This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
A minimal browser harness for agents
Teach an AI a browser task once. Run it on a thousand rows
Pixelpi lets any AI model use a real web browser, and reads each page in about 2,000 tokens instead of 180,000. Record a solved task once, then replay it or run it across a whole dataset in parallel, with no model in the loop and self-healing when pages change. Six tools, raw Chrome DevTools Protocol, your own key. Open source, MIT, one npm install.
👋 Hi Product Hunt! I'm Harsh, the maker of Pixelpi.
Browser agents are expensive for a dumb reason: most of them make the model read 180,000 tokens of raw HTML to look at one page, then bolt on 20–30 tools on top. You pay for that twice—in cost and in worse decisions.
pixelpi takes the opposite bet, borrowed from Mario Zechner's pi: the model is already smart enough, so keep the harness thin.
Instead of raw HTML, it reads the browser's accessibility tree (the semantic view the browser already builds) and gives the model 6 clean tools instead of 30.
The result:
1. 37×–100× fewer tokens per page on real websites.
2. Token usage stays nearly flat as pages grow.
3. Then it goes further.
Once a task works, you can record it into a trace.
A trace:
1. replays with no model in the loop
2. is free, deterministic, and fast
3. addresses elements by their accessibility role instead of brittle CSS selectors
4. survives most layout changes
5. self-heals with the model only on the step that drifted
The part I'm most excited about:
1. A trace is a function.
2. Record it once with an example input, then run it across a CSV or JSONL in parallel.
3. Each row replays for about zero tokens.
4. A 5,000-row job costs one model run plus, at most, a handful of repairs - instead of 5,000 full agent loops.
You can also:
1. call a trace from code as a typed function
2. let any other AI agent introspect it as a clean JSON contract
3. What you can do with it
4. Fill hundreds of forms
5. Scrape thousands of listings
6. Check prices and accounts across a list
7. Give your own agent a browser tool it can actually afford and reason about
8. Turn a one-off automation into a cheap, repeatable, self-healing job
It's open source under MIT, available on npm as pixelpi, and built directly on raw CDP with no Playwright.
I'd love your feedback, and if it saves you a 30-tool MCP install, a ⭐ helps others find it.
npm i -g pixelpi
GitHub: github.com/josharsh/pixelpi
About A minimal browser harness for agents on Product Hunt
“Teach an AI a browser task once. Run it on a thousand rows”
A minimal browser harness for agents was submitted on Product Hunt and earned 5 upvotes and 1 comments, placing #73 on the daily leaderboard. Pixelpi lets any AI model use a real web browser, and reads each page in about 2,000 tokens instead of 180,000. Record a solved task once, then replay it or run it across a whole dataset in parallel, with no model in the loop and self-healing when pages change. Six tools, raw Chrome DevTools Protocol, your own key. Open source, MIT, one npm install.
On the analytics side, A minimal browser harness for agents competes within Open Source, Artificial Intelligence and GitHub — topics that collectively have 582.2k followers on Product Hunt. The dashboard above tracks how A minimal browser harness for agents performed against the three products that launched closest to it on the same day.
Who hunted A minimal browser harness for agents?
A minimal browser harness for agents was hunted by Harsh Joshi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of A minimal browser harness for agents including community comment highlights and product details, visit the product overview.
Harsh Joshi