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
- LLM_GATEWAY_MAX_TOKENS is missing from .env.example and bad values fall back silently
- config.MemoryType is defined but never used
- debug_recall.py prints the first 8 characters of the API key
- fix: indicate omitted memory results
- fix: validate MCP tool set during dry run
- fix(ci): give the test workflow an environment and fix the two red tests
- CI has never passed on master: test.yml sets no environment, so 6 agent_base tests fail in Actions but pass locally
- A failed --reset exits 0, and --loop keeps running against the fleet it failed to clear
- fix(pipeline): run fleet teardown as the orchestrator, not the Manager
- fix(pipeline): share one definition of a mutating tool call
- Docs
- Python not yet supported