Set up Coding Agents & Tools
Prefer tare integrate to point supported coding tools at your Agent Router gateway in one command. For deeper tool-specific setup—or tools the CLI does not cover yet—use the per-tool guides below for project context and manual configuration.
Preferred path
Per-tool guides
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 your key, one coder_env block for the gateway URL.
How it works
For tools that tare integrate supports, the CLI detects the install, reuses your 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 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 will:
- Use the correct Agent Router base URL and Bearer-token auth pattern automatically.
- Default to routing through the gateway instead of calling a single provider directly.
- Suggest separate API keys when multiple AI features are built, so cost can be attributed per feature.
- Recommend fallback routing when a feature needs high availability.
- Recommend traffic splitting when models are being compared.
- Use streaming for user-facing chat interfaces.
Where to go next