Databricks founder Matei Zaharia open-sources Omnigent, a meta-harness to orchestrate and govern multiple AI agents without model lock-in
It supports Model Context Protocols and automated session failover
Story Brief
It supports Model Context Protocols and automated session failover
Related Stories
3 linkedGitHub - omnigent-ai/omnigent: A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in check with policies and sandboxing, and collaborate in real time on the same live session, from any device.A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in ch...23d agoGitHub
Omnigent — a meta-harness for building and running AI agentsOmnigent is an open-source meta-harness: a common layer for composing, governing, and collaborating on AI agents — coding and otherwise — on top of the harnesses you already use.24d agoOmnigent
Introducing Omnigent: A Meta-Harness to Combine, Control and Share Your Agents | Databricks BlogOmnigent is a new open source meta-harness that sits above coding tools like Claude Code, Codex, and custom agents, so you can compose, govern, and share AI agents from one place.24d agoDatabricks
Omnigent — a meta-harness for building and running AI agentsOmnigent is an open-source meta-harness: a common layer for composing, governing, and collaborating on AI agents — coding and otherwise — on top of the harnesses you already use.24d agoOmnigentIntroducing Omnigent: A Meta-Harness to Combine, Control and Share Your Agents | Databricks BlogOmnigent is a new open source meta-harness that sits above coding tools like Claude Code, Codex, and custom agents, so you can compose, govern, and share AI agents from one place.24d agoDatabricks
