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
- Fix/skip manager identity
- fix: keep oversized tool results valid JSON
- Document LLM_GATEWAY_MAX_TOKENS and warn on invalid values
- fix: fully redact API key in debug output
- Split pytest into dev requirements
- Split pytest out of pipeline/requirements.txt into a dev requirements file
- load_dotenv(override=True) lets .env silently beat exported environment variables
- _bootstrap_agent has an if/else whose two arms are identical
- _tool_message_content truncates by string slice, so oversized tool results reach the model as invalid JSON
- recall/list results are silently capped at 5 with no 'omitted' marker for the model
- Docs
- Python not yet supported