Coworker: Open-Source Desktop App for AI Agents
Melvin Vivas · X post · 2026-09-20 · Open on X
Topics: AI Agents, Tool Use & MCP, Portfolio Projects · Level: intermediate
Summary
The creator shares Coworker, his open-source desktop app where AI agents do work for you, using local or cloud models. He says he wants to add sandboxes for running agents. The repo is a useful reference for desktop agent apps.
Key points
- Coworker is a desktop app where AI agents complete tasks for the user.
- It supports both local and cloud models.
- Sandboxed execution is the next planned feature, so agents can run safely.
- The source code is on GitHub at donvito/coworker.
Resources mentioned
- Coworker (donvito/coworker) · repo · github.com · free
The creator's agent/bot tool. Version 0.7.0 adds a Primary Bot, free web search, an activity dashboard and support for open models through OpenRouter.
Also in: Coworker: a local-first desktop AI coworker that works with any model (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes), Coworker: A Desktop AI Assistant App, Not a Coding Agent (Melvin Vivas on X · notes), Coworker v0.7.2: Open-Source Desktop AI Assistant (Melvin Vivas on X · notes) and 59 more
Try this
- Add sandboxed execution environments to a desktop AI-agent app such as Coworker.
More in AI Agents, Tool Use & MCP
- Claude Advisor Pattern: Routing Work to Cheaper Executor Models
- Pointer: How Devin Fusion Works
- The complete arXiv corpus as a Hugging Face dataset
- Melvin Vivas's refreshed website: AI agents, local models, workflows
- Running Gemma4-E2B tool calling locally on an iPhone
- Jev + WebMCP Solves 100% of Benchmark Tasks at About 112× Lower Cost