Introducing Omnigent: A Meta-Harness to Combine, Control and Share Your Agents | Databricks Blog
- Source
- databricks.com
- Date
Context
Omnigent gives different AI agents a common session interface so teams can combine them and apply controls in one place. In its announcement, Databricks describes a runner that wraps an in a session and a server that handles sharing and policies. Those policies can respond to the session's history, such as requiring approval to push code after a package download, rather than depending on a reminder inside the model's prompt. The Apache 2.0 alpha release also supports shared live sessions. Its proposed value is continuity: collaboration and controls can sit above the individual agent interface a team happens to use.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
“The problem is that LLM capabilities are wrapped into an agent harness, and these harnesses have different interfaces that make combining them or swapping them difficult.”
Databricks
“We adopted coding agents early across our 5,000+ member engineering team and built thousands of agents for customers. That experience convinced us that the frontier of agent engineering is moving up a level.”
Databricks
“The best results no longer come from a single model in a single harness: Harvey beat a frontier model on quality and cost by giving an open-source worker model a frontier advisor it can call, Anthropic built its research product as a lead agent orchestrating parallel subagents, and our own Genie uses different LLMs for planning, search, and code generation.”
Databricks
“The models and harnesses will keep changing as the field evolves; the layer you work at shouldn t have to.”
Databricks
Checking sign-in…
Loading comments…