Collective Memory
Gives Claude persistent memory across sessions using semantic search. Exposes two tools: remember() to store decisions, learnings, and context with optional project scoping and type tags, and recall() to search that memory bank with natural language queries. Uses OpenAI embeddings and LanceDB under the hood, automatically deduplicates similar content above 95% similarity. Everything lives in a local embedded database at ~/.collective-memory/data, no separate server process. Reach for this when you're tired of re-explaining project context every session or want Claude to actually remember architectural decisions and patterns from previous conversations. Also ships with a CLI for command line memory management.
- tools
- 2
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- May 29, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
rememberStore a memory with semantic embedding.
Store a memory with semantic embedding.
No parameter schema in public metadata yet.
recallSearch memories by semantic similarity.
Search memories by semantic similarity.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
OPENAI_API_KEY*secretOpenAI API key for generating embeddings
Readme
Collective Memory
MCP server for persistent, semantic memory across AI sessions. Store context, decisions, and learnings — recall them later with natural language search.
Why
AI assistants forget everything between sessions. Collective Memory fixes that. Store what matters, search by meaning, build context that compounds.
Features
- Semantic search — Find memories by meaning, not keywords (OpenAI embeddings + LanceDB)
- Automatic deduplication — Won't store near-duplicates (>95% similarity)
- Project scoping — Organize memories by project
- Type classification — Categorize as
decision,milestone,context,learning, orsession_summary - Zero config storage — Embedded vector database, no server required
Installation
npm install -g collective-memory
Or clone and build:
git clone https://github.com/Hustada/collective-memory.git
cd collective-memory
npm install
npm run build
Setup
1. Get an OpenAI API key
Required for embeddings. Get one at platform.openai.com.
2. Add to Claude Code
Add to ~/.claude/settings.json under mcpServers:
Details
- Repository
- github.com/hustada/collective-memory
- Category
- AI & LLM Tools
- Package
collective-memory- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Bluecolumn Memorybluecolumnconsulting-lgtm/bluecolumn-mcpPersistent memory for AI agents — audio intelligence + Music Memory ingestion and recall0stars
Agentic Commerce Catalogsuede-ai/suede-ai-appAI music, video, image, and voice tools callable by agents with USDC payments via x402 on Base.0stars
Ai Prompt Optimizerlazymac2x/ai-prompt-optimizer-apiCloudflare Workers MCP server: ai-prompt-optimizer0starsEmbedding Searchlazymac2x/embedding-search-apiCloudflare Workers MCP server: embedding-search0starsLlm Output Quality Monitorlazymac2x/llm-output-quality-monitor-apiCloudflare Workers MCP server: llm-output-quality-monitor0stars
Agent Replaymdfifty50-boop/agent-replay-mcpRecord and replay AI agent execution for debugging0stars