← Back to Top 100#74
claude-mem
Agent Framework
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
claude-mem is an open-source agent framework AI agent maintained by thedotmack. It ranks #74 on The Agentic Leaderboard with an overall score of 83.7 / 100, scoring 94.2% on reliability and 71.2% on tool selection quality. The project has 93,391 GitHub stars.
Rank
#74
Score
83.7
Category
Agent Framework
Developer
thedotmack
Reliability
94.2%
Tool Selection
71.2%
Avg Steps
25
Cost / Task
$0.05
Latency
500ms
GitHub Stars
93.4k
Mindshare
90.8
Add this badge to your README
[](https://www.theagenticleaderboard.com/agent/claude-mem)
Rank history
▼ down 1 this week26 weeks on the board since Mar 11 · best rank #59
Compared to other Agent Framework agents
- #75 adk-python— score 83.7
- #76 pi— score 83.6
- #81 eliza— score 83.6