skill over the CLI | install/pi.md |
| Any other MCP host | o2b install --target generic --apply --out - prints the server entries | install/generic.md |
o2b uninstall --target <name> --apply removes what o2b install wrote; the vault is never touched (install.md).
Capabilities
Preferences that learn and expire. Signals, a deterministic dream pass, confidence and retirement: how it works.
Reversible changes. Brain mutations take a snapshot first;
o2b brain rollbackrestores it: snapshots.Attributed writes.
o2b brain writeslists every note write by agent and device,writes revertplans a restore,o2b brain freezestops all writers, ando2b brain log verifychecks the hash-chained log: Brain CLI.Search. Keyword search with an optional semantic lane, result explanations, recall profiles and compact cards; an opt-in iterative loop (
search_iterative_recall_enabled, default off) keeps querying when coverage gaps survive, pausing with a plan the caller answers throughbrain_search's round trip; and an opt-in per-source-session cap (search_pool_max_per_session, default off) keeps one long imported session from filling the candidate window, so diversity spreads across sessions: search CLI, iterative recall, pool cap, ranking.Session recall. Import agent transcripts already on disk, search them, or select whole-thread coverage under a character budget (
o2b brain session-grep --operation coverage --char-budget <n>, with--entity-keyseeding the fan-out from mined entity mentions): session logs, coverage.Hygiene.
o2b brain hygiene scanfinds contested, duplicate, stale and unused memories;applyruns only the findings you pick: maintenance.Claim ledger.
o2b brain truth ingestrecords an entity claim with an optional validity window (--valid-from/--valid-until; with the flags absent, a window on the source record's frontmatter is adopted and frozen at ingest),truth eventsrecalls a windowed slice of the ledger, andtruth stategrounds an agent-stated claim with an anchoring verdict - committed, or reported back with reason codes.truth stateaccepts an optional opaque--sample-idnaming the context-pack sample the claim drew on, and claim reads report the receipt and outcome provenance behind it at the caller's reach - "receipt known, outcome unknown", never an invented verdict: entity truth CLI.Corrections.
o2b brain lifecycle correct <target>reports a correction's blast radius and retires the affected records - validity-closed by default, tombstoned with--flatly-wrong, dry run by default and--applyto write. A retired record that recall can still serve is served only beside its correction, never alone: belief lifecycle CLI.Sharing and backup. Knowledge packs export a chosen subset;
o2b brain bank-exportwrites a one-file backup bundle: knowledge packs.Secret custody. Credentials live encrypted in the vault's state dir behind a capability-gated store;
$secret:NAMEreferences resolve at the use sites,o2b brain secret unlockwraps the keyfile under a passphrase, andsecret export/importmove the store between installs as one passphrase-encrypted bundle: custody CLI.Today view and note markers.
o2b brain today,@osb loopand@osb setmarkers: Brain CLI.Self-inspection.
o2b version,o2b install --frictionando2b state statusreport what is installed and where state lives: CLI reference.MCP surface. Tools, tool profiles for hosts with tool limits, and the always-loaded writer server:
docs/mcp.md.
Optional features
Semantic search: an embedding provider plus
sqlite-vec; theembeddings-setupskill walks through it:skills/embeddings-setup/SKILL.md.Decision models: a typed judgment model that can rerank search and filter candidates, off by default per use:
docs/decision-models.md.Deep relational recall: a fourth search arm over typed links, off by default. Its traversal runs under width budgets - 8 seeds, 4 edges per node, 16 nodes in total, and a hub above 12 walked edges is reached but not expanded - each overridable through an
OPEN_SECOND_BRAIN_SEARCH_TRAVERSAL_*environment variable or asearch_traversal_*config key; entity co-occurrence bridges join the walk by default and switch off separately (OPEN_SECOND_BRAIN_SEARCH_ENTITY_BRIDGES): retrieval quality.Staged review for agent writes, off by default. With no key set every write publishes exactly as before.
write_approval.notes/OPEN_SECOND_BRAIN_WRITE_APPROVAL_NOTES_ENABLEDandwrite_approval.ingest/OPEN_SECOND_BRAIN_WRITE_APPROVAL_INGEST_ENABLED(each falling back to thewrite_approval.enabledmaster, default off) stage note creates and ingest summary pages intoBrain/pending/beside the staged signals, where they stay out of the search index until an operator runso2b brain pending listand applies or rejects them; write-path integrity.A permissions document, absent by default.
Brain/_permissions.yaml(an operator-edited vault file) resolvesallow/ask/denyper agent, role and target for the write, ingest and owner-write actions; with the file absent every check behaves exactly as today.askstages the write,denyrefuses with thewrite-refusedtoken and the next commando2b brain permissions show, and every ask/deny verdict lands in a queryable decision ledger underBrain/logs/decisions/;o2b brain permissions showdry-runs the decision table,ledgerreads the rows; Brain CLI.The owner-write gate, off by default.
integrity.owner_scope_writesinBrain/_brain.yaml(off|warn|fail, defaultoff) refuses a caller-named owner that differs from the caller's resolved identity on the preference and note lanes (warnallows and records one decision-ledger row); a documentowner_writeverdict composes most-restrictive-wins with the gate; write-time integrity.Named MCP tokens, optional.
o2b mcp token mint|rotate|revoke|listkeeps a hash-at-rest token per agent (.open-second-brain/secrets/mcp-tokens.json; material shown exactly once). Over HTTP a valid token authenticates as its agent per request, the shared--api-keystays valid as the operator master credential, andmcp_tokens_required/OPEN_SECOND_BRAIN_MCP_TOKENS_REQUIRED(defaultfalse) makes a non-empty token map refuse credential-less requests.o2b bootstrap --target <harness> [--token] [--rotate] [--check]provisions MCP registration, token and receipt in one idempotent command, ando2b bootstrap --remove <harness>tears a provision down again; the minted token authenticates HTTP clients configured by hand, while the registered stdio harness presents no credential and keeps its config-derived identity; core CLI.Ambient capture consent, opt-out.
guardrails.ambient_writeback: falsesuppresses the ambient extraction lane with a countedambient-withheldevent (absent keeps today's behavior), andguardrails.ambient_ttl_daysstamps anexpiration_dateon ambient-extracted signals so reads drop them after the window (absent stamps nothing); a TTL-stamped signal still stages when the review gate is on and survives apply verbatim.Open decisions.
o2b brain decision open --title <t> --question <q> --option <o> [...]parks a question with enumerated options atBrain/decisions/open-<slug>.md;resolvemints the realtype: decisionpage,discardcloses without deciding, and the morning brief renders up to five open questions: belief lifecycle.
