claude-mem

Free

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future ses

Search ToolsFreeFree tier

#claude-code-plugin#persistent-memory#context-management#mcp-server#developer-tools#coding-assistant#memory-persistence#ai-context#session-continuity#knowledge-base

Type

Open Source

Visit Website GitHub (71.3k stars)

About claude-mem

claude-mem is an open-source memory engine for AI coding agents. While your agent works, it writes structured observations—decisions, fixes, dead ends—into a temporal database. CMEM Cloud syncs that memory to every machine through one private MCP link, enabling recall across Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and more. No re-explaining context, no starting from zero. Features include persistent memory, semantic vector recall, offline-first sync, progressive disclosure, and easy setup via npx claude-mem install. The engine is local-first and free; cloud sync is in free early access.

Key Features

Persistent memory storage across Claude Code sessions with no re-explanation needed

Structured memory categories: architecture, convention, decision, bugfix, todo

Scoped relevance — project-wide or directory-specific memory loading

Automatic memory extraction prompts after task completion

Plain Markdown memory format that is human-readable and editable

MCP server integration — connects to Claude Code in two minutes

Git-friendly storage in .claude-mem directory for team sharing

Zero configuration — no database, no API keys, no external dependencies

Works with all Claude Code tiers: free, Pro, and Max

Growing knowledge base that accumulates project intelligence over time

Pros & Cons

Pros

Open-source engine is free and local-first, respecting privacy
Works with multiple agents and IDEs, not locked to one platform
Automatic capture of observations eliminates manual note-taking
Semantic vector recall finds relevant memories in milliseconds
Offline-first design works without internet; cloud sync is opt-in
Setup is trivial – one command with no database or API keys required

Cons

Cloud sync is currently in free early access and requires joining a waitlist
Team governance features (roles, audit, shared workspaces) are still coming soon
Observation generation runs out-of-band but may still add minor overhead on very long sessions
Requires familiarity with MCP clients for cloud sync; local-only mode is simpler

Best For

Developers using Claude Code daily: Maintain architectural decisions and rationales across coding sessionsDevelopment teams: Share project conventions and coding standards with AI assistantsSolo developers: Build a project-specific knowledge base that grows over timeNew team members: Onboard by accessing accumulated AI session knowledge

Alternatives to claude-mem

cognee

The memory for your AI Agents in 6 lines of code

databend

Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.

awesome-llm-apps

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

deeplake

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

anything-llm

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

Flowise

Build AI Agents, Visually