Broswerable- open source browser automation library for agents
Hi HN, Sid here. I made Browserable, an open-source and self-hostable JS library (MIT license) for building agents that can execute web tasks, track status and fetch results: https://github.com/browserable/browserable. It allows you to build agents that can navigate sites, fill out forms, and extract information. It is currently at 90.4% on the Web Voyager benchmark. With this library, you can: - Run a browser agent suite in your local machine with one command- npx browserable. - Integrate into existing code with REST APIs/ SDKs. - Self-host the browser agent and…
What it does
In the maker’s words, at launch
Hi HN, Sid here. I made Browserable, an open-source and self-hostable JS library (MIT license) for building agents that can execute web tasks, track status and fetch results: https://github.com/browserable/browserable. It allows you to build agents that can navigate sites, fill out forms, and extract information. It is currently at 90.4% on the Web Voyager benchmark. With this library, you can: - Run a browser agent suite in your local machine with one command- npx browserable. - Integrate into existing code with REST APIs/ SDKs. - Self-host the browser agent and scale without being tied to any single browser/ browser infrastructure/ LLM provider. It comes with a UI to run a task and an admin interface to trace, track and debug LLM calls (and costs). Works with multiple browser providers (Steel, Hyperbrowser, Browserbase) and concurrency restrictions. We built Browserable because we enjoyed building AI agents to automate tasks for our B2B SaaS startup, but we were frustrated at how hard it was to set up and maintain reliable automations even for simple tasks since the groundwork did not exist. We had to integrate with multiple browser providers with various concurrency restrictions, multiple LLM providers with various rate limits and there was no easy way to tie all the logs back to one single task to analyze the accuracy, latency, and cost of the implementation. We are hoping to make it easier to build, test and improve agents without having to write all of the infrastructure from scratch. We would love to know what you are building and if this library would be useful, or how we could make it more useful for you!
Does the same job
all alternatives →
- ARA remote browser product, open-sourced2019 · github.com · ▲253
- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
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 · 26d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
