Codeoid

Codeoid

[](https://www.npmjs.com/package/@highflame/codeoid) [](https://www.npmjs.com/package/@highflame/codeoid) [](https://github.com/highflame-ai/codeoid/actions/workflows/ci.yml) [](https://codecov.io/gh/highflame-ai/codeoid) [](https://www.npmjs.com/package/@highflame/codeoid) [](LICENSE) [](https://bun.sh)

**Multi-agent harness for AI coding agents — multi-session, multi-frontend, with cross-session memory.**

Run N parallel coding-agent sessions across repos — Claude Code by default, with Codex, Gemini, OpenAI, and pi as drop-in backends. Switch between them from a terminal cockpit, a web UI, or Telegram. Memory persists across sessions, so each agent inherits what the last one learned. Every action is auditable, and with [ZeroID](https://github.com/highflame-ai/zeroid) every agent and sub-agent carries a cryptographic identity.

bun install -g @highflame/codeoid
codeoid start --local          # no account, no login, no config — running in seconds

That's the whole first run. [Add real identities](#path-b--zeroid-identities-for-real-work) whenever you're ready.

**Terminal client lives in its own repo.** The recommended cockpit is [**codeoid-tui**](https://github.com/highflame-ai/codeoid-ui) — a native Rust/[Ratatui](https://ratatui.rs) client that speaks the daemon's WebSocket protocol. A built-in `codeoid tui` (Ink/React) ships in this repo