Self-hosted alternatives to Omnigent
200 self-hosted apps like Omnigent, closest match first.
Top picks
- O
ORG-2
LaunchOpen-source workspace that runs 20+ AI coding agents and records every session as a replayable trajectory. Replay any session, review as a team, and trace every line back to the decision behind it.
Self-hosted
- H

HarnessRouter
LaunchHarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure
Self-hosted
- C
Cezar
LaunchOpen-source orchestrator that runs Claude Code, Codex, OpenCode and other coding agents in parallel, on your laptop or 24/7 on your own server, using the subscriptions you already pay for. No API keys.
Self-hosted
- C
Codeg
LaunchCodeg is a multi-agent coding workspace. It aggregates sessions from several coding agents, including Claude Code, Codex, OpenCode, Pi and Grok Build, so you can run the agents you use together in one place and keep work moving on each scre
Self-hosted
- P
Pydantic Deepagents
LaunchOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
Self-hosted
- A

ADHDev
LaunchThe control plane for your coding agents. See every Claude Code, Codex CLI, Kimi, Cursor CLI, Antigravity CLI, Grok and OpenCode session on every machine, hand them one shared task queue across Mac, Windows and Linux, and merge only the wor
Self-hosted
More like Omnigent
Alma by Olivares.AI
Self-hosted control plane that maps and governs what your AI agents can reach
About Omnigent
Omnigent
Meta-harness that sits above Claude Code, Codex
Omnigent is an open-source meta-harness that sits above coding agents such as Claude Code, Codex and Pi, and above agents you write yourself. It gives you one layer to compose, govern and share agents: you can swap or combine harnesses without rewriting code, and enforce policies such as spend caps, model routing and risk-based escalation at that layer rather than through prompts. Secure sandboxes run any agent in a local operating-system sandbox or a remote cloud sandbox, where filesystem and network access can be restricted and credentials are brokered without being exposed to the agent. Teammates can share a live agent session by URL with its full history, and review, comment and steer it together. Omnigent includes built-in multi-agent setups, a coding orchestrator and a model debate, which you can define in YAML. A runner, a server and a REST API expose sessions in the terminal, the web, native apps and mobile. The project is on GitHub, with a Discord community.
- Price
- Open source
- Category
- AI
- Website
- omnigent.ai


