Omnigent, a meta-harness for AI agentsOmnigent, a meta-harness for AI agents

A common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in check with policies and sandboxing, and collaborate in real time on the same live session, from any device.

$ curl -fsSL https://omnigent.ai/install.sh | sh
Omnigent web UI running two sub-agents in parallel on a shared session

Features

  • Polly & Debby: built-in multi-AI agents (a coding orchestrator and a model debate). Build your own in YAML.
  • Contextual Policies: stateful spend caps, model routing, and risk-based escalation.
  • Secure OS Sandbox: restrict filesystem and network access. Hide credentials from the agent, and broker access to them. Run YOLO mode safely.

What Omnigent gives you

Omnigent starfish mascots stacked in layers to illustrate composability.

Composition

Combine multiple models, harnesses, and techniques without rewriting code. Switch between Claude Code, Codex, Pi, and your own agents with one-line changes.


Architecture

A runner wraps any agent in a sandboxed, uniform session. A server adds policies and shared history, and exposes every session over the terminal, the web, a native app, mobile, and a REST API.

Omnigent architecture: CLI agents and custom agents run through a runner (on your machine, Modal, or Daytona), then a server that adds policies and history, reachable from a terminal, the web, native and mobile apps, and a REST API.

Omnigent is alpha and built in the open. Try it and give us feedback on Discord.