Omnigent
A meta-harness that runs Claude Code, Codex, Cursor and other agents under one orchestration layer with shared policies and sessions.
Open Source Alternative to:

Omnigent is an open source meta-harness, a common orchestration layer sitting above Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and the agents you write yourself. Swapping or combining harnesses stops meaning a rewrite of everything around them, and one session is reachable from a terminal, a browser, a phone or the native macOS desktop app.
Sessions follow the person rather than the device. Messages, sub-agents, terminals and files stay in sync as you move between clients, and a session can be shared so teammates chat with your agent, watch it work live, co-drive it on your machine, or fork the conversation and continue on their own.
Four areas matter once more than one agent is involved.
- Mixed agents: several harnesses run in the same session, so one can review another's work or a task can be split by strength.
- Any model: a first-party API key, a Claude or ChatGPT subscription, or any compatible gateway are all first class.
- Cloud sandboxes: sessions run in disposable sandboxes on Modal, Daytona, Blaxel, E2B, Kubernetes and others, launched from the CLI or provisioned per session by the server.
- Policies: approval pauses before risky actions, spend caps and tool limits, applied server wide, to one agent or to a single chat.
Installation is a single shell command, or uv and pip manually, and Python 3.12 or newer is required. Terminal wrappers need tmux, and on Linux bubblewrap is mandatory for their sandboxing, while macOS uses the built-in seatbelt. The project is Apache 2.0 and marked alpha.
Stars
9,750Forks
1,515Last commit
5 days agoRepository age
3 monthsLicense
Apache-2.0Version
0.12.0Repository
omnigent-ai/omnigent
Auto-fetched from GitHub .
Open source alternatives similar to Omnigent:
Stars
Forks
Last commit
Stars
Forks
Last commit
Stars
Forks
Last commit