Contact sales

The Matilda API, on our GPUs

Sign in with your Matilda account, create an API key and call Matilda from your own code, served from Melbourne.

Manage API keys Read the docs

Client SDK

Chat, streaming, and files

A TypeScript client that follows the OpenAI API’s request shape, with chat, durable streaming, structured output and files.

  • npm install @maincode-ai/matilda-client-sdk
  • const client = new Matilda({ baseUrl, accessToken })
  • await client.chat.create({ input })
  • for await (const event of client.chat.stream({ input }))
  • await client.files.upload(file)
Client SDK docs

Agent SDK

Agents, tools, and sessions

Built on the client SDK, it adds named agents, a tool loop, multi-turn sessions and resumable streams.

  • npm install @maincode-ai/matilda-agent-sdk
  • const result = await run(agent, 'Say hello.')
  • for await (const event of stream(agent, prompt))
  • await session.run('Show me an example.')
  • const toolHandlers: ToolHandlers = { … }
Agent SDK docs

Account management

Keys and usage

Create and revoke keys, and see tokens and requests by day. During early access, we raise limits account by account.

Manage API keys

Dedicated capacity or your own instance

Talk to us about reserved capacity on MC-2, or about running your own Matilda model in our facility or your data centre.

Contact sales For organisations

More Matilda

Overview
Chat Matilda shows its searches and sources before it answers, on the web, iOS and Android. Explore Code It reads the repo, runs the tests and opens the pull request, from your terminal or CI. Explore Desktop Matilda plans, edits and tests code in a desktop app for macOS, Windows and Linux. Download Deploy We train a model on your material and run it in Melbourne or in your own data centre. For organisations