Integrations
Connect coding agents and developer tools to the Triton AI Developer API.
Use the Developer API with clients that accept an Anthropic or OpenAI-compatible endpoint.
Supported by Triton AI
Triton AI tests these setup paths and maintains the instructions on this site.
| Client | Available surfaces | Protocol |
|---|---|---|
| Claude Code | CLI, desktop app, and VS Code | Anthropic Messages |
| Codex | CLI, desktop app, and VS Code | OpenAI Responses |
Jira and Confluence tools
Use MCP connections to add Jira and Confluence tools to your client. MCP configuration is separate from the model-provider connection on this page.
Community integrations
Continue, Hermes Agent, OpenClaw, Cline, Aider, and Open WebUI can use custom OpenAI-compatible endpoints.
Best-effort support
Other projects maintain these clients. Triton AI does not guarantee compatibility with every release.
Choose the correct base URL
| Client protocol | Base URL |
|---|---|
| Anthropic Messages | https://tritonai-api.ucsd.edu |
| OpenAI compatible | https://tritonai-api.ucsd.edu/v1 |
Claude clients add /v1/messages to the Anthropic base URL. Do not add /v1 to that base URL.
Before you start
- Request Developer API access.
- Choose a model that supports the tools your client needs.
- Store the API key in a user-level secret or environment variable.
- Send a harmless test prompt after setup.
Features depend on the selected model
The model route determines support for tool use, image input, reasoning controls, and other client features.