Monorepo for Reminix TypeScript SDK packages.
npm install @reminix/sdk
import { Client } from '@reminix/sdk';
const client = new Client({
apiKey: 'your-api-key',
});
const project = await client.project.get();
console.log(`Project: ${project.name}`);
For complete documentation, examples, and API reference, see the SDK README.
# Install dependencies (this automatically sets up git hooks via husky)
pnpm install
Note: Git hooks are automatically installed when you run pnpm install (via the prepare script). Pre-commit hooks will run formatting and linting checks before each commit.
For more details, see CONTRIBUTING.md.
Integration tests verify that the SDK works correctly with the actual Reminix API. These tests require a valid API key.
# Set your API key and run integration tests
REMINIX_API_KEY=your-api-key pnpm test:integration
# Or run from the client package directly
cd packages/client
REMINIX_API_KEY=your-api-key pnpm test:integration
See packages/client/tests/integration/README.md for more details.
Integration tests verify that adapters work correctly with real LLM APIs:
# Run all adapter integration tests
OPENAI_API_KEY=sk-... ANTHROPIC_API_KEY=sk-ant-... pnpm test:integration:adapters
# Run specific adapter tests
pnpm --filter @reminix/adapters test:integration -- -t openai
See packages/adapters/tests/integration/README.md for more details.
E2E tests verify the full HTTP request/response cycle through the Hono server:
# Run all E2E tests
OPENAI_API_KEY=sk-... ANTHROPIC_API_KEY=sk-ant-... pnpm test:e2e:adapters
# Run specific adapter
pnpm --filter @reminix/adapters test:e2e -- -t openai
See packages/adapters/tests/e2e/README.md for more details.
Build AI agents that integrate with the Reminix API:
npm install @reminix/runtime
import { Agent, serve } from '@reminix/runtime';
const agent = new Agent('my-agent');
agent.onInvoke(async (input) => {
return { output: `Processed: ${input.message}` };
});
agent.onChat(async (messages) => {
const lastMessage = messages[messages.length - 1];
return { message: { role: 'assistant', content: `Reply: ${lastMessage.content}` } };
});
serve(agent, { port: 8080 });
See examples for more details.
Ready to deploy your agent? See the Project Structure Guide for deployment requirements.
MIT