Set up Coding Agents & Tools
Use tare integrate to point supported coding tools at a Tetrate Agent Router gateway in one command. For deeper tool-specific setup, and for tools the CLI does not cover yet, the per-tool guides below give project context and manual configuration.
Preferred path
Per-tool guides
Visual Studio Code
Install the Tetrate model provider extension so one key serves VS Code chat, agent mode, and every extension that uses the Language Model API.
Claude Code
Point Claude Code at the gateway (managed or Max), then optionally add a CLAUDE.md for Agent Router patterns.
Cursor
Add a .cursorrules file so Cursor's agent and inline chat default to Agent Router.
Codex CLI
Configure the gateway with tare integrate, then add project context so Codex uses Agent Router endpoints.
Lovable
Paste project context so apps generated in Lovable call the Agent Router API.
Coder
Route agents inside Coder workspaces: a user secret for the API key, one coder_env block for the gateway URL.
How it works
For tools that tare integrate supports, the CLI detects the install, reuses the logged-in Agent Router session, writes the tool's config (with a backup), and validates the key against the gateway. Preview with --dry-run before applying.
For project context, and for tools configured by hand, the setup follows four steps:
- Pick a tool above and copy its config.
- Paste the config into the project, in the file the tool reads (a repo-root instructions file, a rules file, or a project context field).
- Start prompting. The agent now understands the Agent Router base URL, authentication, and available endpoints.
- Layer in routing, fallback, and cost-tracking patterns as the application grows.
The config teaches the agent to use the Agent Router Gateway APIs (chat completions, embeddings, image generation, and audio speech), along with routing, fallback, and cost-tracking patterns, so generated code points at the gateway from the first request.
What every config provides
With the config in place, the coding agent:
- Uses the correct Agent Router base URL and Bearer-token auth pattern automatically.
- Defaults to routing through the gateway instead of calling a single provider directly.
- Suggests separate API keys when multiple AI features are built, so cost can be attributed per feature.
- Recommends fallback routing when a feature needs high availability.
- Recommends traffic splitting when models are being compared.
- Uses streaming for user-facing chat interfaces.
Where to go next