#15 · Primary category: AI Agents & Automation

claude-mem

ai ai-agents ai-memory anthropic artificial-intelligence chromadb claude claude-agent-sdk claude-agents claude-code claude-code-plugin claude-skills embeddings long-term-memory mem0 memory-engine openmemory rag sqlite supermemory

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Project last updated:08/29/26

GitHub Stars

92.6K

Forks

8.1K

Contributors

139

License

Apache-2.0

Why we included this project

Every coding agent session starts from zero unless you give it context, and anyone who has pasted the same project notes into a prompt for the tenth time knows how that grinds long-running work to a halt. claude-mem keeps a memory layer between sessions for agents like Claude Code, Codex, and Gemini. It watches what the agent does and compresses the session with AI, so the relevant pieces come back automatically when a new one starts. An agent can then resume a task knowing the fixes it already made and the preferences you've stated, without you re-explaining everything. That makes it a good fit for solo developers and small teams who want continuity without building their own memory infrastructure. It installs as a plugin that hooks into agent lifecycle events, so it works with your existing setup rather than asking you to change how you work.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category