What is new
Open Second Brain 1.98.0 is the agent-presence and self-improvement release. o2b install --target <host> --apply now writes the brain-usage block into the agent-instruction file the installed host reads at the vault root (AGENTS.md for codex, cursor, opencode and aider; GEMINI.md for gemini-cli) under the same consent prompt as the config writes, preserving every byte outside the block and recording its ownership so uninstall removes exactly the pair the tool wrote; the dream pass gains an operator-approved exit into those same files, where a lesson promotes into a managed lessons block only with a fresh approval pinned to the approved text, and the doctor grades every block state it can name. The skill lane gains a benchmark-gated rewrite loop: a skill is rewritten only after a candidate beats the incumbent on scored dev tasks with full coverage and survives the one held-out check - Open Second Brain never calls a model, the scorer reads structural predicates and nothing the agent claims about its own work, and the accept stays an operator step on the command line. And ChatGPT desktop is named where its operators look for it: it reads the shared Codex config, so one codex registration serves both. Every release is described in the CHANGELOG.
Documentation
| Topic | Page |
|---|---|
| Mental model, vault layout, dream pass, safety properties | docs/how-it-works.md |
| Every CLI verb and flag | docs/cli-reference.md |
| MCP protocol, tools, writer split | docs/mcp.md |
| Brain store: setup, sync, migration, the human view | docs/brain-store.md |
| Architecture and configuration model | docs/architecture.md |
Updating (o2b update) and upgrade notes | docs/updating.md |
| Observability events | docs/observability.md |
| Metrics data contract | docs/metrics.md |
| Cross-project pointer | docs/cross-project-pointer.md |
| Scheduled Brain digest (Hermes cron) | docs/hermes-cron.md |
| Stability policy | docs/stability.md |
| Origin of the idea | docs/idea.md |
Project
CHANGELOG · Security policy · Source on GitHub · MIT License
docs/cross-project-pointer.md
Cross-project setup
When the coding work happens in a project directory that is not the Open Second Brain vault, the agent needs a pointer to find the vault on session start. This page describes the canonical snippet to drop into a project, the conventions around the vault's primary dream-running agent, and what changes when several devices share the same vault.
1. Add the pointer snippet to your project
Append the block below to one of the agent-prompt files your runtime reads on startup. Common targets:
CLAUDE.md— Claude Code.AGENTS.md— Codex, Cursor, Aider, and other tools that follow theagents.mdconvention.
Pick one location per project. You can have Open Second Brain write
and maintain this block for you instead of pasting it by hand:
o2b install --target <host> --apply writes the managed block into the
agent-instruction file your host reads at the vault root (AGENTS.md for
codex, cursor, opencode and aider; GEMINI.md for gemini-cli), under an
explicit consent prompt, keeping every byte outside the block intact on
every re-run. The installed block merges the usage content below with
the memory write gate, and a later uninstall removes exactly the pair
the tool wrote. The manual snippet stays for hosts you provision by
hand. Install only writes the vault-root instruction file of the target
host; there, a pasted snippet or any hand edit inside the managed
fences makes the run refuse with user-modified-block unless --force
replaces it (a backup of the previous file is taken first).
Replace <absolute-vault-path> with the absolute path of your
Obsidian-compatible vault before pasting.
# >>> open-second-brain managed >>>
## Open Second Brain
This project shares an Obsidian-compatible vault with an active
observing-memory layer. At session start, read the current
preferences:
<absolute-vault-path>/Brain/active.md
Record taste signals via `brain_feedback` (MCP) or
`o2b brain feedback` (CLI). After producing a durable artifact, call
`brain_apply_evidence` with `result: applied | violated | outdated`
for any preference whose `scope` matches.
Do not run `o2b brain dream` from this runtime. The vault has a
primary dream-running agent declared in `<vault>/Brain/_brain.yaml`
(key `primary_agent`).
# <<< open-second-brain managed <<<The snippet is intentionally short. The agent does not need
configuration here — every operational detail lives in the vault
itself (preferences, the active digest, the _brain.yaml config).
2. Primary agent and the dream cron
A shared vault has exactly one runtime responsible for running the
deterministic dream consolidation pass. Declare that runtime in
Brain/_brain.yaml:
o2b brain set-primary <agent-name> --vault <vault-path><agent-name> is the value of agent_name in
~/.config/open-second-brain/config.yaml on the host that runs the
dream cron. To verify, run:
grep agent_name ~/.config/open-second-brain/config.yamlWhen dream runs from a different agent, the response carries a structured warning:
The CLI prints
warning: non-primary-dream-run: dream run from agent '<caller>', ...tostderr. Exit code stays0.The MCP
brain_dreamtool returns awarningsarray containing{ code: "non-primary-dream-run", message: "..." }alongside the usual summary.The dream summary log event (
Brain/log/<date>.md) gains anon_primary_agent: <caller>payload row so the breach is greppable in the audit trail.
The pass still completes — the declaration is observability, not access control. Pinning, rejecting, and toggling pins remain unrestricted: any agent on any device can mutate the protected set.
To clear the primary declaration (the vault becomes single-host again, or you want to disable the check during local experimentation):
o2b brain set-primary --clear --vault <vault-path>A vault initialised with o2b brain init --primary-agent <name>
writes the value into the fresh _brain.yaml on the first run; on
re-runs against an existing file --primary-agent is ignored — use
set-primary instead.
3. Multi-device through Syncthing
The vault is designed to be Syncthing-shared. Signals can be captured on any peer:
brain_feedbackfrom a coding session on the laptop.o2b brain feedbackfrom a terminal.@osbmarkers added by hand in Daily notes from the phone (captured later byo2b brain scan-inlineon any peer).
All of these land in Brain/inbox/. The primary host's dream cron
picks them up on the next pass, regardless of which peer wrote them.
Use the primary_agent declaration to keep dream serialised to one
host so signal processing does not race; the rest of the Brain
layer is conflict-free because writes are append-only or
locally-scoped (signals, daily logs, snapshots).
