Unity AI Gateway Coding CLI (ucode)

ucode is a lightweight launcher for running Codex, Claude Code, Gemini CLI, OpenCode, and GitHub Copilot CLI through Databricks.

Requirements

• Python 3.12+ — install with uv (uv.astral.sh)
• npm if tool CLIs need to be installed automatically

Installation

uv tool install git+https://github.com/databricks/ucode

---

Usage

Just run the tool you want:

ucode codex      # OpenAI Codex
ucode claude     # Claude Code
ucode gemini     # Gemini CLI
ucode opencode   # OpenCode
ucode copilot    # GitHub Copilot CLI

On first launch, ucode will prompt for your Databricks workspace URL, authenticate, and configure that tool automatically. Subsequent launches go straight to the agent.

Pass flags directly to the underlying tool:

ucode claude -r          # resume last session
ucode codex --full-auto

All agents route through Databricks AI Gateway using your workspace credentials — no API keys required.

To configure all tools at once:

ucode configure

MCP servers (optional)

ucode configure mcp

Add Databricks MCP servers to installed MCP-capable tools: Codex, Claude Code, Gemini CLI, OpenCode, and GitHub Copilot CLI. Options are shown in this order:

• Discovered external MCP connections
• Databricks SQL
• Managed Databricks MCPs (Vector Search, UC Functions, etc.)
• Custom MCP server URL

Discovered external MCP connections are listed directly. MCP auth uses a Databricks token that ucode sets when launching each tool.

---

Other Commands

Command	Description
ucode status	Show current workspace, base URLs, managed config files, and selected models
ucode usage	Show AI Gateway usage summary
ucode revert	Clear saved state and restore backed-up config files
ucode configure --dry-run	Preview config files without writing them

Managed Local Files

ucode manages these files:

File	Tool
~/.codex/config.toml	Codex
~/.claude/settings.json	Claude Code
~/.gemini/.env	Gemini CLI
~/.config/opencode/opencode.json	OpenCode
~/.copilot/.env	GitHub Copilot CLI

Existing files are backed up before being overwritten. ucode revert restores backups.

Documentation

• Databricks AI Gateway overview
• Databricks AI Gateway coding agent integration
• Databricks CLI authentication
• Monitor AI Gateway usage

Contributing

Contributions are welcome.

Getting started

git clone https://github.com/databricks/ucode
cd ucode
uv sync

Development workflow

1. Create a feature branch off main.

2. Make your changes — keep them scoped to the requested behavior.

3. Run the test suite before pushing:

   uv run pytest          # unit tests
   uv run ruff check .    # lint

4. For end-to-end testing against a real workspace:

   UCODE_TEST_WORKSPACE=<db_workspace_url> uv run pytest tests/test_e2e.py -v

5. Open a pull request against main.

Adding a new agent

• Add src/ucode/agents/<name>.py with at least write_tool_config, launch, default_model, and validate_cmd.
• Register it in src/ucode/agents/__init__.py.
• Add focused tests under tests/.

Security

Please report security vulnerabilities to security@databricks.com rather than opening a public issue.

License

See LICENSE.md and NOTICE.md.