OpenWorker

OpenWorker is an open-source, local-first desktop AI coworker from Andrew Ng, founder of DeepLearning.AI and AI Fund. Instead of returning chat, it returns finished work: a polished document, a filled spreadsheet, a drafted report, a Slack reply with the numbers, an updated calendar, or a triaged inbox. You describe an outcome ("prepare a customer brief," "untangle my calendar," "check where the release stands across Jira and GitHub"), and OpenWorker breaks it into steps, works across your desktop, files, and connected apps, and hands back the deliverable as a file you can open and share. It is aimed at knowledge workers, developers, and small teams who want real output from an agent that runs on their own machine. Integration depth is a core strength. OpenWorker ships with 25+ native connectors, including GitHub, Slack, Jira, Notion, Linear, HubSpot, Microsoft Outlook, monday.com, Gmail, and Google Calendar, plus direct access to your terminal and local files. Slack is bidirectional: mention @OpenWorker in a channel and a session opens on your desktop, the work runs with your tools, and the answer returns as a thread reply. Any tool reachable over the Model Context Protocol (MCP) plugs in as well, with per-tool control, so the integration surface is not limited to the built-in list. OpenWorker acts as an MCP client, consuming external MCP servers rather than publishing its own. Native SSO, SCIM, and centralized team administration are not part of the product, since it is a local, single-user desktop install rather than a managed cloud service. Pricing is simple: OpenWorker is free and open-source under the MIT license, with no paid tiers for the software itself. It is model-agnostic and bring-your-own-key: you supply an API key for OpenAI, Anthropic, Google Gemini, DeepSeek, Qwen, Mistral, xAI Grok, Moonshot Kimi, MiniMax, Z.ai GLM, or Thinking Machines Inkling, use open-weight models via Together or Fireworks, or run fully local and free with Ollama. Model usage is billed by whichever provider you choose (USD), not by OpenWorker, so the effective cost is your own token spend, and running locally with Ollama has no per-token cost at all. Because the app is free, the thing to understand is what free does not include. There is no hosted cloud option and no managed model: you must provide your own model key or stand up Ollama locally, and you pay the model provider directly for anything beyond a local model. There is no vendor SLA, enterprise support contract, or compliance program, and the software is in open beta, so some workflows are still being polished. OpenWorker is not the right fit for teams that need a fully hosted, zero-setup SaaS agent with centralized administration, audit logging, SSO, and a compliance program; a local-first, single-user desktop tool does not provide those. Teams that want a personal assistant living inside their text messages rather than a work coworker producing files may prefer a messaging-native agent like Poke ($19/mo). Organizations that require a vendor-managed, enterprise-governed deployment should evaluate a hosted platform instead. Current state Q3 2026: OpenWorker launched in July 2026 as an open beta and is developed in the open on GitHub (andrewyng/openworker, MIT license, roughly 3.4k stars). The macOS build for Apple Silicon is signed and notarized and auto-updates; the Windows 10/11 build is functional but not yet code-signed, so Windows SmartScreen shows a warning during install. There is no G2 or Capterra presence yet, and no third-party security certifications, consistent with a local-first tool that keeps data on your machine. The engine is built on Andrew Ng's open-source aisuite library.