omnigent
by omnigent-ai (organization)
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 and sandboxing, and collaborate in real time from any device. (description from the project’s GitHub page)
Repository facts
- Stars
- 10,874
- Forks
- 1,760
- Open issues and pull requests
- 2,280
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- omnigent-ai · Organization
- Created
- Jun 11, 2026
- Last push
- Oct 18, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/omnigent-ai--omnigent/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/omnigent-ai--omnigent/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/omnigent-ai--omnigent.svg" alt="Ranked #743 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 928: HarnessMD/munder-difflin
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subsc…
8,876 starsTypeScriptMITLast push Oct 18, 2026
Rank 7,616: open-mercato/cezar
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.
717 starsTypeScriptMITLast push Oct 17, 2026
Rank 5,066: autonomous-ai/openharness
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines…
1,307 starsTypeScriptMITLast push Oct 18, 2026
Rank 3,667: the-open-engine/zeroshot
Enforced QA for Claude Code, Codex and Copilot. Draw the graph: code review, your own reviewers and test agents, any model per node. Slop goes back to repair, and the agent that w…
1,994 starsRustMITLast push Oct 18, 2026
Rank 2,115: foryourhealth111-pixel/Vibe-Skills
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
3,725 starsPythonApache-2.0Last push Oct 18, 2026
Rank 5,063: dohooo/helmor
Open-source local workbench for multi-agent software development.
1,308 starsTypeScriptApache-2.0Last push Aug 22, 2026