AutoGineer
Generated banner for Octobrain
Generated logo for Octobrain

Octobrain

Memory serverOfficial Muvon project

Created by Muvon

Published in Muvon/octobrain. Publisher page

20 GitHub stars

What it is

Persistent memory for AI assistants — semantic search, knowledge graph, and MCP server integration. Built in Rust.
— the description by Muvon

AutoGineer overview, from the brain’s own files

Octobrain provides long-term memory for AI assistants by storing insights, architecture decisions, and project knowledge. It functions as a CLI tool or an MCP server, allowing AI agents to persist context across sessions. The system uses vector embeddings for semantic search and supports hybrid search by combining vector similarity with BM25 full-text search. It includes features for auto-linking memories, managing knowledge bases via indexed files and URLs, and consolidating goal-related memories into summaries. The system is built in Rust and uses LanceDB for storage.

How it works

Memory model: Vector store

AutoGineer overview, from the brain’s own files

Octobrain stores memories and knowledge in a vector database. It uses embedding models to convert text into vectors for semantic retrieval. When a user or agent interacts with it, the system performs searches across stored memories and indexed knowledge sources. It supports project scoping based on Git remotes and allows for the creation of relationships between memories. The MCP server implementation enables integration with tools like Claude Desktop, allowing agents to call functions to memorize, remember, or search through indexed knowledge.

Folders
FolderRoleFiles
.githubagent-config2
scriptsscripts2
srcsource-code47
.cargofolder1
benchesfolder18
config-templatesfolder1

The agent reads

The agent writes

Requirements

Apps: Docker

Runtimes: Rust

Databases: Qdrant

API keys (by name): GOOGLE_API_KEY, JINA_API_KEY, OPENAI_API_KEY, VOYAGE_API_KEY

Works with: Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Kiro, OpenCode, Amp, Cline, JetBrains Junie, Devin (ex-Windsurf)

Set it up

  1. This brain runs code automatically: 1 script. Review Makefile before opening the folder in Claude Code. No step below turns a hook on for you.

    • Makefile: echo "$(YELLOW)Installing $(BINARY_NAME)...$(NC)"; cargo install --path .; echo "$(GREEN)$(BINARY_NAME) installed successfully$(NC)"
  2. Not scanned by AutoGineerThe author’s MCP configuration (README.md) 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/Muvon/octobrain/blob/bfb15d6772028f00207b757e883e2d1ddd3fb562/README.md
  3. Not scanned by AutoGineerThe author’s README also describes installing it from a clone of its repository. Read its install section: AutoGineer did not scan that path. https://github.com/Muvon/octobrain/blob/bfb15d6772028f00207b757e883e2d1ddd3fb562/README.md#development-setup
  4. Not scanned by AutoGineerThe author’s README also describes installing it with Homebrew (the author’s own tap). Read its install section: AutoGineer did not scan that path. https://github.com/Muvon/octobrain/blob/bfb15d6772028f00207b757e883e2d1ddd3fb562/README.md#installation
  5. Not scanned by AutoGineerThe author’s README also describes installing it with cargo. Read its install section: AutoGineer did not scan that path. https://github.com/Muvon/octobrain/blob/bfb15d6772028f00207b757e883e2d1ddd3fb562/README.md#installation
  6. Not scanned by AutoGineerThe author’s README also describes installing it from a clone of its repository. Read its install section: AutoGineer did not scan that path. https://github.com/Muvon/octobrain/blob/bfb15d6772028f00207b757e883e2d1ddd3fb562/README.md#installation
  7. Not scanned by AutoGineerThe author’s README also describes installing it with cargo. Read its install section: AutoGineer did not scan that path. https://github.com/Muvon/octobrain/blob/bfb15d6772028f00207b757e883e2d1ddd3fb562/README.md#quick-start

  8. Created by Muvon. Published in Muvon/octobrain. Licence: Apache License 2.0.

Usage

AutoGineer overview, from the brain’s own files

  • Store project insights and decisions for future retrieval
  • Search for relevant context across past conversations
  • Index documentation and web content for agent access
  • Connect related memories to form a knowledge graph
  • Integrate with AI assistants via the MCP protocol
“octobrain memory memorize --title "API Design" --content "Use REST for CRUD" --memory-type architecture”
Stores a new memory entry regarding API design patterns in the persistent store.
“octobrain memory remember "api design patterns"”
Performs a semantic search and returns relevant memories matching the query.
“octobrain knowledge index https://docs.rs/tokio/latest/tokio/”
Indexes the content of the provided URL into the knowledge base for future retrieval.

Documentation by Muvon

Octobrain

Persistent memory for AI assistants — store insights, decisions, and knowledge that survives across conversations.

Image: Crates.io Image: License Image: Rust Image: CI Image: Coverage

MCP Registry: mcp-name: io.github.Muvon/octobrain

Table of Contents

  • Why Octobrain?

  • Quick Start

  • Installation

  • Usage

  • Features

  • Benchmarks

  • Configuration

  • Memory Types

  • MCP Integration

  • Storage Locations

  • Contributing

  • License

Octobrain gives your AI assistant a long-term memory. Store code insights, architecture decisions, bug fixes, and knowledge — then retrieve them with semantic search in future sessions. Works as a CLI tool or as an MCP server for integration with Claude Desktop and other AI tools.

Why Octobrain?

AI assistants start every conversation with zero context. You explain your project, your preferences, your decisions — every single time. Octobrain breaks that cycle:

  • Persistent memory — Insights survive across sessions, not just within them

  • Semantic search — Find memories by meaning, not exact keywords

  • Auto-linking — Related memories connect automatically (Zettelkasten-style)

  • Knowledge indexing — Ingest docs, articles, and files for retrieval

  • MCP integration — Works with Claude Desktop and other MCP-compatible tools

Quick Start

# Install from crates.io
cargo install octobrain

# Store your first memory
octobrain memory memorize --title "API Design Pattern" \
  --content "Use REST for CRUD, GraphQL for complex queries" \
  --memory-type architecture --tags "api,design"

# Search memories
octobrain memory remember "how should I design APIs"

# Start MCP server for Claude Desktop integration
octobrain mcp

Installation

From crates.io (Recommended)
cargo install octobrain
From Source
# Clone and build
git clone https://github.com/muvon/octobrain.git
cd octobrain
cargo build --release