512 files · 486 not served here
- .agents/plugins/marketplace.json (not served here)
- .ai-notes/.gitignore (not served here)
- .apb/.gitignore (not served here)
- .apb/config.yaml (not served here)
- .apb/playbooks/osb-feature-release/1.1.0/playbook.yaml (not served here)
- .apb/playbooks/osb-feature-release/1.2.0/playbook.yaml (not served here)
- .apb/playbooks/osb-feature-release/1.3.0/playbook.yaml (not served here)
- .apb/playbooks/osb-feature-release/1.4.0/playbook.yaml (not served here)
- .apb/playbooks/osb-feature-release/current (not served here)
- .apb/playbooks/osb-feature-release/lifecycle (not served here)
- .apb/playbooks/osb-feature-release/meta/1.1.0.yaml (not served here)
- .apb/playbooks/osb-feature-release/meta/1.2.0.yaml (not served here)
- .apb/playbooks/osb-feature-release/meta/1.3.0.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/playbook.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/arch-gate.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/check-context.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/check-pr.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/check-release.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/ci-wait.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/lib.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/qa-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.0.0/scripts/zg-index.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/playbook.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/arch-gate.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/check-context.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/check-pr.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/check-release.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/ci-wait.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/final-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/lib.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/qa-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.1.0/scripts/zg-index.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/playbook.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/arch-gate.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/check-context.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/check-pr.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/check-release.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/ci-wait.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/final-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/lib.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/qa-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.2.0/scripts/zg-index.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/playbook.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/arch-gate.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/check-context.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/check-pr.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/check-release.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/ci-wait.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/cycle-run.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/final-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/lib.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/qa-gates.sh (not served here)
- .apb/playbooks/osb-pr-prepare/1.4.0/scripts/zg-index.sh (not served here)
- .apb/playbooks/osb-pr-prepare/current (not served here)
- .apb/playbooks/osb-pr-prepare/lifecycle (not served here)
- .apb/playbooks/osb-pr-prepare/meta/1.0.0.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/meta/1.1.0.yaml (not served here)
- .apb/playbooks/osb-pr-prepare/meta/1.4.0.yaml (not served here)
- .apb/playbooks/osb-release/1.0.0/playbook.yaml (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/discard.sh (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/lib.sh (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/publish.sh (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/release-image-style.md (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/render.sh (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/render.ts (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/scope.sh (not served here)
- .apb/playbooks/osb-release/1.0.0/scripts/stage.sh (not served here)
- .apb/playbooks/osb-release/current (not served here)
- .apb/playbooks/osb-release/lifecycle (not served here)
- .apb/playbooks/osb-release/meta/1.0.0.yaml (not served here)
- .apb/playbooks/osb-triage-validator/1.2.0/playbook.yaml (not served here)
- .apb/playbooks/osb-triage-validator/1.3.0/playbook.yaml (not served here)
- .apb/playbooks/osb-triage-validator/current (not served here)
- .apb/playbooks/osb-triage-validator/lifecycle (not served here)
- .apb/playbooks/osb-triage-validator/meta/1.2.0.yaml (not served here)
- .apb/playbooks/osb-triage-validator/meta/1.3.0.yaml (not served here)
- .apb/playbooks/osb-upstream-watch/1.0.0/playbook.yaml (not served here)
- .apb/playbooks/osb-upstream-watch/1.0.0/scripts/materialize-collector.sh (not served here)
- .apb/playbooks/osb-upstream-watch/current (not served here)
- .apb/playbooks/osb-upstream-watch/lifecycle (not served here)
- .apb/playbooks/osb-upstream-watch/meta/1.0.0.yaml (not served here)
- .apb/profiles/osb-collector/SOUL.md (not served here)
- .apb/profiles/osb-collector/profile.yaml (not served here)
- .apb/profiles/osb-developer/SOUL.md (not served here)
- .apb/profiles/osb-developer/profile.yaml (not served here)
- .apb/profiles/osb-reviewer/SOUL.md (not served here)
- .apb/profiles/osb-reviewer/profile.yaml (not served here)
- .apb/profiles/osb-validator/SOUL.md (not served here)
- .apb/profiles/osb-validator/profile.yaml (not served here)
- .claude-plugin/marketplace.json (not served here)
- .claude-plugin/plugin.json
- .codex-plugin/plugin.json (not served here)
- .codexignore (not served here)
- .gitattributes (not served here)
- .githooks/pre-commit (not served here)
- .githooks/pre-push (not served here)
- .github/dependabot.yml (not served here)
- .github/scripts/ci-scope.sh (not served here)
- .github/scripts/windows-timings.sh (not served here)
- .github/windows-test-timings.json (not served here)
- .github/workflows/ci.yml (not served here)
- .github/workflows/plugin-scanner.yml (not served here)
- .github/workflows/release.yml (not served here)
- .gitignore (not served here)
- .oxfmtrc.json (not served here)
- ATTRIBUTION.md
- AUTOGINEER-RUNS.md
- CHANGELOG.md
- CLAUDE.md
- LICENSE
- README.md
- SECURITY.md
- __init__.py (not served here)
- after-install.md
- bin/o2b-discipline-report (not served here)
- bun.lock (not served here)
- bunfig.toml (not served here)
- cli.py (not served here)
- docs/architecture.md
- docs/brain-store.md
- docs/brainstorm/a-label-is-not-a-boundary/cli-output/claude.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/cli-output/prompt.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/design.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/plan.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/census-lexer.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/conventions-and-release-machinery.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/egress-boundary.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/fleet-and-shared-scope.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/identity-and-attribution.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/mcp-instruction-surface.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/owner-scope-isolation.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/recon/retrieval-confidence-floor.md (not served here)
- docs/brainstorm/a-label-is-not-a-boundary/variants.md (not served here)
- docs/brainstorm/actionable-now-batch/cli-output/consultant.md (not served here)
- docs/brainstorm/actionable-now-batch/cli-output/prompt.md (not served here)
- docs/brainstorm/actionable-now-batch/design.md (not served here)
- docs/brainstorm/actionable-now-batch/plan.md (not served here)
- docs/brainstorm/actionable-now-batch/variants.md (not served here)
- docs/brainstorm/agent-boundary-control-surfaces/README.md (not served here)
- docs/brainstorm/agent-boundary-control-surfaces/cli-output/claude.md (not served here)
