fasthands
Computer use that sends diffs, not screenshots: 91% fewer tokens, any model as the brain
- Area
- Agents
- Language
- TypeScript
- License
- MIT
- Plate
- No. 03 of 14
What came back
fasthands is an open-source computer-use engine that observes a page once and then sends only what changed. Every click is hash-checked at the moment it fires, so a page that shifts under the agent aborts the batch instead of hitting the wrong button. It runs with Claude, GPT, or a small model on your own laptop.
How it works
- 01
The engine takes one compact tree of the interactive page, gives each element a stable ref and content hash, and afterwards sends only diffs.
- 02
The model returns a JSON batch of actions; the executor re-hashes every ref before firing and aborts with a drift note if the page changed.
- 03
xray adds the page's own validation rules to the observation, so the agent fixes forms before submitting instead of after a failed submit.
What it does
- Observes the page as a compact tree once, then sends diffs with stable element refs
- Guarded action batches: every ref is re-hashed before it fires and the batch aborts on drift
- xray reads the HTML contract (required, pattern, min/max) and blocks a submit the browser says will fail
- Reads canvas draw commands and WebGL scene graphs, and draws with guarded pointer strokes
- Works with Anthropic, OpenAI or any OpenAI-compatible endpoint such as Ollama, with no SDK dependencies
More from the bench
All projectsUnClaude
An open-source AI engineer that runs on your machine, with any model you choose
Quicky Wiki
Turn a pile of documents into a knowledge base that scores how sure it is
faultline
A live architecture map that stops agents crossing the boundaries you drew