Vibeleaderboard
← All Intel
Intel / post

OpenWorker: an open-source, model-agnostic agent that produces deliverables

Source
x.com
Date
Andrew Ng@AndrewYNg

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential. OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose. @rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think! Try it out: https://t.co/P0mGnI1o31 (requires your own API key) Source code:

Context

OpenWorker is presented as a desktop that carries out work across files and connected applications, producing a deliverable such as a report or calendar update. In the launch announcement, co-builder Andrew Ng says users choose the model and the application checks in before consequential actions. That choice also affects data handling: although the agent runs on the user's computer, selected model providers and integrations can receive data. Its local application and configurable connections give users choices about where the work happens.

Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
More from Andrew Ng
Recommended reads
Comments

Checking sign-in…

Loading comments…