I made Codex work as a Claude Code teammate
Speaks Claude Code's native agent protocol, not a chat wrapper around external APIs.

Runs Claude/Codex/Gemini side-by-side with persistent memory, but embedding CLI tools in Rust is table stakes.
Developers using multiple AI coding agents simultaneously; teams needing coordinated multi-LLM workflows.
Continue.dev (IDE-based multi-agent) · GitHub Copilot Chat (multi-tool coordination) · Custom agentic frameworks (LangChain, CrewAI)
Single Rust binary. Manages multiple AI coding agent sessions in tmux — Claude Code, Codex CLI, Gemini CLI side by side. Dashboard gives you tabs (F1–F11) to see each agent's terminal live. The agents get personas, persistent memory across sessions, and can message each other directly. Cross-machine P2P works over TLS 1.3 so crews on different machines collaborate. My favorite part: a dedicated archivist agent that never writes code, just indexes the entire repo on every push so other agents stop burning context grepping for files but ask him questions instead.
Free account, created during first run.Speaks Claude Code's native agent protocol, not a chat wrapper around external APIs.
Meta-agents can control Circus Chief itself, a rare self-referential twist.
Auto-split pane for Claude Code + shell eliminates 50-times-a-day context switching.
CLI agents with repo access debate, not just API calls.
Git worktree isolation lets agents vote on code before merging anything.
Actual Kubernetes operator for agent lifecycle, but orchestrating agents is still a niche use case.