BrowseBrawl
What if browser agents battled to generate training data?
Details
- External ID
- 47248684
- Source
- HN
- Company
- —
- Product
- BrowseBrawl
- Website domain
- browser-brawl.com
- Launched
- March 4, 2026
- Cohort
- —
- Upvotes
- 30
- Upvotes percentile
- 0.7958179581795818
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I remember watching the AlphaGo documentary in 2017. What stood out to me was that the model got drastically better when it started competing against itself. GANs clicked for me similarly: a generator and discriminator competing, and somehow the competition is what produces something remarkable.I've been curious whether this principle generalizes to today's agents.So mehulkalia and I built Browser Brawl at the YC / BrowserUse hackathon last weekend and won first place. It is a fun experiment in which an attacker agent tries to complete tasks on live websites while a defender agent injects JavaScript to sabotage it.The analogy isn't perfect, because browser tasks aren't zero-sum. But our hypothesis is that an agent faced with an adversary should produce more interesting training data than one navigating clean, static environments.Try it on: http://browser-brawl.comGitHub: https://github.com/RichardHruby/browser-brawlDemo Video: https://youtu.be/NIoFXv-JvBY(Skip to [0:55](https://www.youtube.com/watch?v=NIoFXv-JvBY&t=55s) to see the agents “brawling” in the arena :), [1:52](https://www.youtube.com/watch?v=NIoFXv-JvBY&t=1m52s) to see the browser traces generated)Would love to chat with anyone building or training browser agents. Happy to dive in below!
Enrichment
- Theme
- browser automation and scraping for AI
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- browser agents compete to generate training data
- Manually corrected
- False
Could you build this?
Partial Building the Next.js UI and running basic Playwright scripts is simple, but orchestrating concurrent adversarial browser agents with real-time DOM mutation and fine-tuning data pipelines is complex.
What it would actually take: The platform requires a distributed runner infrastructure (e.g., Docker containers running isolated Chromium instances via Playwright/Browserbase) coordinating real-time WebSocket communication between two LLM agents. The core difficulty is creating deterministic DOM mutation engines (saboteur) and structured trajectory-logging middleware to capture replayable step-action-observation datasets for RL/SFT. This requires expertise in browser automation at scale and reinforcement learning data pipelines.
Discussion
18 comments analyzed.
Concerns raised: Authenticity of comments (paid comments question)
Feature requests: Handicaps/abilities for attacker agents to increase difficulty
Competitors
Other products that read as similar to this one — 127 launches clear the similarity bar, closest 8 shown.
Attention rank: #31 of 128 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 121 days after the earliest competitor.
- Agent-browser-shield · hn · 2026-06-03 · 7 upvotes · similarity 0.52
- Agent Arena · hn · 2026-02-06 · 47 upvotes · similarity 0.50
- Vuln Box Arena · ph · 2026-09-23 · 1 upvotes · similarity 0.46
- Clawfight.ai MCP-driven agentic game play · hn · 2026-09-11 · 13 upvotes · similarity 0.45
- CivBench a long-horizon AI benchmark for multi-agent games · hn · 2026-02-25 · 12 upvotes · similarity 0.44
- BrowserAct · ph · 2026-06-25 · 561 upvotes · similarity 0.43
- Open-source playground to red-team AI agents with exploits published · hn · 2026-03-15 · 30 upvotes · similarity 0.42
- I trained a chess engine to play like humans · hn · 2026-05-10 · 14 upvotes · similarity 0.41
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.