- docs/brainstorm/agent-boundary-control-surfaces/cli-output/prompt.md (not served here)
- docs/brainstorm/agent-boundary-control-surfaces/design.md (not served here)
- docs/brainstorm/agent-boundary-control-surfaces/plan.md (not served here)
- docs/brainstorm/agent-boundary-control-surfaces/variants.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/README.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/adr.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/cli-output/claude.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/cli-output/prompt.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/context.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/design.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/implementation-notes.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/notes.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/phase-log.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/plan.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/pr-notes.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/scope.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/task-body.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/test-matrix.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/variants.md (not served here)
- docs/brainstorm/agent-capability-cli-integration/verification.md (not served here)
- docs/brainstorm/agent-presence-self-improvement/cli-output/consultant.md (not served here)
- docs/brainstorm/agent-presence-self-improvement/cli-output/prompt.md (not served here)
- docs/brainstorm/agent-presence-self-improvement/design.md (not served here)
- docs/brainstorm/agent-presence-self-improvement/plan.md (not served here)
- docs/brainstorm/agent-presence-self-improvement/variants.md (not served here)
- docs/brainstorm/agent-surface-suite/cli-output/claude.md (not served here)
- docs/brainstorm/agent-surface-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/agent-surface-suite/design.md (not served here)
- docs/brainstorm/agent-surface-suite/plan.md (not served here)
- docs/brainstorm/agent-surface-suite/variants.md (not served here)
- docs/brainstorm/agent-write-contract-suite/cli-output/claude.md (not served here)
- docs/brainstorm/agent-write-contract-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/agent-write-contract-suite/design.md (not served here)
- docs/brainstorm/agent-write-contract-suite/plan.md (not served here)
- docs/brainstorm/agent-write-contract-suite/variants.md (not served here)
- docs/brainstorm/answer-trust/cli-output/consultant.md (not served here)
- docs/brainstorm/answer-trust/cli-output/prompt.md (not served here)
- docs/brainstorm/answer-trust/design.md (not served here)
- docs/brainstorm/answer-trust/plan.md (not served here)
- docs/brainstorm/answer-trust/variants.md (not served here)
- docs/brainstorm/auto-migrate-on-upgrade/design.md (not served here)
- docs/brainstorm/auto-migrate-on-upgrade/plan.md (not served here)
- docs/brainstorm/auto-migrate-on-upgrade/variants.md (not served here)
- docs/brainstorm/belief-lifecycle-decision-memory/cli-output/claude.md (not served here)
- docs/brainstorm/belief-lifecycle-decision-memory/cli-output/prompt.md (not served here)
- docs/brainstorm/belief-lifecycle-decision-memory/design.md (not served here)
- docs/brainstorm/belief-lifecycle-decision-memory/plan.md (not served here)
- docs/brainstorm/belief-lifecycle-decision-memory/variants.md (not served here)
- docs/brainstorm/brain-centric-layout/design.md (not served here)
- docs/brainstorm/brain-centric-layout/plan.md (not served here)
- docs/brainstorm/brain-integrity-safety-hardening/cli-output/claude.md (not served here)
- docs/brainstorm/brain-integrity-safety-hardening/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-integrity-safety-hardening/design.md (not served here)
- docs/brainstorm/brain-integrity-safety-hardening/plan.md (not served here)
- docs/brainstorm/brain-integrity-safety-hardening/variants.md (not served here)
- docs/brainstorm/brain-integrity-suite/cli-output/claude.md (not served here)
- docs/brainstorm/brain-integrity-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-integrity-suite/design.md (not served here)
- docs/brainstorm/brain-integrity-suite/plan.md (not served here)
- docs/brainstorm/brain-integrity-suite/pr-body.md (not served here)
- docs/brainstorm/brain-integrity-suite/variants.md (not served here)
- docs/brainstorm/brain-lifecycle-review-suite/cli-output/claude.md (not served here)
- docs/brainstorm/brain-lifecycle-review-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-lifecycle-review-suite/design.md (not served here)
- docs/brainstorm/brain-lifecycle-review-suite/plan.md (not served here)
- docs/brainstorm/brain-lifecycle-review-suite/variants.md (not served here)
- docs/brainstorm/brain-lifecycle-suite/cli-output/claude.md (not served here)
- docs/brainstorm/brain-lifecycle-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-lifecycle-suite/design.md (not served here)
- docs/brainstorm/brain-lifecycle-suite/plan.md (not served here)
- docs/brainstorm/brain-lifecycle-suite/variants.md (not served here)
- docs/brainstorm/brain-model-semantics-foundation/adr.md (not served here)
- docs/brainstorm/brain-model-semantics-foundation/cli-output/claude.md (not served here)
- docs/brainstorm/brain-model-semantics-foundation/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-model-semantics-foundation/design.md (not served here)
- docs/brainstorm/brain-model-semantics-foundation/plan.md (not served here)
- docs/brainstorm/brain-model-semantics-foundation/variants.md (not served here)
- docs/brainstorm/brain-portability-interop/cli-output/claude.md (not served here)
- docs/brainstorm/brain-portability-interop/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-portability-interop/design.md (not served here)
- docs/brainstorm/brain-portability-interop/plan.md (not served here)
- docs/brainstorm/brain-portability-interop/variants.md (not served here)
- docs/brainstorm/brain-safety-governance-suite/cli-output/claude.md (not served here)
- docs/brainstorm/brain-safety-governance-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/brain-safety-governance-suite/design.md (not served here)
- docs/brainstorm/brain-safety-governance-suite/plan.md (not served here)
- docs/brainstorm/brain-safety-governance-suite/variants.md (not served here)
- docs/brainstorm/cjk-schema-lifecycle-recovery/cli-output/claude.md (not served here)
- docs/brainstorm/cjk-schema-lifecycle-recovery/cli-output/prompt.md (not served here)
- docs/brainstorm/cjk-schema-lifecycle-recovery/design.md (not served here)
- docs/brainstorm/cjk-schema-lifecycle-recovery/plan.md (not served here)
- docs/brainstorm/cjk-schema-lifecycle-recovery/variants.md (not served here)
- docs/brainstorm/codegraph-link-depth-mcp/cli-output/claude.md (not served here)
- docs/brainstorm/codegraph-link-depth-mcp/cli-output/prompt.md (not served here)
- docs/brainstorm/codegraph-link-depth-mcp/design.md (not served here)
- docs/brainstorm/codegraph-link-depth-mcp/plan.md (not served here)
- docs/brainstorm/codegraph-link-depth-mcp/variants.md (not served here)
- docs/brainstorm/codegraph-mcp-operational-readability/cli-output/claude.md (not served here)
- docs/brainstorm/codegraph-mcp-operational-readability/cli-output/prompt.md (not served here)
- docs/brainstorm/codegraph-mcp-operational-readability/design.md (not served here)
- docs/brainstorm/codegraph-mcp-operational-readability/plan.md (not served here)
- docs/brainstorm/codegraph-mcp-operational-readability/variants.md (not served here)
- docs/brainstorm/context-continuity-receipts-suite/cli-output/claude.md (not served here)
- docs/brainstorm/context-continuity-receipts-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/context-continuity-receipts-suite/design.md (not served here)
- docs/brainstorm/context-continuity-receipts-suite/plan.md (not served here)
- docs/brainstorm/context-continuity-receipts-suite/variants.md (not served here)
- docs/brainstorm/context-injection-pipeline/cli-output/consultant.md (not served here)
- docs/brainstorm/context-injection-pipeline/cli-output/prompt.md (not served here)
- docs/brainstorm/context-injection-pipeline/design.md (not served here)
