AutoGineer
Generated banner for Open Second Brain
Generated logo for Open Second Brain

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.
— the description by hermes-vps-agent

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.

Folders
FolderRoleFiles
.githubagent-config7
binscripts1
docsdocs774
hookshooks35
scriptsscripts22
skillsagent-instructions6
srcsource-code1496
templatestemplates23
teststests2101
.agentsfolder1
.ai-notesfolder1
.apbfolder87
.claude-pluginfolder2
.codex-pluginfolder1
.githooksfolder2
installfolder16
openclawfolder1
openspecfolder33
pluginsfolder21
schemasfolder5

The agent reads

The agent writes

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

  1. 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-push
    • 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
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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
    • 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
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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
    • 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 0
    • 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 0
    • 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 0
    • 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 0
    • 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
    • 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
    • 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 0
    • 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 0
    • 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
    • package.json: bun scripts/prepare.ts || exit 0
    • plugins/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
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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
    • plugins/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
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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 0
    • plugins/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
    • plugins/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
    • plugins/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 0
    • plugins/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 0
    • plugins/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
  2. 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

  3. 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 .-> Notes

Each 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| Pref

The 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

  1. Install Bun 1.1 or later: install/prerequisites.md.

  2. Install the plugin for your client (guides below), or get the o2b CLI: install/prerequisites.md.

  3. Create the vault files:

    o2b init       --vault /path/to/vault --name "My Second Brain"
o2b brain init --vault /path/to/vault

  4. Connect 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

ClientIntegrationGuide
Claude CodeMarketplace plugin: MCP servers and hooksinstall/claudecode.md
OpenAI CodexMarketplace plugin, then o2b install --target codex --applyinstall/codex.md
ChatGPT desktopReads the shared Codex config: o2b install --target codex --applyinstall/codex.md
Hermes AgentPlugin and memory providerinstall/hermes.md
OpenClawNative plugin, no MCPinstall/openclaw.md
opencodeo2b install --target opencode --apply: MCP servers and a native plugininstall/opencode.md
Grok Buildo2b install --target grok --apply: MCP servers and hooksinstall/grok.md
Cursoro2b install --target cursor --applyinstall/cursor.md
kiroo2b install --target kiro --applyinstall/kiro.md
GitHub Copilot CLIo2b install --target copilot-cli --applyinstall/copilot-cli.md
Gemini CLIo2b install --target gemini-cli --applyinstall/gemini-cli.md
ZCodeMCP servers added to its config by handinstall/zcode.md
Aidero2b install --target aider --apply: context file, no MCPinstall/aider.md
Pio2b install --target pi --apply: skill over the CLIinstall/pi.md
Any other MCP hosto2b install --target generic --apply --out - prints the server entriesinstall/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 rollback restores it: snapshots.

  • Attributed writes. o2b brain writes lists every note write by agent and device, writes revert plans a restore, o2b brain freeze stops all writers, and o2b brain log verify checks 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 through brain_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-key seeding the fan-out from mined entity mentions): session logs, coverage.

  • Hygiene. o2b brain hygiene scan finds contested, duplicate, stale and unused memories; apply runs only the findings you pick: maintenance.

  • Claim ledger. o2b brain truth ingest records 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 events recalls a windowed slice of the ledger, and truth state grounds an agent-stated claim with an anchoring verdict - committed, or reported back with reason codes. truth state accepts an optional opaque --sample-id naming 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 --apply to 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-export writes a one-file backup bundle: knowledge packs.

  • Secret custody. Credentials live encrypted in the vault's state dir behind a capability-gated store; $secret:NAME references resolve at the use sites, o2b brain secret unlock wraps the keyfile under a passphrase, and secret export/import move the store between installs as one passphrase-encrypted bundle: custody CLI.

  • Today view and note markers. o2b brain today, @osb loop and @osb set markers: Brain CLI.

  • Self-inspection. o2b version, o2b install --friction and o2b state status report 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; the embeddings-setup skill 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 a search_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_ENABLED and write_approval.ingest / OPEN_SECOND_BRAIN_WRITE_APPROVAL_INGEST_ENABLED (each falling back to the write_approval.enabled master, default off) stage note creates and ingest summary pages into Brain/pending/ beside the staged signals, where they stay out of the search index until an operator runs o2b brain pending list and applies or rejects them; write-path integrity.

  • A permissions document, absent by default. Brain/_permissions.yaml (an operator-edited vault file) resolves allow/ask/deny per agent, role and target for the write, ingest and owner-write actions; with the file absent every check behaves exactly as today. ask stages the write, deny refuses with the write-refused token and the next command o2b brain permissions show, and every ask/deny verdict lands in a queryable decision ledger under Brain/logs/decisions/; o2b brain permissions show dry-runs the decision table, ledger reads the rows; Brain CLI.

  • The owner-write gate, off by default. integrity.owner_scope_writes in Brain/_brain.yaml (off | warn | fail, default off) refuses a caller-named owner that differs from the caller's resolved identity on the preference and note lanes (warn allows and records one decision-ledger row); a document owner_write verdict composes most-restrictive-wins with the gate; write-time integrity.

