Vibe Coding Discoverfast-browser-use
View on GitHubA fast browser-use skill powered by local LLMs via single-token reflexes. Fast, local-first, zero hallucinations.
A local-first browser automation engine and agent skill that drives Playwright via local Qwen models. It scores discrete candidate actions with a single-token logits pass instead of generating code, avoiding selector hallucinations, running fully offline on MLX or PyTorch.
Use Cases
Autonomous browser navigation and clickingForm filling and text input on web pagesLocal/offline browser agent for Claude Code, Codex, CursorWeb task automation with verified final URL/title/textBenchmarking local LLM browser agentsRecording and replaying browser automation tracesSelector-free DOM interaction
Built With
- Language
- Python
- Frameworks
- Playwright · MLX · PyTorch · HuggingFace Transformers · Accelerate · ModelScope · pytest · Ruff · Hatchling
Tags
browser-automation · browser-use · local-first · agent-skill · playwright · qwen · single-token-logits · offline · dom-scraping · llm-inference · zero-hallucination · mlx · pytorch · computer-use · cli