- docs/brainstorm/context-injection-pipeline/plan.md (not served here)
- docs/brainstorm/context-injection-pipeline/variants.md (not served here)
- docs/brainstorm/context-integrity-gates/cli-output/claude.md (not served here)
- docs/brainstorm/context-integrity-gates/cli-output/prompt.md (not served here)
- docs/brainstorm/context-integrity-gates/design.md (not served here)
- docs/brainstorm/context-integrity-gates/plan.md (not served here)
- docs/brainstorm/context-integrity-gates/variants.md (not served here)
- docs/brainstorm/context-pack-economics-observability/cli-output/claude.md (not served here)
- docs/brainstorm/context-pack-economics-observability/cli-output/prompt.md (not served here)
- docs/brainstorm/context-pack-economics-observability/design.md (not served here)
- docs/brainstorm/context-pack-economics-observability/plan.md (not served here)
- docs/brainstorm/context-pack-economics-observability/variants.md (not served here)
- docs/brainstorm/continuity-hygiene-freshness/cli-output/claude.md (not served here)
- docs/brainstorm/continuity-hygiene-freshness/cli-output/prompt.md (not served here)
- docs/brainstorm/continuity-hygiene-freshness/design.md (not served here)
- docs/brainstorm/continuity-hygiene-freshness/plan.md (not served here)
- docs/brainstorm/continuity-hygiene-freshness/variants.md (not served here)
- docs/brainstorm/cross-agent-query-foundation/cli-output/claude.md (not served here)
- docs/brainstorm/cross-agent-query-foundation/cli-output/prompt.md (not served here)
- docs/brainstorm/cross-agent-query-foundation/design.md (not served here)
- docs/brainstorm/cross-agent-query-foundation/plan.md (not served here)
- docs/brainstorm/cross-agent-query-foundation/variants.md (not served here)
- docs/brainstorm/crossvault-cards-eventtrace-fixes/design.md (not served here)
- docs/brainstorm/crossvault-cards-eventtrace-fixes/plan.md (not served here)
- docs/brainstorm/crossvault-cards-eventtrace-fixes/variants.md (not served here)
- docs/brainstorm/cycle-20261020/cli-output/claude.md (not served here)
- docs/brainstorm/cycle-20261020/cli-output/prompt.md (not served here)
- docs/brainstorm/cycle-20261020/design.md (not served here)
- docs/brainstorm/cycle-20261020/plan.md (not served here)
- docs/brainstorm/cycle-20261020/variants.md (not served here)
- docs/brainstorm/dated-commitments/cli-output/claude.md (not served here)
- docs/brainstorm/dated-commitments/cli-output/prompt.md (not served here)
- docs/brainstorm/dated-commitments/design.md (not served here)
- docs/brainstorm/dated-commitments/plan.md (not served here)
- docs/brainstorm/dated-commitments/variants.md (not served here)
- docs/brainstorm/default-scope-feedback/cli-output/claude.md (not served here)
- docs/brainstorm/default-scope-feedback/cli-output/prompt.md (not served here)
- docs/brainstorm/default-scope-feedback/design.md (not served here)
- docs/brainstorm/default-scope-feedback/plan.md (not served here)
- docs/brainstorm/default-scope-feedback/variants.md (not served here)
- docs/brainstorm/delivery-trust/cli-output/consultant.md (not served here)
- docs/brainstorm/delivery-trust/cli-output/prompt.md (not served here)
- docs/brainstorm/delivery-trust/design.md (not served here)
- docs/brainstorm/delivery-trust/plan.md (not served here)
- docs/brainstorm/delivery-trust/variants.md (not served here)
- docs/brainstorm/distilled-provenance/cli-output/claude.md (not served here)
- docs/brainstorm/distilled-provenance/cli-output/expected-output.md (not served here)
- docs/brainstorm/distilled-provenance/cli-output/prompt.md (not served here)
- docs/brainstorm/distilled-provenance/design.md (not served here)
- docs/brainstorm/distilled-provenance/plan.md (not served here)
- docs/brainstorm/distilled-provenance/variants.md (not served here)
- docs/brainstorm/embedding-provider-suite/cli-output/claude.md (not served here)
- docs/brainstorm/embedding-provider-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/embedding-provider-suite/design.md (not served here)
- docs/brainstorm/embedding-provider-suite/plan.md (not served here)
- docs/brainstorm/embedding-provider-suite/variants.md (not served here)
- docs/brainstorm/entity-truth-dream-suite/cli-output/claude.md (not served here)
- docs/brainstorm/entity-truth-dream-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/entity-truth-dream-suite/design.md (not served here)
- docs/brainstorm/entity-truth-dream-suite/plan.md (not served here)
- docs/brainstorm/entity-truth-dream-suite/variants.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/cli-output/claude.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/cli-output/prompt.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/design.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/plan.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/0e79f0-lint-on-write.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/130-hermes-readiness.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/155-include-paths.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/160-source-trust.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/161-slug-race.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/3309-retrieval-trail.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/a3254-readiness-liveness.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/conventions.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/e24c6d-schema-completeness.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/recon/e5f447-recall-channels.md (not served here)
- docs/brainstorm/evidence-at-the-boundary/variants.md (not served here)
- docs/brainstorm/grok-native-integration/cli-output/claude.md (not served here)
- docs/brainstorm/grok-native-integration/cli-output/prompt.md (not served here)
- docs/brainstorm/grok-native-integration/design.md (not served here)
- docs/brainstorm/grok-native-integration/plan.md (not served here)
- docs/brainstorm/grok-native-integration/variants.md (not served here)
- docs/brainstorm/hermes-memory-provider/cli-output/claude.md (not served here)
- docs/brainstorm/hermes-memory-provider/cli-output/prompt.md (not served here)
- docs/brainstorm/hermes-memory-provider/design.md (not served here)
- docs/brainstorm/hermes-memory-provider/plan.md (not served here)
- docs/brainstorm/hermes-memory-provider/variants.md (not served here)
- docs/brainstorm/hermes-static-tool-schemas/cli-output/claude.md (not served here)
- docs/brainstorm/hermes-static-tool-schemas/cli-output/prompt.md (not served here)
- docs/brainstorm/hermes-static-tool-schemas/design.md (not served here)
- docs/brainstorm/hermes-static-tool-schemas/plan.md (not served here)
- docs/brainstorm/hermes-static-tool-schemas/variants.md (not served here)
- docs/brainstorm/hindsight-brain-loop-ops/cli-output/claude.md (not served here)
- docs/brainstorm/hindsight-brain-loop-ops/cli-output/prompt.md (not served here)
- docs/brainstorm/hindsight-brain-loop-ops/design.md (not served here)
- docs/brainstorm/hindsight-brain-loop-ops/plan.md (not served here)
- docs/brainstorm/hindsight-brain-loop-ops/variants.md (not served here)
- docs/brainstorm/honest-embedding-spend/cli-output/claude.md (not served here)
- docs/brainstorm/honest-embedding-spend/cli-output/prompt.md (not served here)
- docs/brainstorm/honest-embedding-spend/design.md (not served here)
- docs/brainstorm/honest-embedding-spend/plan.md (not served here)
- docs/brainstorm/honest-embedding-spend/variants.md (not served here)
- docs/brainstorm/honest-query-embed-and-safe-upgrades/cli-output/claude.md (not served here)
- docs/brainstorm/honest-query-embed-and-safe-upgrades/cli-output/prompt.md (not served here)
- docs/brainstorm/honest-query-embed-and-safe-upgrades/design.md (not served here)
- docs/brainstorm/honest-query-embed-and-safe-upgrades/plan.md (not served here)
- docs/brainstorm/honest-query-embed-and-safe-upgrades/variants.md (not served here)
- docs/brainstorm/hook-update-resilience/design.md (not served here)
- docs/brainstorm/hook-update-resilience/plan.md (not served here)
- docs/brainstorm/hook-update-resilience/variants.md (not served here)
- docs/brainstorm/index-freshness/design.md (not served here)
- docs/brainstorm/index-freshness/plan.md (not served here)
