At Databricks, we use and construct brokers extensively, from coding with them at scale to delivery agent merchandise like Genie. However though the capabilities of brokers have gotten a lot better, working with them feels clunky. As customers, we frequently have 4-5 brokers open directly (coding brokers, Gemini search, and so on) and spend our time copy-pasting textual content between them and Docs, Slack, and different collaboration instruments. And as agent builders, we’re on a treadmill to enhance our brokers by combining the most recent harnesses, SDKs and fashions. The issue is that LLM capabilities are wrapped into an agent harness, and these harnesses have completely different interfaces that make combining them or swapping them tough.
So we constructed Omnigent: a meta-harness that sits above the brokers you already use (Claude Code, Codex, Pi, or customized brokers) and makes them interoperable components of a richer system. Omnigent targets the issues the place a single harness stops: it provides straightforward methods to compose a number of brokers, management them with superior insurance policies, and collaborate dwell with teammates.
We consider folks will quickly work with brokers by way of this new layer, the meta-harness. That’s why right this moment we’re open sourcing Omnigent below Apache 2.0.
Why construct a meta-harness?
At Databricks, we adopted coding brokers early throughout our 5000+ member engineering crew and constructed 1000’s of brokers for patrons. That have satisfied us that the frontier of agent engineering is transferring up a stage. One of the best outcomes not come from a single mannequin in a single harness: Harvey beat a frontier mannequin on high quality and value by giving an open-source employee mannequin a frontier advisor it could possibly name, Anthropic constructed its analysis product as a lead agent orchestrating parallel subagents, and our personal Genie makes use of completely different LLMs for planning, search, and code technology. Engineers are altering how they work, too: as an alternative of prompting one agent at a time, they design loops that drive complete groups of brokers.
These patterns span a number of harnesses, fashions, and folks, however every harness solely understands its personal periods. To mix brokers, govern them, and work on them with different folks, you want a layer above the harness. Omnigent is that layer, and it gives:
- Composition. Mix a number of fashions, harnesses, and methods with out rewriting code, and swap between Claude Code, Codex, Pi, and your personal brokers with one-line modifications.
- Management. Stateful, contextual insurance policies that monitor agent actions and implement guardrails like price budgets and permissions on the meta-harness layer, not by way of prompts.
- Collaboration. Share dwell agent periods by way of URL and assessment information in them collectively, so teammates can assessment, remark, and steer brokers collectively in actual time.
How Omnigent works
Omnigent introduces a typical interface above command-line brokers and agent SDKs to allow you to simply mix and interchange them, after which focuses on the shared issues the place a harness stops. The important thing perception is that nevertheless every agent harness calls into its LLM internally, the interface to customers is similar: messages and information in, textual content streams and gear calls out. Thus we constructed a typical API that wraps each terminal-based coding brokers (Claude Code, Codex, Pi, and so on) and SDKs (OpenAI Brokers, Claude Brokers SDK, and so on).
On prime of this interface, the present model of Omnigent provides the next key options:
- Real-time collaboration: you may invite different folks to view your agent session, touch upon information in its workspace, and even ship instructions, so your periods and dealing directories turn out to be the principle place you collaborate.
- Multiple interfaces to the same agent: when you join an agent equivalent to Claude Code to the Omnigent server, you may entry it on the net, cellular, Mac OS native app, or APIs.
- Cloud execution: launch any agent by yourself machine or on hosted sandbox suppliers like Modal and Daytona, for protected collaboration in a airtight surroundings.
- Contextual security policies: Omingent’s safety insurance policies transcend the easy “enable X / deny Y” of coding brokers, to trace dynamic state about every session and make smarter selections. For instance, you may say that after an agent downloads a brand new bundle from npm, it ought to require human approval to git push, or that it ought to solely have the ability to write to docs it created, not any doc.
- Cost policies: One of many issues we monitor dynamically is every session’s LLM price. For instance, you may ask Omnigent to pause an agent and ask to proceed after each $100 it spends.
- Strong OS sandbox: In Omnigent, we embody a versatile OS sandbox from our safety crew with the power to flexibility lock down OS entry and intercept and remodel community requests (e.g., don’t let an agent ever see your GitHub safety token, however as an alternative, inject it solely within the egress proxy on permitted requests).
- Multi-harness authoring: Specify a customized agent as a YAML and port it throughout harnesses with a one-line change, or mix subagents utilizing completely different harnesses in the identical agent.
These options are simply scratching the floor of what might be completed on the meta-harness layer, nevertheless, and we anticipate to see much more concepts quickly from our crew and the open supply neighborhood. Some objects on our roadmap embody computerized optimization on the meta-harness stage with GEPA, code-based introspection inside brokers just like MemEx and RLM, an Omnigent Server MCP so brokers can work throughout your periods, and extra harnesses. We’ve additionally made Omnigent straightforward to deploy on a variety of infrastructure, together with Fly.io, Railway, Modal and Daytona sandboxes, and plenty of LLM suppliers, and we welcome patches for extra integrations.
A brand new layer for working with brokers
Most of the greatest shifts in our trade got here from transferring to a brand new layer of abstraction: for instance, whereas engineers used to handle particular person processes and servers, they’ll now handle an entire fleet by way of cloud programs like Kubernetes and Terraform.
We predict brokers are on the identical level right this moment. Every harness is its personal silo, with its personal context, its personal controls, and its personal manner of operating, and none of it carries over whenever you swap instruments. Furthermore, many issues intrinsically span harnesses, together with composition, safety and collaboration. A meta-harness lifts your work above any single harness, so your periods, insurance policies, and expertise stick with you regardless of which agent or mannequin is operating. The fashions and harnesses will preserve altering as the sector evolves; the layer you’re employed at should not must.
We’re constructing that layer within the open, and we would love so that you can construct it with us.
Strive it out
Omnigent is open supply in alpha right this moment.