Bbrowser-useBrowser & computer use

Jev Ultrafast

A browser agent that turns a single goal into a sequence of lightning-fast actions.

Explore repositoryVisit website
Jev Ultrafast project preview

Fastest and cheapest web agent

How it uses Jev

Give it one goal. TypeSafe's Jev picks an operation and an element. A small LLM writes text only when the operation is TYPE TEXT .

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to Jev Ultrafast

Browse all
hunch project preview

hunch

Browser & computer use
⚡ Browser agent that acts on a hunch: Jev (TypeSafe System One) picks every click in ~150 ms, an LLM is only needed when confidence drops. Zero-dependency Python on top of agent-browser.
HMade byHAR5HA-76631
jev-browser project preview

jev-browser

Browser & computer use
Browser use using Typesafe's Jev model
JMade byjkudish257
jev-ultrafast-mcp project preview

jev-ultrafast-mcp

Browser & computer use
Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.
JMade byjiawei68615
jev-drone project preview
Image 1 of 3

jev-drone

Jev for robotics
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
RMade byRomanSlack170
ego-jev-ultrafast project preview

ego-jev-ultrafast

Benchmarks & research
Jev drives your Ego Lite browser: one typed-choice request per step. Single-file, zero-dependency port of browser-use/jev-ultrafast with multi-model benchmarks and extra guardrails. Unofficial.
SMade byshikaizhong-design3
jev-agent-failure-benchmark project preview

jev-agent-failure-benchmark

Benchmarks & research
Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).
TMade byTokenTrim2

Yes / No

Demos & playgrounds
Free, no-signup Noul demo. Ask a question, get yes, no, or maybe, with web search when needed.
CMade byCommunity contributor
jevlike project preview

jevlike

Benchmarks & research
Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.
VMade byvinnylarouge1.3k
jev-cli (tumf) project preview

jev-cli (tumf)

Applications
Small dependency-free CLI for TypeSafe Jev
TMade bytumf13