Quick start

Requirements

• Node.js 20 or newer
• An existing TypeScript project
• An LLM provider key, unless you use a local provider such as Ollama

1. Find an agent

Use the catalog to search by task, category, or capability. Open an agent page to review its description, packages, examples, required environment variables, and source.

2. Add the source

npx agentskit add coding-test-runner

The command writes ./agents/coding-test-runner/. Commit this directory: it is application code, not generated cache.

3. Install its packages

The CLI reports the required packages. For a typical agent:

npm install @agentskit/core @agentskit/runtime @agentskit/adapters

4. Configure and run

import { openai } from '@agentskit/adapters'
import { createCodingTestRunnerAgent } from './agents/coding-test-runner/agent'

const agent = createCodingTestRunnerAgent({
  adapter: openai({
    apiKey: process.env.OPENAI_API_KEY!,
    model: 'gpt-4o',
  }),
})

const result = await agent.run(vitestOutput)
console.log(result.content)

Keep provider credentials on the server. Never expose API keys in browser bundles.

5. Review before production

Read the copied agent.ts, run its tests, and verify tool permissions for your environment. Agents in sensitive domains produce decision support; keep a human approval step for consequential actions.

Next: customize the agent or learn how validation works.