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
thedotmack/claude-mem is accelerating — star growth is speeding up by +841.1/day (100th percentile in the tracked cohort), on top of +1077.1 stars/day. A recent release is helping fuel the run.
Reconstructed from 352 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 386.
~101 forks/day, 3.9× the trailing baseline.
Release count rose to 385.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/thedotmack/claude-mem)Elevated breakout odds over the next 14 days, led by star acceleration (100th pctl) and star velocity (100th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Release count rose to 379.
Release count rose to 378.
Release count rose to 377.
Release count rose to 376.
Release count rose to 373.
Release count rose to 372.
Release count rose to 370.
Release count rose to 368.
Release count rose to 366.