💾claude-mem
thedotmack/claude-mem · homepage ↗
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
⭐ Hugely popular: 91k stars, gaining about 762 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- It gives coding agents persistent memory across sessions, so context from past work is captured and injected into new sessions instead of being lost when a session ends.
- It targets developers using Claude Code and similar agent harnesses, and also claims support for OpenCode, Claude Desktop, and other gateways.
- Its progressive-disclosure retrieval returns compact search indexes first and fetches full observation details only for filtered IDs, cutting the tokens spent on recall.
under the hood
- Written in JavaScript, it hooks into five Claude Code lifecycle events (SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd) to capture tool usage and generate semantic summaries automatically.
- A local worker service on port 37777 exposes an HTTP API and web viewer, backed by SQLite with FTS5 full-text search and a Chroma vector store for hybrid semantic and keyword search.
- It installs via npx or a plugin marketplace, requires Node 20 plus auto-installed Bun and uv, ships four MCP search tools, and is licensed Apache-2.0 to allow embedding in other tools.
Radar summary, generated from the project's public sources
star history
- PR#23 1k 2025-12-10
- now 91k + 89k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Output and attention are roughly in balance.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Persistent memory plugin for Claude Code
similar projects
compare these →- ☤ hermes-agent
Python · 2.5× the stars
The agent that grows with you
231k ACTIVE - 🧠 oh-my-opencode
TypeScript
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
68k ACTIVE - 🧠 Mem0
Python
Universal memory layer for AI Agents
63k ACTIVE
comments
Sign in with GitHub to add your blip on claude-mem.