- docs/brainstorm/indexer-durability/cli-output/claude.md (not served here)
- docs/brainstorm/indexer-durability/cli-output/prompt.md (not served here)
- docs/brainstorm/indexer-durability/design.md (not served here)
- docs/brainstorm/indexer-durability/plan.md (not served here)
- docs/brainstorm/indexer-durability/variants.md (not served here)
- docs/brainstorm/ingestion-import-robustness/design.md (not served here)
- docs/brainstorm/ingestion-import-robustness/plan.md (not served here)
- docs/brainstorm/ingestion-import-robustness/variants.md (not served here)
- docs/brainstorm/integrity-control-agent-memory-surface/cli-output/claude.md (not served here)
- docs/brainstorm/integrity-control-agent-memory-surface/cli-output/prompt.md (not served here)
- docs/brainstorm/integrity-control-agent-memory-surface/design.md (not served here)
- docs/brainstorm/integrity-control-agent-memory-surface/plan.md (not served here)
- docs/brainstorm/integrity-control-agent-memory-surface/variants.md (not served here)
- docs/brainstorm/knowledge-intake-and-consolidation/cli-output/claude.md (not served here)
- docs/brainstorm/knowledge-intake-and-consolidation/cli-output/prompt.md (not served here)
- docs/brainstorm/knowledge-intake-and-consolidation/design.md (not served here)
- docs/brainstorm/knowledge-intake-and-consolidation/plan.md (not served here)
- docs/brainstorm/knowledge-intake-and-consolidation/variants.md (not served here)
- docs/brainstorm/knowledge-provenance/cli-output/claude.md (not served here)
- docs/brainstorm/knowledge-provenance/cli-output/prompt.md (not served here)
- docs/brainstorm/knowledge-provenance/design.md (not served here)
- docs/brainstorm/knowledge-provenance/plan.md (not served here)
- docs/brainstorm/knowledge-provenance/variants.md (not served here)
- docs/brainstorm/language-agnostic-fact-extraction/cli-output/claude.md (not served here)
- docs/brainstorm/language-agnostic-fact-extraction/cli-output/prompt.md (not served here)
- docs/brainstorm/language-agnostic-fact-extraction/design.md (not served here)
- docs/brainstorm/language-agnostic-fact-extraction/plan.md (not served here)
- docs/brainstorm/language-agnostic-fact-extraction/variants.md (not served here)
- docs/brainstorm/link-graph-surfaces/cli-output/claude.md (not served here)
- docs/brainstorm/link-graph-surfaces/cli-output/prompt.md (not served here)
- docs/brainstorm/link-graph-surfaces/design.md (not served here)
- docs/brainstorm/link-graph-surfaces/plan.md (not served here)
- docs/brainstorm/link-graph-surfaces/variants.md (not served here)
- docs/brainstorm/link-recall-intelligence/cli-output/claude.md (not served here)
- docs/brainstorm/link-recall-intelligence/cli-output/prompt.md (not served here)
- docs/brainstorm/link-recall-intelligence/design.md (not served here)
- docs/brainstorm/link-recall-intelligence/plan.md (not served here)
- docs/brainstorm/link-recall-intelligence/variants.md (not served here)
- docs/brainstorm/manifest-dependency-facts/cli-output/claude.md (not served here)
- docs/brainstorm/manifest-dependency-facts/cli-output/expected-output.md (not served here)
- docs/brainstorm/manifest-dependency-facts/cli-output/prompt.md (not served here)
- docs/brainstorm/manifest-dependency-facts/design.md (not served here)
- docs/brainstorm/manifest-dependency-facts/plan.md (not served here)
- docs/brainstorm/manifest-dependency-facts/variants.md (not served here)
- docs/brainstorm/mcp-context-economy/cli-output/claude.md (not served here)
- docs/brainstorm/mcp-context-economy/cli-output/prompt.md (not served here)
- docs/brainstorm/mcp-context-economy/design.md (not served here)
- docs/brainstorm/mcp-context-economy/plan.md (not served here)
- docs/brainstorm/mcp-context-economy/variants.md (not served here)
- docs/brainstorm/mcp-error-codes/cli-output/claude.md (not served here)
- docs/brainstorm/mcp-error-codes/cli-output/prompt.md (not served here)
- docs/brainstorm/mcp-error-codes/design.md (not served here)
- docs/brainstorm/mcp-error-codes/plan.md (not served here)
- docs/brainstorm/mcp-error-codes/variants.md (not served here)
- docs/brainstorm/memory-integrity/cli-output/claude.md (not served here)
- docs/brainstorm/memory-integrity/cli-output/prompt.md (not served here)
- docs/brainstorm/memory-integrity/design.md (not served here)
- docs/brainstorm/memory-integrity/plan.md (not served here)
- docs/brainstorm/memory-integrity/variants.md (not served here)
- docs/brainstorm/memory-observability-suite/atof-atif-mapping.md (not served here)
- docs/brainstorm/memory-observability-suite/cli-output/claude.md (not served here)
- docs/brainstorm/memory-observability-suite/cli-output/prompt.md (not served here)
- docs/brainstorm/memory-observability-suite/design.md (not served here)
- docs/brainstorm/memory-observability-suite/plan.md (not served here)
- docs/brainstorm/memory-observability-suite/variants.md (not served here)
- docs/brainstorm/memory-signal-provenance-lifecycle/cli-output/claude.md (not served here)
- docs/brainstorm/memory-signal-provenance-lifecycle/cli-output/prompt.md (not served here)
- docs/brainstorm/memory-signal-provenance-lifecycle/design.md (not served here)
- docs/brainstorm/memory-signal-provenance-lifecycle/plan.md (not served here)
- docs/brainstorm/memory-signal-provenance-lifecycle/variants.md (not served here)
- docs/brainstorm/memory-subsystem-alignment/cli-output/claude.md (not served here)
- docs/brainstorm/memory-subsystem-alignment/cli-output/prompt.md (not served here)
- docs/brainstorm/memory-subsystem-alignment/design.md (not served here)
- docs/brainstorm/memory-subsystem-alignment/plan.md (not served here)
- docs/brainstorm/memory-subsystem-alignment/variants.md (not served here)
- docs/brainstorm/memory-write-path-integrity/cli-output/claude.md (not served here)
- docs/brainstorm/memory-write-path-integrity/cli-output/prompt.md (not served here)
- docs/brainstorm/memory-write-path-integrity/design.md (not served here)
- docs/brainstorm/memory-write-path-integrity/plan.md (not served here)
- docs/brainstorm/memory-write-path-integrity/variants.md (not served here)
- docs/brainstorm/near-duplicate-defense/cli-output/claude.md (not served here)
- docs/brainstorm/near-duplicate-defense/cli-output/codex.md (not served here)
- docs/brainstorm/near-duplicate-defense/cli-output/opencode.md (not served here)
- docs/brainstorm/near-duplicate-defense/cli-output/prompt.md (not served here)
- docs/brainstorm/near-duplicate-defense/cli-output/second-claude.md (not served here)
- docs/brainstorm/near-duplicate-defense/design.md (not served here)
- docs/brainstorm/near-duplicate-defense/plan.md (not served here)
- docs/brainstorm/near-duplicate-defense/variants.md (not served here)
- docs/brainstorm/no-dead-ends/cli-output/claude.md (not served here)
- docs/brainstorm/no-dead-ends/cli-output/prompt.md (not served here)
- docs/brainstorm/no-dead-ends/design.md (not served here)
- docs/brainstorm/no-dead-ends/plan.md (not served here)
- docs/brainstorm/no-dead-ends/variants.md (not served here)
- docs/brainstorm/non-markdown-ingest/cli-output/claude.md (not served here)
- docs/brainstorm/non-markdown-ingest/cli-output/expected-output.md (not served here)
- docs/brainstorm/non-markdown-ingest/cli-output/prompt.md (not served here)
- docs/brainstorm/non-markdown-ingest/design.md (not served here)
- docs/brainstorm/non-markdown-ingest/plan.md (not served here)
- docs/brainstorm/non-markdown-ingest/variants.md (not served here)
- docs/brainstorm/note-change-truth-maintenance/cli-output/claude.md (not served here)
- docs/brainstorm/note-change-truth-maintenance/cli-output/prompt.md (not served here)
- docs/brainstorm/note-change-truth-maintenance/cli-output/task-bodies.md (not served here)
- docs/brainstorm/note-change-truth-maintenance/design.md (not served here)
- docs/brainstorm/note-change-truth-maintenance/plan.md (not served here)
