claude-mem: Persistent context across sessions for all agents
Decision Brief
What changedclaude-mem captures all agent actions in a session, compresses them with AI, and injects relevant context into future sessions.
Why it mattersFor developers using CLI agents like Claude Code, Codex, or Copilot, this solves the pain of starting from scratch every time, reducing repetitive prompts and context loss.
Who should careOpen-source model users, AI coding tool users
Affected stackClaude CodeOpenAIGeminiCopilot
Source confidenceHigh · Official release / blog / repo
claude-mem is an open-source project (JavaScript) that provides cross-session persistent context for multiple agent tools. It automatically records all actions in each session, uses AI to compress and summarize them, and injects the relevant context into prompts of future sessions. It supports Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode, and more, with quick install via npx claude-mem install. The project gained over 1000 stars in 7 days, with a total of 85,951 stars.
Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.
Sources
- Skill Radar(GitHub 趨勢)
Trending hands-on MCP servers, agent skills, and AI-coding tools discovered from GitHub search momentum.
- GitHub:thedotmack/claude-mem