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
- The conftest tenant sweep matches almost nothing: 12,714 rows leak per local DB, 0 reclaimed
- core-api: POST /admin/agent-keys/provision is called by the plugin but never implemented server-side (404)
- Audit findings recur inside the PRs that fix them: propose a lint for the reintroduced shapes and schema-derived guards for sibling drift
- main is red: test_aggregate_is_worst_first fails in full-suite runs, passes in isolation
- [Bug] fix(release-please): core-operations/pyproject.toml missing from release-please-config.json extra-files — version stuck at 1.0.0
- [Bug] core-worker and core-operations have Dockerfiles but are never run docker-compose.yml only starts core-api and core-storage-api
- Interviewer/Prism: reports filed under de-collapsed main-<install_id> — misattributed & unreadable per-agent
- Per-worker settings cache: tenant setting flips take up to 5 min to enforce on the other uvicorn worker
- docs(api-surfaces): document missing MCP tools (memclaw_write, memclaw_evolve, memclaw_insights, memclaw_tune)
- feat(client-python): opt-in retry with backoff for transient failures (429/502/503/504)
- Docs
- Python not yet supported