- docs/brainstorm/note-change-truth-maintenance/variants.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/cli-output/claude.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/cli-output/prompt.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/design.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/plan.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/architect-module.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/concurrency-and-cancellation.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/durability-and-ownership.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/failure-mode-bench.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/ingest-adapters-and-lease.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/progress-reporting.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/recon/provider-sunset.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/review/claims-and-refusals.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/review/cross-cutting.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/review/locks-and-races.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/review/progress-and-cancellation.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/review/tests-and-docs.md (not served here)
- docs/brainstorm/nothing-runs-unwatched/variants.md (not served here)
- docs/brainstorm/nothing-writes-silently/cli-output/claude.md (not served here)
- docs/brainstorm/nothing-writes-silently/cli-output/prompt.md (not served here)
- docs/brainstorm/nothing-writes-silently/design.md (not served here)
- docs/brainstorm/nothing-writes-silently/plan.md (not served here)
- docs/brainstorm/nothing-writes-silently/variants.md (not served here)
- docs/brainstorm/opencode-native-integration/cli-output/claude.md (not served here)
- docs/brainstorm/opencode-native-integration/cli-output/prompt.md (not served here)
- docs/brainstorm/opencode-native-integration/design.md (not served here)
- docs/brainstorm/opencode-native-integration/plan.md (not served here)
- docs/brainstorm/opencode-native-integration/variants.md (not served here)
- docs/brainstorm/operability-first-run/design.md (not served here)
- docs/brainstorm/operability-first-run/plan.md (not served here)
- docs/brainstorm/operability-first-run/variants.md (not served here)
- docs/brainstorm/operational-friction-reduction/design.md (not served here)
- docs/cli-reference.md
- docs/cross-project-pointer.md
- docs/decision-models.md
- docs/hermes-cron.md
- docs/how-it-works.md
- docs/idea.md
- docs/ingest-manifest.md
- docs/mcp.md
- docs/metrics.md
- docs/observability.md
- docs/stability.md
- docs/updating.md
- hooks/hooks.json
- install.md
- plugins/codex/LICENSE
Advantages
- Human-readable and editable memory stored as standard Markdown files in an Obsidian vault. evidence: README.md
- Deterministic dream pass ensures rules are derived from repeated signals without requiring additional model runs. evidence: README.md
- Supports reversible changes through snapshots and rollback capabilities. evidence: README.md
Limitations
- Requires Bun runtime for the CLI and core operations. evidence: README.md
- Advanced features like semantic search require additional setup with sqlite-vec. evidence: README.md
- Some integrations depend on specific client-side plugin support or MCP host capabilities. evidence: README.md
Security
Risk level: Low risk
This brain runs
MCP servers (2)
.claude-plugin/plugin.json(open-second-brain):${CLAUDE_PLUGIN_ROOT}/scripts/o2b mcp --harness claude-code.claude-plugin/plugin.json(open-second-brain-writer):${CLAUDE_PLUGIN_ROOT}/scripts/o2b mcp --scope writer --harness claude-code
Git hooks (2)
.githooks/pre-commit(pre-commit):runs on git pre-commit.githooks/pre-push(pre-push):runs on git pre-push
Agent instructions that run or fetch something (46)
CLAUDE.md:bun run scripts/sync-version.tsCLAUDE.md:CI gates on `bun run scripts/sync-version.ts --check` (the `validate` job, step "Verify manifest version sync").CLAUDE.md:Run the `--check` form locally before pushing a version change.CLAUDE.md:Bump `package.json` (and run `sync-version.ts`) on the feature branch and include it in the SAME pull request as the feature, before you push.CLAUDE.md:Bump `package.json` to `X.Y.Z` and run `bun run scripts/sync-version.ts`.CLAUDE.md:After changing a skill or `hooks/hooks.json`, run:CLAUDE.md:bun run sync-plugin-mirrorsCLAUDE.md:CI gates on `bun run sync-plugin-mirrors:check` (the `validate` and `windows` jobs), and the pre-commit hook runs the same check.docs/legacy-skills/agent-event-log/SKILL.md:Read-only queries (running `git log`, `o2b status`, `vault_health`, `second_brain_query`).docs/legacy-skills/agent-event-log/SKILL.md:**Technical identifiers stay verbatim regardless of surrounding language**: command names (`bun test`, `o2b doctor`), file paths (`src/core/event-log.ts`), package and library names (`proper-lockfile`, `@anthropic-ai/sdk`), API symbols, error messages quoted from logs.plugins/codex/skills/brain-memory/SKILL.md:Read-only inspection (running `git log`, `o2b status`, `vault_health`).plugins/codex/skills/brain-memory/SKILL.md:After scan, the source line becomes `@osb✓ [[sig-...]]` so a second run is idempotent.plugins/codex/skills/codegraph-partner/SKILL.md:Run these checks in order.plugins/codex/skills/codegraph-partner/SKILL.md:No install talk.plugins/codex/skills/codegraph-partner/SKILL.md:| | not_indexed (CLI present, no `.codegraph/` or `initialized: false`) | Offer one line: "run `codegraph init <path>` to index this repo".plugins/codex/skills/codegraph-partner/SKILL.md:Whenever you run `codegraph init` in any repository on the user's behalf, immediately read that repo's `.gitignore` and append a `.codegraph/` line if one is not already present.plugins/codex/skills/decision-model-setup/SKILL.md:That is the operator's command, and only the operator can run it: the key is operator-only, so the `brain_settings` tool refuses an agent's write to it with `operator_only_setting` on every machine, switched or not.plugins/codex/skills/decision-model-setup/SKILL.md:Ask the operator to run the command;plugins/codex/skills/decision-model-setup/SKILL.md:Does not install servers or download model weights.plugins/codex/skills/embeddings-setup/SKILL.md:Every run that uses it prints one stderr warning per endpoint.plugins/codex/skills/embeddings-setup/SKILL.md:If the install path missed it, force a rebuild:plugins/codex/skills/embeddings-setup/SKILL.md:bun pm ls | grep sqlite-vecplugins/codex/skills/embeddings-setup/SKILL.md:bun install --forceplugins/codex/skills/embeddings-setup/SKILL.md:When the index already exists and only some chunks lack vectors, price the work first with the dry run, then apply it:plugins/codex/skills/embeddings-setup/SKILL.md:Does not invoke `brew install` on the user's behalf.plugins/codex/skills/schema-author/SKILL.md:Preview the batch first with `schema_apply_mutations` (`dry_run=true`) or `o2b brain schema apply --dry-run --mutation ...`: it returns the pack that would result and its diff and writes nothing at all - no config write, no audit record, no lock file.plugins/codex/skills/schema-author/SKILL.md:It does not run the two checks that exist only because the apply writes: the vault-identity write guard, and the atomic writer's re-parse of the rendered YAML.plugins/codex/skills/schema-author/SKILL.md:Re-run lint/stats after mutation and report changed tokens plus any remaining findings.skills/brain-memory/SKILL.md:Read-only inspection (running `git log`, `o2b status`, `vault_health`).skills/brain-memory/SKILL.md:After scan, the source line becomes `@osb✓ [[sig-...]]` so a second run is idempotent.skills/codegraph-partner/SKILL.md:Run these checks in order.skills/codegraph-partner/SKILL.md:No install talk.skills/codegraph-partner/SKILL.md:| | not_indexed (CLI present, no `.codegraph/` or `initialized: false`) | Offer one line: "run `codegraph init <path>` to index this repo".skills/codegraph-partner/SKILL.md:Whenever you run `codegraph init` in any repository on the user's behalf, immediately read that repo's `.gitignore` and append a `.codegraph/` line if one is not already present.skills/decision-model-setup/SKILL.md:That is the operator's command, and only the operator can run it: the key is operator-only, so the `brain_settings` tool refuses an agent's write to it with `operator_only_setting` on every machine, switched or not.skills/decision-model-setup/SKILL.md:Ask the operator to run the command;skills/decision-model-setup/SKILL.md:Does not install servers or download model weights.skills/embeddings-setup/SKILL.md:Every run that uses it prints one stderr warning per endpoint.skills/embeddings-setup/SKILL.md:If the install path missed it, force a rebuild:skills/embeddings-setup/SKILL.md:bun pm ls | grep sqlite-vecskills/embeddings-setup/SKILL.md:bun install --forceskills/embeddings-setup/SKILL.md:When the index already exists and only some chunks lack vectors, price the work first with the dry run, then apply it:skills/embeddings-setup/SKILL.md:Does not invoke `brew install` on the user's behalf.skills/schema-author/SKILL.md:Preview the batch first with `schema_apply_mutations` (`dry_run=true`) or `o2b brain schema apply --dry-run --mutation ...`: it returns the pack that would result and its diff and writes nothing at all - no config write, no audit record, no lock file.skills/schema-author/SKILL.md:It does not run the two checks that exist only because the apply writes: the vault-identity write guard, and the atomic writer's re-parse of the rendered YAML.skills/schema-author/SKILL.md:Re-run lint/stats after mutation and report changed tokens plus any remaining findings.