# Binary location
./target/release/octobrain --help
Docker
docker pull ghcr.io/muvon/octobrain:latest
Homebrew (macOS/Linux)
brew install muvon/tap/octobrain
Feature Flags

Octobrain supports multiple embedding providers:

FlagDescriptionAPI Key Required
fastembedLocal embeddings via FastEmbedNo
huggingfaceLocal embeddings via HuggingFaceNo
(default)Both fastembed + huggingfaceNo
(no features)API-based: Voyage, OpenAI, Google, JinaYes
# Build with local embeddings (default, no API keys needed)
cargo build --release

# Build with API-based embeddings only
cargo build --no-default-features --release

For API-based embeddings, set the appropriate environment variable:

  • VOYAGE_API_KEY for Voyage AI

  • OPENAI_API_KEY for OpenAI

  • GOOGLE_API_KEY for Google

  • JINA_API_KEY for Jina

Usage

Memory Management

Store and retrieve insights, decisions, and context:

All memory subcommands accept global flags:

  • --scope <string> — Override project scope (default: auto-detected from Git remote)

  • --role <string> — Filter by role (e.g. "developer", "reviewer")

# Store a memory
octobrain memory memorize --title "API Design" \
  --content "Use REST for CRUD, GraphQL for complex queries" \
  --memory-type architecture --tags "api,design"

# Search memories (semantic search)
octobrain memory remember "api design patterns"

# Multi-query search for broader coverage
octobrain memory remember "authentication" "security" "jwt"

# Get a memory by ID
octobrain memory get <id>

# Get recent memories
octobrain memory recent --limit 20

# Filter by type
octobrain memory by-type architecture --limit 10

# Filter by tags
octobrain memory by-tags "api,security"

# Find memories related to files
octobrain memory for-files "src/main.rs,src/lib.rs"

# Update a memory
octobrain memory update <id> --title "New Title" --add-tags "new-tag"

# Delete a memory
octobrain memory forget --memory-id <id>

# Get memories relevant to the current Git commit
octobrain memory current-commit

# Show memory statistics
octobrain memory stats

# Clean up old/low-importance memories
octobrain memory cleanup

# Compact tables and refresh indices (run when searches slow down)
octobrain memory maintenance

# ⚠️ Delete ALL memory data
octobrain memory clear-all --yes
Memory Consolidation

Close a goal and fold all its contributing memories into a consolidated summary:

# Consolidate a goal (Achieves-link sources → Consolidated state, importance dampened)
octobrain memory consolidate <goal-id> --summary "Final summary"

# Sleep consolidation: auto-cluster recent similar memories
octobrain memory sleep-consolidate --threshold 0.85 --min-size 3
Memory Relationships

Connect related memories for context-rich retrieval:

# Create a relationship between memories
octobrain memory relate <source-id> <target-id> \
  --relationship-type "depends_on" \
  --description "Source requires target to function"

# View relationships for a memory
octobrain memory relationships <memory-id>

# Find related memories through relationships
octobrain memory related <memory-id>

# Auto-link similar memories (Zettelkasten-style)
octobrain memory auto-link <memory-id>

# Explore memory graph
octobrain memory graph <memory-id> --depth 2
Knowledge Base

Index and search web content, docs, and files:

# Index a URL
octobrain knowledge index https://docs.rs/tokio/latest/tokio/

# Index a local file (.txt, .md, .pdf, .docx, .html)
octobrain knowledge index ./docs/architecture.md

# Search knowledge base
octobrain knowledge search "how to handle async tasks"

# Search within a specific source (auto-indexes if outdated)
octobrain knowledge search "spawn blocking" --source https://docs.rs/tokio/

# Read full content of a URL or local file
octobrain knowledge read https://docs.rs/tokio/latest/tokio/

# Search indexed content by regex pattern
octobrain knowledge match "spawn_blocking|block_in_place"

# Store raw text content
octobrain knowledge store "meeting-notes" --content "Discussion points..."

# List indexed sources
octobrain knowledge list --limit 20

# Show statistics
octobrain knowledge stats

# Delete a source
octobrain knowledge delete https://example.com/docs

# Delete stored content by key
octobrain knowledge delete-stored "meeting-notes"
Knowledge Boxes

Import and sync git-backed knowledge bundles scoped to your projects:

# Import a remote git repo as a knowledge box
octobrain box import https://github.com/org/docs-repo.git

# Import at global scope (visible in every project)
octobrain box import https://github.com/org/docs-repo.git --global

# Pull and re-index all subscribed boxes + local .box/ directories
# (the MCP server syncs each session's repos on first contact; agents run `knowledge` `sync` after editing .box/)
octobrain box sync

# List subscribed boxes
octobrain box list

# Remove a box
octobrain box remove github.com/org/docs-repo
MCP Server

Run as an MCP server for integration with Claude Desktop and other AI tools:

# Start with stdio transport (for Claude Desktop)
octobrain mcp

# Start with HTTP transport (for web-based tools)
octobrain mcp --bind 0.0.0.0:12345

Available MCP Tools:

ToolDescription
memorizeStore memories with metadata; optional related_to for inline relationships
rememberSemantic search with filters; returns 1-hop graph neighbors
forgetDelete memories (requires confirmation)
knowledgeUnified tool: search, store, delete, read, match, sync via command field; sync re-indexes knowledge boxes after .box/ edits
See MCP Integration for Claude Desktop setup.

Features

  • Semantic Search — Find memories by meaning using vector embeddings, not exact keyword matches

  • Hybrid Search — Combines BM25 full-text search with vector similarity for better results

  • Reranking Support — Pluggable cross-encoder reranking stage (provider-dependent)

  • Auto-Linking — Automatically connects semantically similar memories (Zettelkasten-style)

  • Temporal Decay — Ebbinghaus forgetting curve for importance management

  • Knowledge Indexing — Ingest URLs, PDFs, docs for retrieval

  • Project Scoping — Isolate memories per Git project or share across projects

  • Role Filtering — Tag memories by role (developer, reviewer, etc.)

  • Query Expansion (HyDE-lite) — Pseudo-relevance feedback for +10-30% recall on long-tail queries

  • MCP Protocol — Full MCP 2026-07-28 compliance for AI tool integration

Benchmarks

Retrieval quality of octobrain's knowledge system on standard BEIR datasets — nDCG@10, fully local, no LLM judge, using the harness's default embedder bge-small-en-v1.5 (384-dim, 33M params). Each corpus passage is indexed through octobrain's real retrieval path and scored against the official qrels (metrics reproduce pytrec_eval).

