Deprecated projects
March 2026
October 2026
Andon
Code measurement an agent could call as it worked.
Each verdict carried its evidence, and a prototype recompute tested whether the agent's own report held up.
Use instead, as of
- CodeScene MCPTo have an agent check code health as it changes code.MCP server
- SonarQube MCP ServerTo read measures, duplication and quality gate status for an analyzed project.MCP server
- Qwen Code
/reviewFor an agent-run code review.Docs
Not covered
A check of a coding agent's recorded measurements against an independent recompute.
Their docs describe no such comparison. In Andon, that check stayed a prototype.
Why I stopped
Established tools already measure code for agents, and Qwen Code ships agent-run review. The independent check was the one part left that was Andon's own, and I chose not to finish it alone. NVIDIA's Open Agent Safety Platform takes a related approach to agent behavior at runtime.
What it took
- commits
- 455
- lines of Rust
- 84,485