Omnigent provides an orchestration and governance layer for multiple heterogeneous AI coding agents, allowing users to combine different harnesses, enforce policies, and collaborate across devices.
Project overview
The project addresses the difficulty of managing disparate coding agents by providing a single layer to swap harnesses, enforce sandboxing, and sync sessions across terminals, browsers, and mobile devices.
Project type
AI Agent · AI Coding
Use cases
Coding & Development
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers and AI engineers managing multiple AI agent harnesses who require cross-device session synchronization and policy enforcement.
Key capabilities
Provides a common orchestration layer over Claude Code, Codex, Cursor, and custom agents to swap or combine harnesses without rewriting.
Sessions follow the user across terminal, browser, and phone, keeping messages, sub-agents, terminals, and files in sync.
Run agent sessions in disposable cloud sandboxes such as Modal, Daytona, E2B, CoreWeave, Kubernetes, or Databricks.
Create policies to pause for approval before risky actions, cap spend, or limit which tools an agent can access.
Share live sessions so teammates can chat with agents, co-drive on a machine, or fork conversations.
Define custom agents in YAML files with prompts, local Python functions, MCP servers, and sub-agents.
Limitations and risks
Windows runs in a degraded mode without bwrap/seatbelt sandboxing or native tmux terminal wrappers.
The project is currently in alpha status.
Getting started
Setup is rated easy due to a one-command installer, a one-command Docker Compose setup, and a PyPI package. The first success path is running a curl install script or using uv tool install, followed by executing the omnigent command.
Evidence and sources
GitHub project description: Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies…
README: Mix Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and custom agents (defined in YAML) together in the same session. Ask one agent to review another's work, or split a task acr…
README: 📱 Work with agents from any device, including your phone.** Sessions follow you: start in your terminal, continue in the browser, pick it up on your phone. Messages, sub-agents, t…
README: ☁️ Run agents in cloud sandboxes.** No laptop required: run sessions in disposable [Modal](https://modal.com), [Daytona](https://www.daytona.io), [Islo](https://islo.dev), [E2B](h…