← Back to Leaderboard#59
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 #59 on The Agentic Leaderboard with an overall score of 83.6 / 100, scoring 94.2% on reliability and 71.2% on tool selection quality. The project has 83,712 GitHub stars.
Rank
#59
Score
83.6
Category
Agent Framework
Developer
thedotmack
Reliability
94.2%
Tool Selection
71.2%
Avg Steps
25
Cost / Task
$0.05
Latency
500ms
GitHub Stars
83.7k
Mindshare
90.3
Add this badge to your README
[](https://www.theagenticleaderboard.com/agent/claude-mem)
Compared to other Agent Framework agents
- #68 ruflo— score 83.4
- #72 ragflow— score 83.3
- #74 adk-python— score 83.3