# Omnigent

> Apache-2.0 meta-harness over Claude Code, Codex, Cursor, Pi and custom agents — sessions on any device, policies, sandboxes

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://omnigent.ai  
**GitHub:** https://github.com/omnigent-ai/omnigent  
**Added:** 2026-10-07

---

## The Hook

Omnigent is an orchestration layer that sits above the coding-agent CLIs you already use: one session can mix Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and YAML-defined agents, follow you from terminal to browser to phone, and run under policies that pause for approval, cap spend or limit tools.

## What's Good

Apache-2.0 (omnigent-ai/omnigent). Free path: uv tool install omnigent, Homebrew, or the install script, then bring your own API key, Claude/ChatGPT subscription or gateway. Ask one agent to review another, split work across harnesses, or share a live session with a teammate who can watch or co-drive. Sessions can run locally (bubblewrap on Linux, seatbelt on macOS) or in disposable sandboxes on Modal, Daytona, E2B, Kubernetes, microsandbox and others via optional extras. Policies apply server-wide, per agent or per chat. ★~10.6k with a very active commit history.

## The Catch

Anonymized usage telemetry is on by default; the opt-out lives in their docs, so flip it before you point it at work code. Heavy toolchain: Python 3.12+, uv, git, Node 22 with pnpm for the web UI, tmux for terminal wrappers, and bubblewrap is mandatory on Linux. First commit was June 2026, so APIs and harness support move fast. A meta-harness is a second layer to debug when an agent misbehaves. Vs Herdr (terminal runtime for agent herds): Omnigent is the bigger server-plus-web-UI play with policies and remote sandboxes.

## Verdict

Most complete open-source way to run several coding agents under one roof with approvals and sandboxes — powerful but young, heavy to install, and telemetry-on by default.