ClawMem
ai-infrastructureNo score yet
On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.
Stars
186
Δ stars 7d
—
Δ stars 30d
—
Forks
29
Contributors
5
npm DL / wk
—
PyPI DL / wk
—
Language
TypeScript
Last push
2026-05-20
About ClawMem
ClawMem fuses recent research into a retrieval-augmented memory layer that agents actually use. The hybrid architecture combines QMD-derived multi-signal retrieval (BM25 + vector search + reciprocal rank fusion + query expansion + cross-encoder reranking), SAME-inspired composite scoring (recency decay, confidence, content-type half-lives, co-activation reinforcement), MAGMA-style intent classification with multi-graph traversal (semantic, temporal, and causal beam search), and A-MEM self-evolving memory notes that enrich documents with…
Read the full README on GitHub →
ClawMem alternatives
Projects in the same category, closest in size — picked by data, not opinion.
See all ai-infrastructure projects ranked by growth →
Frequently asked questions
- Is ClawMem still maintained?
- Yes — actively maintained. The last push was on 2026-05-20, with 5 contributors.
- What are the best ClawMem alternatives?
- Closest by category and size in our data: ac.tandem/docs-mcp, Instrukt, DataEval/dingo — full list with live signals above.
Topics
Embed this badge
Show your project's live signal in your README — it updates weekly with the data.
Tracked since 2026-06-17 · data as of 2026-06-18 · 5 open issues ·