Datasetoctobrain vectoroctobrain hybridBM25¹bge-small-en-v1.5²
SciFact (5.2K docs, 300 q)0.7220.7420.6650.713
NFCorpus (3.6K docs, 323 q)0.3410.3630.3250.343

  • vector = dense-only retrieval; reproduces the embedder's published BEIR numbers (validates the harness).

  • hybrid = BM25 + vector fused with Reciprocal Rank Fusion (k=60) — octobrain's default. Adds +2 nDCG@10 over the bare embedding and beats classic BM25 on both datasets.

¹ Canonical BM25 from the BEIR paper (Anserini/Lucene, k1=0.9 b=0.4). ² From the bge-small-en-v1.5 model card (MTEB).

Scope: this measures the ranking layer (embedding + BM25 fusion + reranking). BEIR passages are pre-chunked, so octobrain's chunking strategy is not exercised here.

⚠️ Reranker status: The cross-encoder reranker is currently a no-op with fastembed models (byte-identical results to hybrid-only). Rerank is excluded from the numbers above pending investigation. See benches/README.md for details.

Reproduce (downloads the datasets, builds a release binary, runs fully offline):

cd benches && bash scripts/run_retrieval.sh

Configuration

Configuration is stored in ~/.local/share/octobrain/config.toml. The template written on first run defines every option with sensible defaults, but loading is strict — a field you delete by hand causes startup to fail rather than falling back to a default.

Override the config location with OCTOBRAIN_CONFIG_PATH=/path/to/config.toml.

Key Settings
SectionOptionDefaultDescription
[embedding]modelfastembed:Qdrant/all-MiniLM-L6-v2-onnxEmbedding model (provider:model format). Default is a local fastembed model — no API key, runs on CPU.
[search]similarity_threshold0.3Minimum relevance (0.0-1.0)
[search.hybrid]enabledtrueEnable BM25 + vector fusion
[search.reranker]enabledtrueEnable cross-encoder reranking
[search.hyde]enabledtruePseudo-relevance feedback query expansion
[memory]max_memories10000Maximum stored memories
[memory]auto_linking_enabledtrueAuto-connect similar memories
[knowledge]chunk_size1200Characters per chunk
[embedding]batch_size32Texts embedded per batch
[embedding]timeout_secs30Embedding call timeout (0 = no timeout)
[search]max_results50Hard ceiling on results from any search
[search.reranker]modelfastembed:jina-reranker-v2-base-multilingualCross-encoder model
[search.reranker]top_k_candidates50Candidates retrieved before reranking
[search.hyde]top_k3Neighbors averaged for the centroid
[search.hyde]alpha0.5Blend weight on the original query embedding
[memory]max_search_results50Default page size when no limit is given
[memory]sleep_consolidation_enabledtrueLazy sleep consolidation on manager init
[memory]sleep_consolidation_interval_hours24Hours between sleep-consolidation passes
[knowledge]outdating_days15Days before indexed content is reindexed on search
[knowledge]max_results5Results returned from knowledge search
Embedding Providers
[embedding]
# Local models (no API key, runs on CPU, model auto-downloaded on first use)
model = "fastembed:Qdrant/all-MiniLM-L6-v2-onnx"                       # Default: 384-dim quantized, ~125MB resident
model = "fastembed:nomic-ai/nomic-embed-text-v1.5"                      # 768-dim, 8192-ctx, ~550MB weights, highest quality
model = "fastembed:BAAI/bge-small-en-v1.5"                              # 384-dim, ~62 MTEB, fast + good quality
model = "fastembed:sentence-transformers/all-MiniLM-L6-v2-quantized"  # Smallest (~22MB), fastest
model = "fastembed:BAAI/bge-base-en-v1.5"                              # Larger (~440MB), higher quality
model = "fastembed:intfloat/multilingual-e5-small"                     # Multilingual

# Cloud providers (require API keys, generally higher quality)
model = "voyage:voyage-3.5-lite"          # VOYAGE_API_KEY
model = "openai:text-embedding-3-small"   # OPENAI_API_KEY
model = "google:text-embedding-004"       # GOOGLE_API_KEY
model = "jina:jina-embeddings-v3"         # JINA_API_KEY
Full Configuration

See config-templates/default.toml for all available options with documentation.

Memory Types

Organize memories by category for better filtering:

TypeUse For
codeCode patterns, solutions, implementations
architectureSystem design, decisions, patterns
bug_fixBug fixes, troubleshooting, solutions
featureFeature specs, implementations
documentationDocs, explanations, knowledge
user_preferenceSettings, preferences, workflows
decisionProject decisions, trade-offs
learningTutorials, notes, education
configurationSetup, config, deployment
testingTest strategies, QA insights
performanceOptimizations, benchmarks
securityVulnerabilities, fixes, considerations
validationIdea/product validation, hypothesis testing
researchTechnical/market research, analysis
workflowSOPs, playbooks, process descriptions
requirementBusiness requirements, specs, constraints
designUI/UX decisions, wireframes, system design
integrationAPI integrations, third-party services
communicationStakeholder updates, team decisions
processDeployment procedures, runbooks, operations
insightGeneral insights, tips
goalTask/intent anchors for consolidation workflow

MCP Integration

Claude Desktop Setup

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "octobrain": {
      "command": "/path/to/octobrain",
      "args": ["mcp"]
    }
  }
}

Restart Claude Desktop. Octobrain tools will be available in your conversations.

HTTP Transport

For web-based integrations:

octobrain mcp --bind 0.0.0.0:12345

The server exposes endpoints at /mcp for MCP protocol communication.

Storage Locations

Data is stored in platform-specific directories:

PlatformLocation
macOS~/.local/share/octobrain/
Linux~/.local/share/octobrain/ or $XDG_DATA_HOME/octobrain/
Windows%APPDATA%\octobrain\

Project-specific memories are isolated by normalized Git remote URL (e.g., github.com/org/repo).

Contributing

Contributions are welcome! Please:

  1. Fork the repository

  2. Create a feature branch (git checkout -b feature/amazing-feature)

  3. Run cargo fmt --all to format code

  4. Run cargo clippy and fix all warnings

  5. Run cargo test --no-default-features

  6. Submit a pull request

Development Setup
# Clone and build
git clone https://github.com/muvon/octobrain.git
cd octobrain
cargo build --no-default-features

# Run tests
cargo test --no-default-features

# Run clippy
cargo clippy --no-default-features

License

Apache-2.0 — see LICENSE for details.

