Lightweight browser automation powered by Claude 3.5 Sonnet
Hey HN! I'm excited to show off Cerebellum, a new open-source tool designed to automate browser tasks using large language models (LLMs). Cerebellum is an LLM-based AI agent that interacts with web sites using mouse and keyboard interactions, much like you would. So it works on web sites whether or not they have an API. The only requirement is that you use a Selenium-supported browser like Chrome, Firefox, or Safari. It’ll even work on Electron apps with a bit of setup! Furthermore, Cerebellum is open-source! We’d love both your feedback and contributions. The GitHub repo is here:…
In plain words
Cerebellum is an open-source browser automation tool that uses Claude 3.5 Sonnet to interact with websites through mouse and keyboard actions, similar to human browsing. It works with any website regardless of API availability and supports Selenium-compatible browsers like Chrome, Firefox, and Safari, as well as Electron apps. Designed for developers who need to automate web tasks, it operates without requiring API access and is built on MIT-licensed open-source code.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! I'm excited to show off Cerebellum, a new open-source tool designed to automate browser tasks using large language models (LLMs). Cerebellum is an LLM-based AI agent that interacts with web sites using mouse and keyboard interactions, much like you would. So it works on web sites whether or not they have an API. The only requirement is that you use a Selenium-supported browser like Chrome, Firefox, or Safari. It’ll even work on Electron apps with a bit of setup! Furthermore, Cerebellum is open-source! We’d love both your feedback and contributions. The GitHub repo is here: https://github.com/theredsix/cerebellum. And the license is MIT. Currently, it uses Claude 3.5 Sonnet’s newly released computer use ability, but the ultimate vision is to crowdsource a high quality set of browser sessions to train an open source local model. Other than that, there is still a lot more work to do: Python SDK, supporting more LLMs, .... So help is very welcome. I'm eager to hear what you think! — Han Wang
Does the same job
all alternatives →
- BHBrowser Harness – Gives LLM freedom to complete any browser taskApr 2026 · github.com · ▲134
Hey HN, We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it's trained on. We gave the harness the ability to self correct and add new tools if the LLM wants (is pre-trained on) that. Our Browser Use library is tens of thousands of lines of deterministic heuristics wrapping Chrome (CDP websocket). Element extractors, click helpers, target managemenet (SUPER painful), watchdogs (crash handling, file downloads, alerts), cross origin iframes (if you want to click on an element you have to switch the target first,…
Tabstack Browser AutomationJul 2026 · tabstack.ai · ▲388Automate the web in your app or agent, no browser to host
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com