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(client-ts): ship the Apache-2.0 LICENSE in the npm package
- ci: test TypeScript client on supported Node versions
- [Feature] let the chat LLM path use any OpenAI-compatible endpoint
- feat(common): allow a self-hosted base URL for the chat LLM path
- chore(clients): published client packages ship no LICENSE file despite declaring Apache-2.0
- chore(ci): Python client CI tests only 3.12 though the package claims 3.9-3.13
- chore(ci): TypeScript client CI tests only Node 20 (engines says >=18) and uses npm install, not npm ci
- `npm install caura` is in our README, and npm's similarity filter blocks the name against `cuara`
- W4a: ship the CAURA_*/MEMCLAW_* dual-read helper, ahead of the Wave 4 doc sweep
- The conftest tenant sweep matches almost nothing: 12,714 rows leak per local DB, 0 reclaimed
- Docs
- Python not yet supported