Hooks (54)
hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" post-write-reminder; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook post-write-reminder; exit 0hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-agenda; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-agenda; exit 0hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" backlog-nudge; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook backlog-nudge; exit 0hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" log-catchup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook log-catchup; exit 0hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" view-render; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook view-render; exit 0hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" recall-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook recall-inject; exit 0hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" nav-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook nav-inject; exit 0hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" counterparty-brief; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook counterparty-brief; exit 0hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0hooks/hooks.json(PreToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-orient; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-orient; exit 0hooks/hooks.json(PreToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-host-backup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-host-backup; exit 0hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" stop-log-guardrail; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook stop-log-guardrail; exit 0hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" answer-quote-check; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook answer-quote-check; exit 0hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" hygiene-digest; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook hygiene-digest; exit 0hooks/hooks.json(SubagentStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0hooks/hooks.json(SubagentStop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json(SessionEnd):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0hooks/hooks.json(SessionEnd):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-promote; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-promote; exit 0hooks/hooks.json(PostCompact):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0hooks/hooks.json(PostCompact):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" post-write-reminder; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook post-write-reminder; exit 0plugins/codex/hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0plugins/codex/hooks/hooks.json(PostToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0plugins/codex/hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0plugins/codex/hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-agenda; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-agenda; exit 0plugins/codex/hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" backlog-nudge; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook backlog-nudge; exit 0plugins/codex/hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" log-catchup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook log-catchup; exit 0plugins/codex/hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" view-render; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook view-render; exit 0plugins/codex/hooks/hooks.json(SessionStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" recall-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook recall-inject; exit 0plugins/codex/hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" nav-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook nav-inject; exit 0plugins/codex/hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" counterparty-brief; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook counterparty-brief; exit 0plugins/codex/hooks/hooks.json(UserPromptSubmit):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" reground-deliver; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook reground-deliver; exit 0plugins/codex/hooks/hooks.json(PreToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-orient; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-orient; exit 0plugins/codex/hooks/hooks.json(PreToolUse):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" pretool-host-backup; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook pretool-host-backup; exit 0plugins/codex/hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" stop-log-guardrail; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook stop-log-guardrail; exit 0plugins/codex/hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" answer-quote-check; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook answer-quote-check; exit 0plugins/codex/hooks/hooks.json(Stop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" hygiene-digest; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook hygiene-digest; exit 0plugins/codex/hooks/hooks.json(SubagentStart):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" subagent-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook subagent-inject; exit 0plugins/codex/hooks/hooks.json(SubagentStop):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(SessionEnd):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0plugins/codex/hooks/hooks.json(SessionEnd):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" gap-promote; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook gap-promote; exit 0plugins/codex/hooks/hooks.json(PostCompact):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" active-inject; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook active-inject; exit 0plugins/codex/hooks/hooks.json(PostCompact):r="$CLAUDE_PLUGIN_ROOT"; if [ -n "$r" ] && [ -x "$r/scripts/o2b-hook" ]; then exec "$r/scripts/o2b-hook" session-capture; fi; command -v o2b-hook >/dev/null 2>&1 && exec o2b-hook session-capture; exit 0
Package scripts (1)
package.json(prepare):bun scripts/prepare.ts || exit 0
- Low risk: scripts-present (.githooks/pre-commit)
- Low risk: scripts-present (.githooks/pre-push)
- Low risk: network-instructions (plugins/codex/skills/codegraph-partner/SKILL.md:115)
- Low risk: scripts-present (scripts/prepare.ts)
- Low risk: network-instructions (skills/codegraph-partner/SKILL.md:115)
Attribution and licence
- First committed by
hermes-vps-agent
- Declared authors
- Open Second Brain contributors (declared in .claude-plugin/plugin.json)
- Open Second Brain contributors (declared in pyproject.toml)
- Publisher
- Serg Eroshe (Community)
- Source
- itechmeat/open-second-brain · commit 233b91d
- Licence
- MIT License (files served here)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
- Contributors
- solaitken, itechmeat, Yori940619, hermes-vps-agent, DanBennettUK
AutoGineer is not affiliated with or endorsed by hermes-vps-agent or Serg Eroshe.
Install from source
486 of its files are not served here, so there is no ZIP. itechmeat/open-second-brain at 233b91d