Coworker: Open-Source Work Agent That Runs on Small Local Models

Melvin Vivas · X post · 2026-08-28 · Open on X

Topics: AI Agents, Tool Use & MCP, LLM Fundamentals, Portfolio Projects · Level: intermediate

Summary

The creator is building Coworker, an open-source AI agent for work tasks. It can run on small local models, for example LFM2.5-2.6B through LM Studio, to create an invoice from a Telegram message. The post lists the stack: Pi for the agent runtime, CopilotKit for the UI, Firecrawl for web search, LM Studio or Ollama for local models, and OpenAI or OpenRouter for cloud models.

Key points

• Goal: see how far small local models can go on real work tasks, not just chat.
• Demo: creating an invoice from Telegram with Liquid AI's LFM2.5-2.6B running locally in LM Studio.
• Agent runtime: Pi (@pidotdev). UI: CopilotKit. Web search: Firecrawl.
• Local models through LM Studio or Ollama; cloud models through OpenAI or OpenRouter.
• Trade-off: local models give privacy and zero cost, cloud models give more power.
• Free and open source, with installers on GitHub releases.

Resources mentioned

• Coworker (donvito/coworker) · repo · github.com · free
  The creator's local-first desktop app where you pick an AI coworker and have it produce work such as invoices as finished PDFs.
  Also in: Claude Opus 5.5 for Video Making: Creator's Showcase Thread (Coworker) (Melvin Vivas on X · notes), Coworker: free open-source desktop AI coworker app (Melvin Vivas on X · notes), Coworker: Open-Source Desktop App for AI Agents (Melvin Vivas on X · notes), Using Devin AI to Test the Coworker Desktop App on Windows (Melvin Vivas on X · notes) and 38 more
• Coworker Releases (installers) · repo · github.com · free
  Downloadable installers for Coworker.
• Liquid AI (@liquidai) on X · website · x.com · free
  An AI company that builds efficient foundation models. The quoted post shows its PII handling working on Japanese text.
  Also in: Zero-Shot Prompt Routing with Liquid AI's LFM 2.5-Encoder-350M (Melvin Vivas on X · notes), Liquid AI LFM 2.5 Encoder: a CPU-friendly encoder model (Melvin Vivas on X · notes), Fine-tuning Liquid AI LFM2/LFM2.5 MoE models with the new Halo framework (Melvin Vivas on X · notes), Liquid AI's LFM2-Longevity models for aging-data analysis (Melvin Vivas on X · notes) and 19 more
• LFM2.5-2.6B · tool · huggingface.co · free
  Liquid AI's small language model, which can be paired with the LFM2.5-VL-3B vision model.
  Also in: Coworker with Liquid AI LFM2.5-2.6B via LM Studio on a Mac (Melvin Vivas on X · notes), Zero-Cost Coworker Setup: OpenRouter Free Models + Local LFM2.5 (Melvin Vivas on X · notes), Coworker: A Subscription-Free AI Agent on Local LFM2.5-2.6B (Melvin Vivas on X · notes), Run Your Hermes Agent on Free LFM2.5-2.6B via OpenRouter (Melvin Vivas on X · notes) and 9 more
• Pi (pi.dev) · tool · pi.dev · free
  Minimal coding agent with four core tools, plus an SDK for adding those tools to your own apps.
  Also in: Re-authenticate the Pi Agent with the New ChatGPT Sign-In (Melvin Vivas on X · notes), Running Coworker on Free OpenRouter Models and Its Agent Stack (Melvin Vivas on X · notes), Pi Coding Agent: Four Built-In Tools (read, bash, edit, write) (Melvin Vivas on X · notes)
• CopilotKit · tool · x.com · free
  An open-source framework for building in-app AI copilot and agent UIs.
  Also in: Running Coworker on Free OpenRouter Models and Its Agent Stack (Melvin Vivas on X · notes), Coworker: Open-Source Grok Bot Clone Built on Pi and CopilotKit (Melvin Vivas on X · notes)
• Firecrawl · tool · x.com · free
  An open-source web data API with Search, Scrape and Interact features that turn web pages into LLM-ready markdown or structured data for AI agents.
  Also in: Firecrawl Keyless: Free Web Search & Scraping for AI Agents, No API Key (Melvin Vivas on X · notes), Running Coworker on Free OpenRouter Models and Its Agent Stack (Melvin Vivas on X · notes), Coworker: Open-Source Grok Bot Clone Built on Pi and CopilotKit (Melvin Vivas on X · notes), Serve LFM2.5-2.6B with vLLM and connect it to Hermes (Melvin Vivas on X · notes)
• LM Studio · tool · x.com · free
  Desktop app for downloading and running LLMs locally, with a developer mode that serves models through an API.
  Also in: Running LLMs Locally Without an Expensive Rig (Melvin Vivas on X · notes), Adding Vercel AI Gateway as a provider in AIBackends with Devin (Melvin Vivas on X · notes), LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes) and 31 more
• Ollama · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Open-source tool for downloading and running LLMs on your own machine with minimal setup.
  Also in: Running LLMs Locally Without an Expensive Rig (Melvin Vivas on X · notes), Adding Vercel AI Gateway as a provider in AIBackends with Devin (Melvin Vivas on X · notes), Running Qwen3.8-27B Locally on an M5 Max MacBook with Inco Splash (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes) and 12 more
• OpenAI · tool · x.com · free
  An AI model provider whose models can be used through managed connectors.
  Also in: Creator's favorite OpenAI DevDay announcements (Melvin Vivas on X · notes), OpenAI Agents API with Bring Your Own Sandbox as a backend for a 'software factory' (Melvin Vivas on X · notes), Building Software Factories on the OpenAI Agents API (Codex-Powered) (Melvin Vivas on X · notes), Coworker: Free Local-First Desktop App for Running AI Agents (Melvin Vivas on X · notes) and 11 more
• OpenRouter · tool · openrouter.ai · free
  A single OpenAI-compatible API that routes requests to hundreds of models from many providers, with one bill and model fallbacks.
  Also in: Customizing Your Coding Setup with Pi Coding Agent Extensions (Melvin Vivas on X · notes), The Jev model is now on OpenRouter (Melvin Vivas on X · notes), Kev-4B model, an alternative to Jev, now available on OpenRouter (Melvin Vivas on X · notes), Space Bunny Alpha: stealth 1M-context flash model on OpenRouter (Melvin Vivas on X · notes) and 42 more

Try this

• Download Coworker from the GitHub releases page and try it with a local model through LM Studio or Ollama.
• Build a work agent that runs on small local models and handles real tasks such as creating invoices, triggered from a Telegram message.