Credits

Developed by Muvon Un Limited.

CHANGELOG.md

Changelog

[0.15.2] - 2026-11-08

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.15.1] - 2026-11-03

🔧 Improvements & Optimizations

  • dependencies: refresh dependency versions 999899c1

  • workflows: pin GitHub Actions to commit SHAs 92867b26

[0.15.0] - 2026-10-28

📋 Release Summary

MCP knowledge box synchronization is now supported, with goal and closes relationships for memories. Memory rewrites handle missing role columns, visibility is respected across scopes, and MCP memory scope behavior is clarified.

✨ New Features & Enhancements

  • mcp: support MCP knowledge box synchronization b4d2f8da

  • mcp: add goal and closes memory relationships dd50b92b

🔧 Improvements & Optimizations

  • dependencies: update octolib and locked dependencies 8cef7b78

🐛 Bug Fixes & Stability

  • memory: handle missing role columns in rewrites 2b007f0e

  • memory: respect memory visibility across scopes 4a76b66a

  • mcp: clarify memory scope behavior 8e1a3f35

[0.14.10] - 2026-10-25

🔧 Improvements & Optimizations

  • dependencies: update locked dependency versions e288aaec

  • mcp: upgrade rmcp to 3.7.0 f56a83af

  • dependencies: update octolib to 0.45.3 cc0819db

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.14.9] - 2026-10-24

📋 Release Summary

Embedding requests now retry after an initial transport failure and recover when embedding owners are unavailable.

🐛 Bug Fixes & Stability

  • embedding: retry after initial transport failure 3b014469

  • embedding: recover from unavailable embedding owners be4007d0

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.14.8] - 2026-10-20

🔧 Improvements & Optimizations

  • format Rust code at 120 columns fbd3a56f

  • release: inherit secrets in release workflow b906f1c3

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.14.7] - 2026-10-11

📋 Release Summary

Scoped session memory contexts are now supported, with scopes resolved per session and derived from work directories.

✨ New Features & Enhancements

  • mcp: support scoped session memory contexts e05c5028

🔧 Improvements & Optimizations

  • dependencies: refresh locked dependency versions 2436d3ff

🐛 Bug Fixes & Stability

  • mcp: resolve MCP scopes per session 4fe4bf24

  • mcp: derive session scopes from work directories ca75ff7c

[0.14.6] - 2026-10-08

🔧 Improvements & Optimizations

  • dependencies: update locked crate versions 69555d41

  • cargo: enable Metal acceleration by default 79dea71b

  • toolchain: upgrade Rust toolchain to 1.99.0 372290c2

[0.14.5] - 2026-10-06

🔧 Improvements & Optimizations

  • dependencies: update Rust dependencies 1dd8b983

[0.14.4] - 2026-09-30

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.14.3] - 2026-09-27

🔧 Improvements & Optimizations

  • dependencies: update dependency requirements and lockfile 15c98f41

[0.14.2] - 2026-09-27

📋 Release Summary

Modern MCP clients now receive cache hints correctly. MCP handler metadata has been switched to ServerConfig.

🔧 Improvements & Optimizations

  • mcp: switch handler metadata to ServerConfig aa7c2ff9

🐛 Bug Fixes & Stability

  • mcp: support cache hints for modern clients 2a369b93

[0.14.1] - 2026-09-18

📋 Release Summary

This release improves project guidance, setup instructions, and maintenance documentation for a clearer user experience (00d76317, 6952568d, 444fb8e7). Rust dependencies were refreshed to keep the project current (e56f7a8f).

📚 Documentation & Examples

  • agents: consolidate project guidance 00d76317

  • project: clarify setup and maintenance 444fb8e7

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.14.0] - 2026-09-14

📋 Release Summary

This release adds support for sharing embedding models across processes (931ba69d). It improves local model handling by updating the default model and caching providers, along with refreshed dependencies for improved maintenance and compatibility (39eac2d7, 6704baaf, 125123e9, 5f4aafb1, 8c5f952b).

✨ New Features & Enhancements

  • embedding: share models across processes 931ba69d

🔧 Improvements & Optimizations

  • providers: cache local model providers 6704baaf

🐛 Bug Fixes & Stability

  • embedding: switch default model locally 39eac2d7

🔄 Other Changes

3 maintenance, dependency, and tooling updates not listed individually.

[0.13.2] - 2026-09-11

📋 Release Summary

Updated dependency versions and lockfiles to keep the project’s configuration current and builds reproducible (0831d14e, 191cde5b).

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.13.1] - 2026-09-04

📋 Release Summary

Updated locked dependencies for improved project reliability (6d3afb44). CI now cancels superseded runs, helping changes receive feedback more efficiently (ea678c31).

🔧 Improvements & Optimizations

  • workflow: cancel superseded CI runs ea678c31

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.13.0] - 2026-09-04

📋 Release Summary

This release adds a maintenance command for managing memory state (3df1717f). Memory maintenance is more reliable, with improved access-write handling and retry behavior (19c1429f), alongside optimized release builds and updated dependencies (4752013d, c1d4300d).

✨ New Features & Enhancements

  • memory: expose maintenance command 3df1717f

🔧 Improvements & Optimizations

  • toolchain: remove Rust toolchain pin 2a4289cf

🐛 Bug Fixes & Stability

  • memory: throttle access writes and retry maintenance 19c1429f

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.12.2] - 2026-09-02

📋 Release Summary

This release updates octolib and its transitive dependencies to newer versions (e5638614). No new user-facing features are included.

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.12.1] - 2026-08-31

📋 Release Summary

Security was improved by addressing 16 vulnerable dependencies in the project’s requirements (8eab1210). Supporting libraries and the Rust toolchain were updated, and coverage reporting was refined as part of ongoing maintenance (f370bd4c, b848ceaf, 13a8ce67, 11ca6871, 3416d59d).

🔧 Improvements & Optimizations

  • toolchain: update Rust version to 1.98.0 b848ceaf

  • coverage: configure coverage reporting 13a8ce67

🐛 Bug Fixes & Stability

  • security: fix(deps): 16 vulnerable dependencies in requirements.txt 8eab1210

🔄 Other Changes

3 maintenance, dependency, and tooling updates not listed individually.

