Introducing ๐ข๐บ๐ป๐ถ๐ด๐ฒ๐ป๐, a meta-harness to combine, control, and share your agents.
The best teams already mix models and harnesses and design loops that drive teams of agents. No single harness can keep up with that alone. So we built the layer above โ we call it a ๐บ๐ฒ๐๐ฎ-๐ต๐ฎ๐ฟ๐ป๐ฒ๐๐.
Omnigent sits above the tools you already use, Claude Code, Codex, Pi, and your own agents, and gives them one shared layer:
โข ๐๐ผ๐บ๐ฝ๐ผ๐๐ถ๐๐ถ๐ผ๐ป: combine models, harnesses, and techniques without rewriting code, and switch between them with one-line changes
โข ๐๐ผ๐ป๐๐ฟ๐ผ๐น: stateful, data-centric policies and cost budgets enforced at the meta-harness layer, not via prompts โ let agents run without watching them
โข ๐๐ผ๐น๐น๐ฎ๐ฏ๐ผ๐ฟ๐ฎ๐๐ถ๐ผ๐ป: share a live agent session via URL with full history, so teammates can review, comment, and steer in real time
Every session is reachable from a terminal, the web, a desktop app, and your phone.
We built Omnigent for our own use at Databricks and are open sourcing it under Apache 2.0.
databricks.com/blog/introducโฆ