Coworker Desktop App Works with Any OpenAI-Compatible Endpoint
Melvin Vivas · X post · 2026-08-29 · Open on X
Topics: AI Dev Tools & Productivity, LLM Fundamentals, AI Agents, Tool Use & MCP · Level: beginner
Summary
Melvin Vivas says his local-first desktop app Coworker can connect to any OpenAI-compatible API endpoint. He shows it running on Baseten's inference platform with the GLM 5.3 Flash model, so you aren't tied to a single model provider.
Key points
- Coworker accepts any OpenAI-compatible endpoint, so you can swap model providers without code changes.
- The creator runs it with Baseten as the inference provider.
- The model used is GLM 5.3 Flash, an alternative to OpenAI models.
- The OpenAI-compatible API format is a de facto standard many inference hosts support, which makes switching providers easy.
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 - Baseten · tool · x.com · paid
Model inference platform offering dedicated GPU deployments for serving open models.
Also in: Serving Qwen3.8 27B FP8 on an H100 with Baseten dedicated inference (Melvin Vivas on X · notes), Running GLM 5.3 Flash on Baseten with the Pi Coding Agent (Melvin Vivas on X · notes), GLM 5.3 Flash Now Available on Baseten (Melvin Vivas on X · notes), GLM-5.2 Vision on Baseten: Turning Images into Code (Melvin Vivas on X · notes) and 6 more - GLM 5.3 Flash · tool · huggingface.co · free
Low-cost model (about $0.15 in / $0.50 out per million tokens) that Theo says beats GPT-5 at agentic work.
Also in: Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), GLM-Legal: Z.ai's Legal-Domain Model Built on GLM-5.3-Flash (Melvin Vivas on X · notes), Running GLM 5.3 Flash on Baseten with the Pi Coding Agent (Melvin Vivas on X · notes)
Try this
- Download Coworker from donvitocodes.com/coworker and point it at an OpenAI-compatible endpoint.
More in AI Dev Tools & Productivity
- Codex Luna reserve: extra usage after your limit runs out
- Claude desktop's built-in browser can import your Chrome profile
- News: Claude desktop now has a built-in browser
- Coworker v0.3.3: Skills Toggle, Schedules and Inline Approvals
- Coworker v0.3.1: Telegram Streaming Sync, Built Fast with Codex
- Coworker v0.3.1: Streaming Sync Between Telegram and Coworker