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
- [Feature] Make OPENAI_CHAT_BASE_URL configurable from environment
- [Feature] Add OPENAI_CHAT_SEND_TEMPERATURE env variable to configure temperature sent to LLM provider
- [Bug] Default search and entity lookup return archived memories
- [Bug] An org's lifecycle.memory_retention_days below 30 does not take effect until a soft-deleted row is already 30 days old
- [Feature] Deployment-wide default for soft-delete retention (LIFECYCLE_MEMORY_RETENTION_DAYS)
- [Feature] Add Cheaper Inference as an OpenAI-compatible LLM provider
- feat(llm): add Cheaper Inference provider
- feat(compose): run core-worker in the stock stack
- Fix false-positive contradiction detection for shared entities
- [Bug] Contradiction detection confirms unrelated memories that share common entities and hides the older one
- Docs
- Python not yet supported