  • Named MCP tokens, optional. o2b mcp token mint|rotate|revoke|list keeps 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-key stays valid as the operator master credential, and mcp_tokens_required / OPEN_SECOND_BRAIN_MCP_TOKENS_REQUIRED (default false) 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, and o2b 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: false suppresses the ambient extraction lane with a counted ambient-withheld event (absent keeps today's behavior), and guardrails.ambient_ttl_days stamps an expiration_date on 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 at Brain/decisions/open-<slug>.md; resolve mints the real type: decision page, discard closes 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

TopicPage
Mental model, vault layout, dream pass, safety propertiesdocs/how-it-works.md
Every CLI verb and flagdocs/cli-reference.md
MCP protocol, tools, writer splitdocs/mcp.md
Brain store: setup, sync, migration, the human viewdocs/brain-store.md
Architecture and configuration modeldocs/architecture.md
Updating (o2b update) and upgrade notesdocs/updating.md
Observability eventsdocs/observability.md
Metrics data contractdocs/metrics.md
Cross-project pointerdocs/cross-project-pointer.md
Scheduled Brain digest (Hermes cron)docs/hermes-cron.md
Stability policydocs/stability.md
Origin of the ideadocs/idea.md

Project

CHANGELOG · Security policy · Source on GitHub · MIT License

docs/metrics.md

Metrics layer - the dashboard data contract

Since v0.45.0 every run-level pass in Open Second Brain reports its numbers into one uniform, machine-readable layer under Brain/metrics/. This document is the stable on-disk contract for consumers - in particular the upcoming dashboard plugin - so they can read metrics without importing Open Second Brain internals.

Layout

One append-only JSONL file per surface PER DEVICE, named <surface>[.<device-id>].jsonl:

Brain/metrics/
├── index.jsonl                  # the shard with the empty device id
├── index.a1b2c3d4.jsonl         # one machine's shard
├── index.e5f6a7b8.jsonl         # another machine's shard
├── bridge_discovery.a1b2c3d4.jsonl
├── communities.a1b2c3d4.jsonl
├── recall_benchmark.a1b2c3d4.jsonl
├── self_tuning.a1b2c3d4.jsonl
├── self_heal_reindex.a1b2c3d4.jsonl
└── dream_stage.a1b2c3d4.jsonl

Surface names are lowercase snake_case ([a-z][a-z0-9_]*, max 64 chars); device ids are lowercase slugs ([a-z0-9-], max 32 chars). The vault is Syncthing-replicated, so a device only ever appends to the file its own id names - see "The per-device shard rule" in docs/observability.md. A file with no device suffix is the shard with the empty device id and is read exactly like any other.

A consumer must therefore group by surface, not by file name: strip an optional trailing .<device-id> segment before the .jsonl extension to get the surface, and read every file that maps to the surface it renders. Two names are never metric shards: a *.sync-conflict-* copy (Syncthing leftover; o2b brain doctor reports it) and any other unknown file in the directory, which must be ignored.

Record envelope

Every line is one JSON object:

{
  "schema": "o2b.metrics.v1",
  "surface": "recall_benchmark",
  "run_at": "2026-06-05T12:00:00Z",
  "payload": { "hit_at_k": 1, "mrr": 0.958 }
}

  • schema - envelope version. Evolution rule mirrors continuity records: additive optional payload fields do NOT bump the version; renames, removals, or semantic changes bump to o2b.metrics.v2.

  • surface - matches the file name with any .<device-id> shard suffix removed.

  • run_at - ISO-8601 UTC timestamp of the run the record describes.

  • payload - surface-specific object (fields below).

Records are RUN-LEVEL: one line per index run, discovery pass, benchmark, or tuning run. Per-query retrieval events stay in recall telemetry (docs/observability.md). Writes are O_APPEND single lines, so concurrent writers interleave instead of racing; readers must skip torn or non-object lines (the bundled listMetrics reader does). Keep payloads small (well under the platform pipe-buffer size, ~4 KiB) - O_APPEND atomicity is only guaranteed for short writes, and a metric record is a summary, not a report.

