vercel-labs/open-agents

This page introduces an external open-source repository. It is not an HDATF product.

What it does

Open Agents is an open-source reference app for running background coding agents on Vercel. A web app handles sessions and chat, the agent runs as a durable workflow, and code runs in a sandbox VM, with GitHub integration.

How it helps ATF

Its split into web app, durable agent workflow and sandbox VM is worth comparing with how Harness separates task state from the executor doing the work. It could be a reference for long agent tasks that keep running without the user's own machine.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• lsdefine/GenericAgent
  GenericAgent is a minimal agent framework that gives an LLM control of a local computer, such as browser, terminal, files, keyboard, mouse and screen. It saves the path of each newly solved task as a reusable skill.
• virattt/ai-hedge-fund
  A proof-of-concept AI hedge fund in which LLM-based investor agents, now being rebuilt as alpha models, analyze prices and fundamentals to make trading decisions. It is for education only and does not place real trades.
• EvoMap/evolver
  A GEP-based engine that lets AI agents evolve themselves, recording that evolution as Genes, Capsules and Events so it can be audited. The readme says future releases will move from open source to source-available.
• multica-ai/multica
  Multica is a self-hostable workspace where AI coding agents are assigned issues like teammates. Agents pick up work, comment on progress, raise blockers and hand results back for review, with the run and diff kept on the same issue.
• huggingface/ml-intern
  An archived Hugging Face project that is no longer maintained. It was an agent that researched, wrote and shipped ML code using the Hugging Face ecosystem, with access to documentation, papers, datasets and cloud compute.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.