caura-build-fleet
https://github.com/caura-ai/caura-build-fleet
Python
A runnable reference implementation of multi-agent constraint propagation using MemClaw. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.
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-build-fleet
Help out
- Issues
- --skip-manager drops the last pipeline step by index, not the Manager
- --reset and --loop only delete the first page of fleet memories
- Fleet reset deletes memories as manager-tenant, the agent documented as read-only
- The "did the Manager write?" check is duplicated and misses evolve/tune
- debug_recall.py never loads .env despite its docstring saying it does
- Agent iteration cap is hit silently, truncated runs look successful
- Add a 6th agent: Accessibility Auditor
- --dry-run doesn't verify MCP tool-schema shape, only connectivity
- Add a unit test for per-agent tool allowlisting
- Document MEMCLAW_TRANSPORT=rest fallback mode with a runnable example
- Docs
- Python not yet supported