Jev picks the tool, a fast LLM fills the arguments: 49 of 49 tasks solved.
Idan Levin’s team ran Jev on their open WebMCP benchmark. Jev picks each tool the website exposes, and Mercury 2.5 writes the arguments. That setup solved 49 of 49 tasks, at about 112 times lower model cost than GPT-6 Astra with computer use and code execution. Jev driving the page directly, through a modified Ultrafast, solved 25 of 49.
Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
@gregpr07 · Agents & browsers · ~$0.004 · ~7 s
@gregpr07
X post
Agents & browsers
~$0.004
~7 s
After every Claude Code message, Jev decides in ~0.3 s whether it holds a decision, rule or bug worth keeping, and jevmem saves it as one line in JEVMEM.md.
@jetwaniavinash · Agents & browsers · ~0.3 s
@jetwaniavinash
GitHub
Agents & browsers
-
~0.3 s
Write Playwright steps like "add the most expensive item to the cart". Jev finds the right buttons and fields, fills forms and checks the result.
Andrey Popov · Agents & browsers
Andrey Popov
GitHub
Agents & browsers
-
-
A Claude Code and MCP hook where Jev answers seven yes/no risk questions per tool call to allow, ask or deny. Usage and benchmark numbers are in the repo.
Jaz · Agents & browsers
Jaz
GitHub
Agents & browsers
-
-
We just ran Jev on our WebMCP benchmark. The result: basically broke the benchmark. Jev + Mercury 2.5 (a fast, low-cost LLM) using WebMCP solved 100% of the tasks at roughly 112× lower model cost than GPT-6 Astra using computer use with code execution. Compared to Astra using Show more