[0.12.0] - 2026-08-29

📋 Release Summary

Added MCP tool annotations and verification coverage, while improving existing query handling and tool descriptions for a clearer, more consistent experience (671deac4, ee02a0bc, 1f3561d6, 07fa5d08, 51da279d). Updated the README with CLI features and setup guidance, along with refreshed dependency versions and lockfile updates (f4a78c87, 5d688f19, e0797172, 354842e6).

✨ New Features & Enhancements

  • mcp: add tool annotations and verification test 671deac4

🔧 Improvements & Optimizations

  • mcp: move parse_query_arg to standalone function ee02a0bc

  • mcp: improve query argument parsing in memory tool 1f3561d6

  • mcp: introduce AnnotationRow type in tests 51da279d

  • mcp: update tool annotations and descriptions 07fa5d08

📚 Documentation & Examples

  • readme: document CLI features and setup f4a78c87

🔄 Other Changes

3 maintenance, dependency, and tooling updates not listed individually.

[0.11.1] - 2026-08-22

📋 Release Summary

This release improves MCP tool schemas and clarifies knowledge tool URL restrictions (d4268122, 26b2d382). Additionally, system dependencies have been updated to ensure stability (dd25097e).

🔧 Improvements & Optimizations

  • mcp: strip null variants from tool schemas d4268122

  • mcp: clarify knowledge tool url restrictions 26b2d382

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.11.0] - 2026-08-17

📋 Release Summary

This release introduces improved knowledge retrieval by adding support for accept headers in URL requests (58d56e5a). Additionally, system stability and performance have been enhanced through updated core dependencies and streamlined release workflows (d972c7b3, b596be4c, bd7c7b3d, f80654ff).

✨ New Features & Enhancements

  • knowledge: add accept header to url requests 58d56e5a

🔧 Improvements & Optimizations

  • release: add npm publish step to workflow f80654ff

🔄 Other Changes

3 maintenance, dependency, and tooling updates not listed individually.

[0.10.2] - 2026-08-04

📋 Release Summary

This release includes routine dependency updates to ensure optimal system stability and security (c242f277).

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.10.1] - 2026-08-03

📋 Release Summary

This release improves overall system performance through an optimized knowledge database compaction strategy (593c2f7c). These enhancements ensure more efficient memory management and improved stability for AI conversation states.

🔧 Improvements & Optimizations

  • knowledge: optimize database compaction strategy 593c2f7c

[0.10.0] - 2026-08-01

📋 Release Summary

This release introduces session context management for improved AI conversation states (3a17d8a0) and implements versioned configuration migrations to ensure seamless updates (58f158ec). General system stability and performance have been enhanced through updated dependencies and refined configuration logic (4ca672e7, b9509012, 3c28d4ad, 7da7fa4e).

✨ New Features & Enhancements

  • mcp: implement session context and update deps 3a17d8a0

  • config: implement versioned configuration migration 58f158ec

🔧 Improvements & Optimizations

  • config: reformat long lines for readability 4ca672e7

  • config: migrate configuration logic to octolib 3c28d4ad

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.9.4] - 2026-07-26

📋 Release Summary

This release improves knowledge management performance through asynchronous operations (9591da0d) and updates core system dependencies for better stability (60ed412f, 833f33ef). Additionally, a fix ensures more reliable embedding provider integrations (6aac8f7a).

🔧 Improvements & Optimizations

  • knowledge: make git operations asynchronous 9591da0d

🐛 Bug Fixes & Stability

  • embedding: handle provider response tuples 6aac8f7a

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.9.3] - 2026-07-17

📋 Release Summary

This release includes routine maintenance to ensure system stability and security through updated project dependencies (1e848fec).

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.9.2] - 2026-07-17

📋 Release Summary

This release improves MCP tool integration by optimizing schema structures and refining documentation for better usability (ea8990a6).

🐛 Bug Fixes & Stability

  • mcp: flatten tool schemas and refine docs ea8990a6

[0.9.1] - 2026-07-06

📋 Release Summary

This release improves system integration through automated MCP registry publishing and updated configuration schemas (377345b8, c5790756, 1501e14a). General stability and performance have been enhanced via comprehensive dependency updates across Rust and core libraries (ade92bf4, f860712f, db6c8a3a).

🔧 Improvements & Optimizations

  • config: remove placeholder package definition e5b6774b

  • release: specify runner for homebrew notification 1501e14a

  • release: automate MCP registry publishing 377345b8

  • server: add crates.io registry base URL f8d725fd

  • mcp: update registry identifier and config schema c5790756

🔄 Other Changes

3 maintenance, dependency, and tooling updates not listed individually.

[0.9.0] - 2026-06-22

📋 Release Summary

This release introduces advanced retrieval capabilities, including RRF-fuse multi-query search, git-backed knowledge boxes, and expanded filtering options for memory management (b9b8ba0e, ac538ad0, 62cc2784). System performance and reliability are improved through refined search configurations, updated dependency pinning, and a more robust multi-arch deployment pipeline (e4302fb4, 8ffe8082, 207ec20c). Several bug fixes enhance search accuracy, reranking logic, and scope assignment across sessions (31c4c801, 6165cf3e, 7500f60d).

✨ New Features & Enhancements

  • bench: implement BEIR retrieval benchmarking 4ebc1c48

  • config: wire search.similarity_threshold and search.max_results into retrieval e4302fb4

  • memory: RRF-fuse multi-query retrieval and honor Supersedes edges b9b8ba0e

  • mcp: expose temporal and relevance filters on remember 62cc2784

  • knowledge: implement git-backed knowledge boxes ac538ad0

  • config: add timeouts for embeddings and reranker 8ffe8082

🔧 Improvements & Optimizations

  • core: move module declarations to library crate 49e722bb

  • memory: spawn initialization tasks in background 3ffcbd80

  • memory: replace project identifiers with scopes 59b42389

  • memory: rename project to scope across system 249da8b8

  • release: add multi-arch Docker build and push 207ec20c

🐛 Bug Fixes & Stability

  • search: reranker limit, RRF normalization, archived exclusion, PRF guard 31c4c801

  • mcp: return full parent section from knowledge search 6165cf3e

  • memory: allow empty scope in predicate filters c6b3a43e

  • mcp: assign correct scope to session 7500f60d

📚 Documentation & Examples

  • mcp: guide agents to create supersedes links on knowledge updates fe52b977

  • memory: add timeout example to reranker config 17e77ef5

🔄 Other Changes

5 maintenance, dependency, and tooling updates not listed individually.

[0.8.0] - 2026-06-07

📋 Release Summary

This release introduces automatic project discovery and the ability to specify custom configuration paths via environment variables (8aa684c3, 54907257). Additionally, MCP performance and reliability have been improved through optimized tool listing and refined locking logic (d1f1c3da, 85956ee3).

✨ New Features & Enhancements

  • mcp: add automatic project discovery and ID derivation 8aa684c3

  • config: allow custom config path via env var 54907257

🔧 Improvements & Optimizations

  • mcp: decouple project and role locking logic 85956ee3

  • mcp: optimize tool listing and memory provider d1f1c3da

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.7.0] - 2026-06-03

📋 Release Summary

This release introduces advanced memory consolidation and persistence features, including automated goal anchoring, half-life decay, and "sleep" clustering for improved long-term retention (434f28dd, b37de658, 8b115380, d9f10bf4, 230cb4ce). Search capabilities have been significantly enhanced through HyDE-lite query expansion and a new integrated SQL module (a8fde461, de606fc5). Additionally, we have streamlined the MCP toolset, implemented the LongMemEval benchmarking framework, and optimized overall system performance and stability (6733a00b, d988af72, 92059bdd, 9fdda3ac).

✨ New Features & Enhancements

  • core: add sql module de606fc5

  • bench: add checkpointing and input padding to longmemeval 92059bdd

  • bench: implement LongMemEval benchmarking framework d988af72

  • memory: automate goal consolidation via closes relation 434f28dd

  • mcp: narrow MCP surface from 8 to 5 tools 6733a00b

  • memory: autonomous lazy sleep consolidation + HyDE default-on d9f10bf4

  • memory: sleep consolidation — batch-cluster recent similar memories 8b115380

  • memory: goal-anchored consolidation, lifecycle state, MCP+CLI 230cb4ce

  • search: add HyDE-lite (PRF / Rocchio) query expansion a8fde461

  • memory: implement half-life decay and persistence b37de658

🔧 Improvements & Optimizations

  • sql: centralize SQL literal escaping 9d98b535

  • memory: centralize utilities and harden sql 59b04f9b

  • config: rename text_model to model 08ba7365

  • ci: fix aarch64 compilation and update default models 6511ee43

  • ci: optimize build pipeline and update embeddings 20276d25

  • memory: implement periodic LanceDB maintenance 9fdda3ac

  • memory: implement async auto-linking and graph retrieval 4cbae3ac

  • workflow: migrate pr brief to reusable workflow 5a434a67

📚 Documentation & Examples

  • guide: expand development guide and architecture details b6b54d0c

  • mcp: update documentation and tool instructions b0f5bfae

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.6.1] - 2026-05-14

📋 Release Summary

This release introduces a dedicated production release profile and updated dependencies to ensure optimal performance and stability (3063c17b). These configuration improvements streamline the build process and enhance the overall reliability of the memory management system.

🔄 Other Changes

1 maintenance, dependency, and tooling update not listed individually.

[0.6.0] - 2026-05-03

📋 Release Summary

This release introduces advanced content retrieval capabilities, including regex pattern matching and full content extraction tools for indexed knowledge (b4c6e800, 0ca75b74). System reliability and performance are significantly improved through optimized memory streaming, stricter path validation, and enhanced vector dimension handling (95f4deb4, 87df649d, 6f831de7). Additionally, the update streamlines the toolset and provides expanded documentation for configuration and development (104c0b59, 069d0495, a44ef316).

✨ New Features & Enhancements

  • knowledge: add regex pattern matching for indexed content b4c6e800

  • knowledge: implement read command for full content extraction 0ca75b74

🔧 Improvements & Optimizations

  • mcp: remove auto_link tool 104c0b59

  • knowledge: stream query results to limit memory 95f4deb4

  • knowledge: simplify logic and improve safety 2963f38e

🐛 Bug Fixes & Stability

  • knowledge: use platform temp dir in tests 201d305f

  • knowledge: reject directory paths as sources 87df649d

  • vector: ensure sub-vectors divide dimension 6f831de7

  • knowledge: normalize source uris and match output 4b154ce1

📚 Documentation & Examples

  • instructions: rewrite development guide for clarity a44ef316

  • knowledge: add read and match tool documentation 921c9d7e

  • config: expand memory and knowledge settings 069d0495

🔄 Other Changes

3 maintenance, dependency, and tooling updates not listed individually.

[0.5.1] - 2026-04-19

📋 Release Summary

This release improves system stability by refining memory cleanup logic to prevent errors when project keys are missing (595318eb). Additionally, core dependencies and internal workflows have been updated to enhance overall performance and security (353f6fc4, afe734ca).

🐛 Bug Fixes & Stability

  • memory: skip cleanup without project key 595318eb

🔄 Other Changes

2 maintenance, dependency, and tooling updates not listed individually.

[0.5.0] - 2026-04-08

📋 Release Summary

This release introduces local file indexing capabilities to the knowledge system (breaking change), enabling direct interaction with local files. Memory management has been significantly enhanced with new product and workflow memory categories, session-scoped storage, and automatic stale reference cleanup. The MCP protocol implementation has been upgraded to the official rmcp SDK, along with various dependency updates and documentation improvements.

🚨 Breaking Changes

⚠️ Important: This release contains breaking changes that may require code updates.

  • knowledge: support local file indexing 0ab5a13f

✨ New Features & Enhancements

  • memory: add stale file reference cleanup 46c8827d

  • knowledge: add session-scoped storage and commands 21216453

  • memory: add product and workflow memory type categories 04b145a1

  • mcp: replace custom server with official rmcp SDK 1f581537

🔧 Improvements & Optimizations

  • memory: add git-aware stale reference cleanup be812684

  • knowledge: use std::slice::from_ref for single-element test slices 21f9da28

  • legal: apply copyright header standards 556b1228

  • mcp: use builder pattern for ServerInfo construction 8041b71a

  • mcp: rename rmcp_server to server and add typed schemas 56b3b6d9

📚 Documentation & Examples

  • restructure README for clearer onboarding 78918bd1

🔄 Other Changes

5 maintenance, dependency, and tooling updates not listed individually.

[0.4.2] - 2026-03-21

📋 Release Summary

This release updates internal dependencies and upgrades the Rust toolchain to version 1.94.0, ensuring improved performance and compatibility.

🔄 Other Changes

  • deps: update Cargo.lock 5b758fa8

  • upgrade Rust toolchain to 1.94.0 c6c56997

📊 Release Summary

Total commits: 2 across 1 categories

🔄 2 other changes - Maintenance & tooling

[0.4.1] - 2026-03-15

📋 Release Summary

This release streamlines cross-project memory queries by making project keys optional, allowing easier access to shared context across workspaces (4ccc1cb0). Additionally, automated Homebrew tap notifications ensure faster availability of future updates for macOS users (cae97de5).

🔧 Improvements & Optimizations

  • memory: make project_key optional for cross-project queries 4ccc1cb0

🔄 Other Changes

  • release: add homebrew tap notification job cae97de5

📊 Release Summary

Total commits: 2 across 2 categories

🔧 1 improvement - Better performance & code quality 🔄 1 other change - Maintenance & tooling

[0.4.0] - 2026-03-14

📋 Release Summary

This release introduces configurable knowledge and memory settings alongside automatic index optimization for improved performance (6d083380, d3d4c3e5). Session management is enhanced with locked project and role assignments during initialization (4ca28abd), while memory operations are streamlined for better efficiency and clarity (06c352fb, 7008ec38, 039c8f9c).

✨ New Features & Enhancements

  • config: add knowledge and memory configuration 6d083380

  • mcp: lock session project and role on initialize 4ca28abd

  • vector: add automatic index optimization d3d4c3e5

🔧 Improvements & Optimizations

  • memory: atomic upsert with merge_insert 06c352fb

  • mcp: remove token truncation from memory tools 7008ec38

  • mcp: simplify memory tool descriptions 039a8f9c

🔄 Other Changes

  • git: ignore mcpregistry temporary files 399431ef

📊 Release Summary

Total commits: 7 across 3 categories

✨ 3 new features - Enhanced functionality 🔧 3 improvements - Better performance & code quality 🔄 1 other change - Maintenance & tooling

[0.3.0] - 2026-03-13

📋 Release Summary

This release introduces confidence scoring and relationship tools for smarter memory management, plus enhanced search with parent content tracking and reranker support (ab2d791b, 502cbe62, 98c7e2f8). The MCP server gains auto-link and memory-graph capabilities with optional HTTP transport (f201c7d4, d7787b76). Multiple fixes improve search accuracy, data isolation, and cross-platform stability (b1524de0, 84dc6854, 0b1df7ee).

✨ New Features & Enhancements

  • memory: add confidence scoring and relationship tools ab2d791b

  • mcp: add auto_link and memory_graph tools with enhanced schema f201c7d4

  • mcp: add HTTP transport option d7787b76

  • knowledge: add parent content tracking for search context 502cbe62

  • memory: activate reranker for hybrid and vector search 98c7e2f8

🔧 Improvements & Optimizations

  • storage: consolidate to shared memory database 3e0b1b8d

  • hybrid: switch to native lancedb rrf fusion df9497d7

  • knowledge: improve HTML extraction with readability 090670c1

🐛 Bug Fixes & Stability

  • server: align MCP server manifest with latest schema b1524de0

  • server: shorten description in server manifest f3ff987d

  • memory: add missing id field to relationships table 54b426c1

  • memory: scope delete operations to project key 84dc6854

  • memory: remove keyword search from hybrid query 8e68099b

  • ci: enable default features and fix Windows static CRT build 0b1df7ee

🔄 Other Changes

  • deps: upgrade html parsing and text extraction libraries 19352773

  • deps: bump octolib to 0.10.4 80de4030

  • release: fix musl builds by disabling default features a37aacb6

  • release: 0.3.0 bb3f9b98

  • deps: upgrade datafusion to 51.0.0 and arrow to 57.3.0 ec4f322e

  • disable fastembed on Windows builds 1b263d44

  • ci: install protoc using setup-protoc action 8cac4795

  • chunker: fix extract_title method name in tests f8664956

  • deps: upgrade octolib to 0.10.0 c86805f1

  • deps: bump octolib to 0.9.3 d24505c8

📊 Release Summary

Total commits: 24 across 4 categories

✨ 5 new features - Enhanced functionality 🔧 3 improvements - Better performance & code quality 🐛 6 bug fixes - Improved stability 🔄 10 other changes - Maintenance & tooling

[0.3.0] - 2026-03-12

📋 Release Summary

This release introduces enhanced memory management with auto-linking capabilities and improved search functionality through hybrid vector search with reranking (f201c7d4, 98c7e2f8, 502cbe62). The system now supports HTTP transport for broader integration options and features consolidated database architecture for improved performance (d7787b76, 3e0b1b8d). Multiple bug fixes enhance data integrity, project scoping, and cross-platform compatibility (54b426c1, 84dc6854, 0b1df7ee).

✨ New Features & Enhancements

  • mcp: add auto_link and memory_graph tools with enhanced schema f201c7d4

  • mcp: add HTTP transport option d7787b76

  • knowledge: add parent content tracking for search context 502cbe62

  • memory: activate reranker for hybrid and vector search 98c7e2f8

🔧 Improvements & Optimizations

  • storage: consolidate to shared memory database 3e0b1b8d

  • hybrid: switch to native lancedb rrf fusion df9497d7

  • knowledge: improve HTML extraction with readability 090670c1

🐛 Bug Fixes & Stability

  • memory: add missing id field to relationships table 54b426c1

  • memory: scope delete operations to project key 84dc6854

  • memory: remove keyword search from hybrid query 8e68099b

  • ci: enable default features and fix Windows static CRT build 0b1df7ee

🔄 Other Changes

  • deps: upgrade datafusion to 51.0.0 and arrow to 57.3.0 ec4f322e

  • disable fastembed on Windows builds 1b263d44

  • ci: install protoc using setup-protoc action 8cac4795

  • chunker: fix extract_title method name in tests f8664956

  • deps: upgrade octolib to 0.10.0 c86805f1

  • deps: bump octolib to 0.9.3 d24505c8

📊 Release Summary

Total commits: 17 across 4 categories

✨ 4 new features - Enhanced functionality 🔧 3 improvements - Better performance & code quality 🐛 4 bug fixes - Improved stability 🔄 6 other changes - Maintenance & tooling

[0.2.0] - 2026-02-16

📋 Release Summary

This release introduces hybrid BM25 search for more accurate knowledge retrieval and adds live URL indexing for real-time content extraction (0dda1e5e, f10cfea5). Performance and stability improvements include optimized search relevance scoring, refined knowledge base defaults, and updated core dependencies (b04079e8, f7f8b22d, 1771be34, 754e8ec2).

✨ New Features & Enhancements

  • knowledge: add bm25 hybrid search to knowledge retrieval 0dda1e5e

  • knowledge: add URL indexing with live extraction f10cfea5

🔧 Improvements & Optimizations

  • octolib: upgrade to 0.8.1 and update embedding interface 6a650b6f

🐛 Bug Fixes & Stability

  • knowledge: resolve hybrid search relevance scoring and crash b04079e8

  • config: adjust knowledge base defaults for better performance f7f8b22d

🔄 Other Changes

  • deps: bump octolib to 0.9.0 1771be34

  • deps: update tokio chrono uuid clap versions 754e8ec2

📊 Release Summary

Total commits: 7 across 4 categories

✨ 2 new features - Enhanced functionality 🔧 1 improvement - Better performance & code quality 🐛 2 bug fixes - Improved stability 🔄 2 other changes - Maintenance & tooling

All notable changes to this project will be documented in this file.

[0.1.0] - 2026-02-04

📋 Release Summary

This release introduces hybrid search with reranking support, auto-linking functionality via MemoryGraph, and temporal decay for memory importance management. Enhanced cross-platform build support and improved logging with rotation provide better reliability and observability.

✨ New Features & Enhancements

  • search: add reranking support 24245634

  • build: expand cross-platform builds and embedding providers a8aab771

  • mcp: add structured file logging with rotation 14f79109

  • autolink: add auto-linking functionality and MemoryGraph 9181de27

  • search: implement hybrid search combining multiple signals edfbca67

  • memory: add temporal decay for memory importance 4f38123b

  • shell: add completion install script and Makefile f5ab4beb

🔧 Improvements & Optimizations

  • mcp: enable lazy memory provider initialization 4414400c

  • memory: configuration options and code cleanup 6f0190ea

  • memory: extract to standalone octobrain project ea7b47e6

🐛 Bug Fixes & Stability

  • memory: validate empty text and query before processing cc91a956

🔄 Other Changes

  • simplify pre-commit config and normalize file formatting 91221bda

  • update dependencies and fix doc example imports c72f508d

  • update octolib dependency to 0.7.0 2917e6ae

  • optimize cache keys for feature matrix e877b204

  • memory: use struct init and range contains in assertions 7a70f6db

  • deps: upgrade lance to v1.0 301fabdd

  • add release workflow for semver tags 12a2a862

📊 Release Summary

Total commits: 18 across 4 categories

✨ 7 new features - Enhanced functionality 🔧 3 improvements - Better performance & code quality 🐛 1 bug fix - Improved stability 🔄 7 other changes - Maintenance & tooling

86 files · 79 not served here

Advantages

Limitations

  • Strict configuration loading causes startup failure if any field is missing from the TOML file evidence: AGENTS.md
  • The cross-encoder reranker is currently a no-op when using fastembed models evidence: README.md

Security

Risk level: Medium risk

This brain runs

Git hooks (5)

  • .pre-commit-config.yaml: pre-commit hooks from https://github.com/doublify/pre-commit-rust at v1.0 (contributor tooling: runs only after pre-commit install) · uses the network
  • .pre-commit-config.yaml: cargo fmt
  • .pre-commit-config.yaml: cargo clippy
  • .pre-commit-config.yaml: cargo check
  • .pre-commit-config.yaml: pre-commit hooks from https://github.com/pre-commit/pre-commit-hooks at v4.4.0 (contributor tooling: runs only after pre-commit install) · uses the network

Agent instructions that run or fetch something (13)

  • AGENTS.md: what Makefile targets use) and **full gate** `--all-features` (what CI + pre-commit run;
  • AGENTS.md: Check: `cargo check --no-default-features --all-targets` · All feature combos: `make check-features`
  • AGENTS.md: Format (write): `cargo fmt --all` · Format (verify): `cargo fmt --all -- --check` — `make fmt` is verify-only
  • AGENTS.md: Run CLI: `cargo run --no-default-features -- <subcommand>` · MCP server: `cargo run --no-default-features -- mcp` (stdio) or `-- mcp --bind=host:port` (streamable HTTP)
  • AGENTS.md: BEIR retrieval bench (local, free): `bash benches/scripts/run_retrieval.sh` or `cargo run --release --features bench --bin beir_bench -- <dataset_dir> [label]`
  • AGENTS.md: Completions: `make install-completions` / `make test-completions`
  • AGENTS.md: `make ci` references nonexistent targets (`format-check`, `lint`) — run the four commands above instead
  • AGENTS.md: boxes under `<storage>/boxes/`, shared-embedding endpoints under `<storage>/run/`.
  • AGENTS.md: `make check-features` passes when touching feature-gated code
  • AGENTS.md: Stale Makefile details: `make fmt` verifies only, `make ci` is broken, `make install-deps` has a `trustup` typo.
  • AGENTS.md: LongMemEval benches require `benches/.env` (LLM keys) and cost ~10M tokens per full run;
  • AGENTS.md: smoke-test with `make smoke` in `benches/`.
  • AGENTS.md: Force-run sleep consolidation or maintenance in production paths

Install scripts (1)

  • Makefile (make install): echo "$(YELLOW)Installing $(BINARY_NAME)...$(NC)"; cargo install --path .; echo "$(GREEN)$(BINARY_NAME) installed successfully$(NC)"

MCP servers (1)

  • README.md (octobrain): /path/to/octobrain mcp
  • Medium risk: runs-git-hook-remote-exec (.pre-commit-config.yaml:4)
  • Medium risk: runs-git-hook-remote-exec (.pre-commit-config.yaml:35)

Attribution and licence

Created by
Muvon
Publisher
Muvon (Official Muvon project)
Source
Muvon/octobrain · commit bfb15d6
Licence
Apache License 2.0 (files served here)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Muvon.

Install from source

79 of its files are not served here, so there is no ZIP. Muvon/octobrain at bfb15d6