Co-Working Developer Agents
Four AI coding agents.
One Databricks App. Three steps to running.
Claude Code, Codex, Gemini CLI, and OpenCode — configured for Unity Catalog, AI Gateway, and Workspace files out of the box.
Four Agents, One Terminal
Different models see different things. Switch agents with a click — they share the same workspace, the same data, the same Databricks context.
Anthropic
databricks-claude-opus-4-6
Deep Databricks skills + useful MCP servers. The most deeply integrated agent.
OpenAI
databricks-codex
OpenAI's reasoning engine. Excels at multi-step code generation and refactoring.
databricks-gemini-2.5-pro
Google's multimodal agent. Vision, long context, and deep reasoning.
Open Source
multi-provider
Open-source, multi-provider. Use any model, any backend, full transparency.
What Ships in the Box
Skills, servers, and integrations keep growing. Here's what's configured today.
Pipelines, dashboards, Unity Catalog, Lakebase — a growing library.
DeepWiki, Exa, and more — wired into every agent and growing.
Every agent session auto-traced, queryable via Genie.
git commit auto-pushes to your Workspace path.
One config, any model, full cost tracking.
Dracula, Nord, Monokai, and more. Pick your vibe.
Dictate or drag-drop images into the terminal.
All deps SHA-pinned. Weekly CVE audits via GitHub Actions.
Why Databricks Apps?
Running coding agents locally means juggling API keys, model access, and governance. Databricks Apps handles all of that.
Your workspace token flows through. No API key juggling. Single-user isolation by default.
Route agents to any foundation model — Claude, GPT, Gemini — through one gateway. Usage tracked, costs governed.
Unity Catalog, MLflow, Workspace files — agents have native access to your entire lakehouse.
Databricks Apps gives coding agents what they actually need: identity, models, data, and governance. CoDA just wires it all together.
Need something more specialized?
The agents in CoDA — Claude Code, Codex, Gemini CLI, OpenCode — are general-purpose coding agents that work across any codebase. They're great for broad software engineering tasks.
But if you need an agent that deeply understands your lakehouse — your table schemas, column lineage, governance policies, pipeline failures — Genie Code is purpose-built for that. It's Databricks' autonomous AI agent for data engineering, data science, and ML work, with native Unity Catalog context that general-purpose agents can't match.
Read the Genie Code announcementGet Started
One click on GitHub. You get the full CoDA setup — agents, skills, MCP servers, themes, and CI.
Connect your repo, pick a name. Databricks handles compute, networking, and identity.
Add your Databricks token as a secret, hit deploy. Agents start with the app.