webbrain-one/webbrain
Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠
About the project
A Chrome and Firefox extension that puts an AI agent in a side panel: it reads pages, answers questions, and performs tasks — clicking, typing, navigating — using the LLM of your choice.
Useful for
- Ask the agent to summarize the current page or find specific links on it
- Fill in a form and click a button on a site using Act mode
- Connect a local Ollama or llama.cpp server instead of a cloud API
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 4 stars so far today, about 10 expected by the end of the day.
- Over the last two days the pace is 2.7× that of the previous week and a half.
- GitHub Trending JavaScript today: #14, +18 stars.
- Recent forks include notable developers: @keysemails (220 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,178
- Today
- 4 · ≈ 10 by evening
- Forks
- 133
- Issues and pull requests
- 2,736
- Watchers
- 7
- Language
- JavaScript
- Latest release
- v38.0.13 · October 1, 2026
- Created
- April 6, 2026
- Last push
- October 2, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- October 2, 2026GitHub Trending JavaScript today: #14, +18 stars
Similar by description
-
1.0
ipenywis/laya-ultrafast
A local port of the jev-ultrafast browser agent that makes action decisions with the open-weight Laya model via MLX instead of a hosted API. Apple Silicon only, and it runs browser tasks without per-step cost.
-
1.9
wy-coliney/jev-browser-use
A browser Skill for Codex: Jev handles routine actions (navigation, clicks, toggles, scrolling) while Codex handles text input, visual judgment, and final verification.
-
0.0
Player-YN/BrowserKitten
Chrome MV3 side-panel extension with an AI agent that operates the current tab: select on the live page, describe the outcome, and get an editable office file. BYOK, sandboxed, no server.