Surfaces and payload fields (v0.45.0)

SurfaceWriterPayload fields
indexevery non-empty index runadded, updated, deleted, alias_resolved, relation_violations, tier_drift
bridge_discoveryo2b brain bridges discover, MCP brain_bridges, maintenance laneproposals, scanned_candidates, vec_available, dismissed_total, min_similarity, max_proposals, lane (lane runs)
communitieso2b brain clusters run, MCP brain_clusters, maintenance lanerun record: communities, sizes, written, removed, min_size, lane (lane runs), batches / failed_batches (batched runs). Freshness record (--if-stale only, since v1.46.0): freshness, freshness_reason, newest_input_ms, oldest_output_ms, oldest_output_age_ms
recall_benchmarko2b brain benchmark run, MCP brain_benchmarktotal, k, expand, hit_at_k, mrr, misses
self_tuningo2b brain tune run, MCP brain_tunechosen, evaluated, best_mrr, dataset_hash
dream_stageo2b brain dream stage / apply, MCP brain_dream (since 1.0.0)action (stage/apply), run_id, proposals, sources, changed; apply adds new_unconfirmed, confirmed, retired counts
prompt_prefixdecision-panel commit (opt-in promptPrefixMetric), context-pack consume (opt-in promptPrefix)kind (write_session/context_pack), prefix_hash (sha-256 of the stable preamble), prefix_chars, call_count, stable_count
vault_vitalso2b brain vitalspreferences_scanned, domain_diversity, connectivity_index, orphan_count, gap_pressure
self_heal_upgradeo2b brain upgrade --self-heal (the detached worker ensureVaultCurrent starts)outcome (applied / failed), duration_ms, files (rewritten, or pending on failed), error (on failed). An attempt that finds nothing pending writes no row
self_heal_reindexensureVaultCurrent (parent) and o2b search reindex --self-heal <run-id> (child)parent row: decision (spawned / skipped_writer_lock), run_id (on spawned). Child row: outcome (completed / failed), run_id, duration_ms, error (on failed)
index_freshen (since v1.76.0)o2b search index --freshen <token> (the background run freshen on read starts)outcome (completed / failed), duration_ms, changed (on completed), error and failures (on failed). A row is written only when the run changed documents or failed
maintenance_spend (since v1.64.0)o2b brain maintenance run, MCP brain_maintenance (run)task (reindex), model (null when the config names none), tokens, estimated_usd, forced (force-cost overrode a positive gate), lane (always true: both front doors are the lane)
storage_usage (since v1.85.0)o2b brain storage, MCP brain_storage (every report invocation), and a maintenance-lane run the capacity gate skips (sampled before the skip, from the gate's own census)run_id, total_bytes, bytes_by_tier (per recoverability tier: vault-content, derived), measured (true when every surface answered), unmeasured (the surfaces refused, each with its reason). The series is the forecast's input: o2b brain storage reports its linear trend, and the run id is the idempotency key, so one invocation never writes a second row

Payload fields marked "(lane runs)" appear only on maintenance-lane emissions. All fields are additive-optional from a consumer's point of view: render what is present, ignore what is unknown.

self_heal_reindex is the one surface written by two processes. The post-upgrade rebuild is spawned detached with every stream ignored, so the parent records what it decided to do and the child records how it ended; the two pair on the run_id the parent mints and passes to the child on its command line. Not a pid: a pid is machine-local, and these rows sync, so two devices' pid spaces (and one device's pid reuse) pair rows from unrelated runs.

A spawned row with no terminal row beside it means only that no terminal outcome was recorded. The child may have been killed or reaped with its session; it may still be running (a full reindex takes minutes); it may have died before the recording was armed; or its own fail-soft append may have failed on a read-only vault or a full disk. The rows describe a per-device index from inside a synced vault, so a row says a self-heal ran on some device, never that this device's index is stale.

Reading

  • Newest records sit at the end of each file; the bundled reader (listMetrics(vault, {surface?, since?, limit?}) in src/core/brain/metrics.ts) returns newest-first and merges surfaces when none is specified.

  • External consumers (dashboards, scripts in other languages) should read the files directly: split on newlines, JSON.parse each line, skip lines that fail to parse or lack a string surface/run_at.

  • Metric emission is fail-soft everywhere: a metrics-layer problem never fails the pass that produced the numbers, so gaps in a file mean the run failed or predates the layer - not data corruption.

prompt_prefix: stability, not provider cache-hit rate

The prompt_prefix surface measures STRUCTURAL prefix stability - how many generation handoffs in one pass led with byte-identical preamble bytes (stable_count of call_count). It deliberately does NOT claim to measure a provider's cache-hit rate: the kernel never calls an LLM, so it cannot observe whether a provider actually reused a cached prefix. What it can guarantee, and what this metric reports, is that the kernel handed the agent a stable, cache-eligible prefix across the pass - the precondition a provider prefix cache rewards. The raw prompt is never stored; only the sha-256 hash and the code-point length of the prefix.

The genuine multi-call pass is the decision panel (every persona step and the synthesis share the Decision topic: frame, so a fully stable pass reports stable_count == call_count == personas + 1). A context-pack consume is a single-call pass over its stable request preamble. Both surfaces are opt-in and default off; the pass output is byte-identical when the gate is unset.

512 files · 486 not served here

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

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.ts
  • CLAUDE.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-mirrors
  • CLAUDE.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-vec
  • plugins/codex/skills/embeddings-setup/SKILL.md: bun install --force
  • plugins/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-vec
  • skills/embeddings-setup/SKILL.md: bun install --force
  • 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:
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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 0
  • 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
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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 0
  • plugins/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
GitHub avatar of hermes-vps-agenthermes-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