Litellm

Pipeline diagram: one context pack fans out to Claude, Codex and Kimi in a blind first round, then a peer round, then a free model synthesises, then a human approval gate, then execute and verify

Three Agents, One Approval Gate — Making Claude, Codex and Kimi Review Each Other

I have three coding agents with access to this lab. Claude Code does most of the building. Codex reviews and runs the scans. Kimi audits. Until this week they had never exchanged a word — each got its own context, its own session, and its own chance to be confidently wrong with nobody checking. So I built a thing that makes them work one request together, and put a human approval gate in front of anything that changes the lab. ...

RAINBOW MATRIX cover — the post title in rainbow monospace over falling matrix rain on black

A Self-Hosted Multi-LLM Gateway for My Homelab

Claude Code is the main LLM running my homelab. It builds, debugs, and documents most of what happens on the Debian VM. But I wanted to try other models — and give the CLI tools a shared backend — without wiring up a different SDK and API key for every provider. So I put a gateway in front: one endpoint, many models. Claude stays the main driver; everything else is now one config line away. ...