Ship with Matilda.

Install the CLI, sign in, and open your first session.

The model, the agent, and the action layer.

Read, plan, act, verify, and the five approval modes.

What Matilda holds in a session, and what carries across them.

Run Matilda Code from scripts, pipelines, and other automation.

Commands, flags, and settings for the matilda CLI.

Install the client SDK, send your first message, and stream a response.

Constructor options, trusted base URLs, and per-instance isolation.

Browser PKCE, device flow, token persistence, and API keys for the client SDK.

Send messages and get complete responses from the chat API.

Full event streaming from the chat API.

Filter a chat stream down to assistant text, with deduped deltas.

Constrain a chat response to a zod schema and get a typed object back.

Resume an interrupted stream from the last received event.

List, retrieve, rename, and rate the threads behind a conversationId.

Carry context across turns with conversationId.

Upload one file or many, then attach the IDs to a chat request.

Report harmful content and manage push notification devices.

Typed error classes, chat error codes, and the SSE stall watchdog.

Six runnable examples, from a CLI chatbot to durable stream recovery.

Every class, interface, and type the client SDK package exports.

Install the agent SDK and run your first agent.

Configure the shared core, or isolate a Runner with its own client and auth.

AgentAuth on the runner — login, restore, and automatic token refresh.

Configure agents with instructions, tools, compaction, and resumable state.

Run a prompt to completion and get the final output.

Full event streaming from an agent run.

Filter a run's stream to assistant text, plus the module-level run and stream helpers.

Constrain an agent turn to a zod schema with runObject and streamObject.

Tools that execute locally, wired into the agent loop.

Stateful multi-turn conversations with a session object.

Durable handles and resuming interrupted agent runs.

The runner files resource — upload, retrieve, and attach file IDs to a run.

Read, rename, and rate conversation threads from the runner.

File bug reports from your application.

Run and stream errors, exponential-backoff retries, and partial results after a failure.

Compose, parallelise, and route between agents.

Six runnable examples, from a device-flow CLI agent to a multi-agent review pipeline.

Classes, functions, constants, and types exported by the agent SDK package.