BrowserOS -- browser agents with GPT-OSS, local llms
Hi HN – we're the founders of BrowserOS.com (YC S24), and we're building an open-source agentic web browser. We're a fork of Chromium and our goal is to let non-developers create and run useful agents locally on their browser. --- When we launched a month ago, we thought we had the right approach: a "one-shot" agent where you give it a high-level task like "order toothpaste from Amazon," and it would figure out the plan and execute it. But we quickly ran into a problem that we've been struggling with ever since: the user experience was completely hit-or-miss. Sometimes agent worked like…
In plain words
BrowserOS is an open-source browser built on Chromium that enables non-developers to create and run AI agents locally for web automation tasks. Users can instruct agents to complete actions like online shopping, with the system handling planning and execution. The software aims to make agent-based automation accessible to general users, though the creators are actively refining the user experience to improve reliability, as early versions showed inconsistent performance when executing complex tasks.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN – we're the founders of BrowserOS.com (YC S24), and we're building an open-source agentic web browser. We're a fork of Chromium and our goal is to let non-developers create and run useful agents locally on their browser. --- When we launched a month ago, we thought we had the right approach: a "one-shot" agent where you give it a high-level task like "order toothpaste from Amazon," and it would figure out the plan and execute it. But we quickly ran into a problem that we've been struggling with ever since: the user experience was completely hit-or-miss. Sometimes agent worked like magic, but other times the agent would get stuck, generate a wrong plan, or just wander off course. It wasn't reliable enough for anyone to trust it. This forced us to go back to the drawing board and question the UX. We spent the last few weeks experimenting with three different ways a user could build an agent: A) Drag-and-drop workflows: Similar to tools like n8n. This approach creates very reliable agents, but we found that the interface felt complex and intimidating for new users. One tester (my wife) said: "This is more work than just doing the task myself." Building a simple workflow took 20+ minutes of configuration. B) The "one-shot" agents: This was our starting point. You give the agent a high-level goal and it does the rest. It feels magical when it works, but it's brittle, and smaller local models really struggle to create good plans on their own. C) Plan-follower agents: A middle ground where a human provides a simple, high-level plan in natural language, and the LLM executes each step. The LLM doesn't have to plan; it just has to follow instructions, like a junior employee. --- After building and trying all three, we've landed on C) as the best trade-off between reliability and ease of use. Here's the demo https://youtu.be/ulTjRMCGJzQ For example, instead of just saying "order toothpaste," the user provides a simple plan: 1. Navigate to Amazon 2. Search for Sensodyne toothpaste 3. Select 1 pack of Sensodyne toothpaste from the results 4. Add the selected toothpaste to the cart 5. Proceed to checkout 6. Verify that there is only one item in the cart. If there is more than one item, alert me 7. Finally place the order With this guidance, our success rate jumped from 30% to ~80%, even with local models. The trade-off: users spend 30 seconds writing a plan instead of just stating a goal. But they get reliability in return. Note that our agent builder gives a good starting plan, and then the user has to just edit/customize it. --- You can try out our agent builder and let us know what you think. We're big proponents of privacy, so we have first-class support for local LLMs. You can try GPT-OSS via Ollama or LMStudio and it works great! I'll be hanging around here most of the day, happy to answer any questions!
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, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca