caura-memclaw
https://github.com/caura-ai/caura-memclaw
Python
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to caura-memclaw
Help out
- Issues
- fix(recall): memory text is evidence, not instruction
- feat(clients): add opt-in retry with backoff for transient failures
- docs(benchmarks): LoCoMo 77.9% on all 1,540 questions; withdraw the April token-savings figure
- feat: add native agent collaboration clients and optional core mounts
- Decision: expires_at is accepted, stored and returned, but never enforced (oss-0902-m-60)
- Decision: flip enforce_mcp_plan_limits, or close the measurement gaps first? (oss-0814-m-29)
- knowledge-update-benchmark: 125k entities with embeddings, zero cross-link matches — likely embedding-space mismatch
- Measure cross-link tenant-entity materialization against a dense tenant
- Type pull_executor concretely in _hold_leases instead of Any
- feat(llm): add Atlas Cloud provider
- Docs
- Python not yet supported