microsoft/Webwright

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

What it does

Webwright gives an LLM a terminal from which it opens browser sessions and completes a web task as a single re-runnable Python script. Solved tasks can be turned into reusable code skills that rerun without a model.

How it helps ATF

Worth comparing for Harness, which hands work to executors such as Claude Code, Codex and Hermes. Leaving each web task as a re-runnable script could be a reference for keeping checkable evidence of what an agent did.

License

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

More in this category

• headroomlabs-ai/headroom
  Headroom compresses tool outputs, logs, files, RAG chunks and conversation history on the local machine before they reach the LLM. It runs as a library, a proxy or an MCP server, and caches originals for later retrieval.
• fathah/hermes-desktop
  A community-maintained desktop app for installing, configuring and chatting with Hermes Agent. It offers a GUI for chat, sessions, profiles, memory, skills, tools, scheduling and messaging gateways instead of managing the CLI by hand.
• nesquena/hermes-webui
  Hermes WebUI is a browser interface for Hermes Agent with near parity to its CLI, built with Python and vanilla JS. It has a session sidebar, chat, a workspace file browser, token usage display, and profile and model controls.
• tinyhumansai/openhuman
  OpenHuman is a local-first agent harness. It stores memory as scored Markdown trees in SQLite, mirrored as an editable Obsidian vault, runs fleets of agents on durable graphs, and researches the user's data and the web.
• odysseus-dev/odysseus
  Odysseus is a self-hosted AI workspace. It combines chat and agents with tools, MCP, skills and memory, multi-step web research with report generation, a document editor, email triage, notes, tasks and a calendar with CalDAV sync.

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.