Skip to content
JevDirectory.org
CommunityTools & Integrations15 starsVerified 2026-09-22

jev-ego

A TypeScript browser agent for ego lite that turns one natural-language goal into CLICK, TYPE_TEXT, or SELECT on a numbered element table, with Jev choosing the operation and target in one request.

Category
Tools & Integrations
Published by
Community
Author
romaluev
Added
2026-09-22
Tagscommunitytypescriptbrowseragentscli

Highlights

  • One TypeSafe request returns the operation and its target together; speculative target questions put two decisions in one network round trip.
  • The whole loop - TypeSafe, the text helper, and CDP - runs inside one ego-browser nodejs process, with no Python process or Browser Harness hop.
  • No screenshots: Jev consumes a structured element table, and visible controls, names, values, and text are read in one browser call per snapshot.
  • Commands include serve, observe, act, suggest, step, run, flights, smoke, probe, and stop; serve keeps one TaskSpace in a loopback daemon.
  • A first snapshot after navigation costs 3 CDP calls, and shadow roots, frames, canvas, uploads, and pop-up tabs stay outside the MVP.

Quickstart

bash
pnpm install
pnpm build
cp .env.example .env   # add TYPESAFE_API_KEY and TEXT_MODEL_API_KEY
pnpm exec jev-ego serve --url https://en.wikipedia.org/wiki/Main_Page --goal 'Find and open the article about Gödel’s incompleteness theorems.'
pnpm exec jev-ego step
pnpm exec jev-ego stop

Watch out

MIT-licensed and not a general web-automation SDK; needs macOS with ego lite installed, ego-browser on PATH, Node 20+ and pnpm, plus TYPESAFE_API_KEY and a TEXT_MODEL_API_KEY for typing.

More like this

172GitHub stars
A browser-use agent where Jev picks one action per step from a page's interactive elements. Runs as an MCP server, CLI, or library and returns a step trace, screenshot, and console errors.
Tools & Integrations#community#typescript#mcp
Communityjev-browser
112GitHub stars
A Jev-first command-line coding agent: natural-language requests are routed by Jev to one of ten bounded review and triage workflows, and unsupported requests fall back to the Pi coding agent or a workflow Stanley stages for promotion.
Tools & Integrations#community#typescript#cli
Communitystanley-code
106GitHub stars
An open-source browser agent extension for Chrome and Edge that browses, fills forms, clicks, and collects data, letting any extension-capable browser act as an AI browser with your own LLM key.
Tools & Integrations#community#typescript#browser
Communitydoma
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A playable 16-judgment demo

AI multiple choice, not essay writing

Screening agent actions with Jev

Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.

Image
Image
Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

Cua's small System One models

A 706K-parameter form filler

cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom

Cua
Cua
@trycua

1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua

Image
Reply

Navigating Neo4j with Jev

Jev 这个 waitlist 还是很给力的,昨天申请,今天就能用上。 给已经拿到 API、但还不知道怎么玩的人整理了一份 Awesome Jev,目前我能确认到的 Jev 项目基本都在这里: 1. jev-ultrafast Browser Use 做的高速浏览器 Agent。Jev Show more

Image
思维怪怪
思维怪怪
@0xLogicrw

前 OpenAI 研究员 Diogo Almeida 创办的 TypeSafe AI 推出新模型 Jev。它有点像一个能读懂自然语言的超级分类器,不生成文本,只返回选项、分数和概率,专门给软件做判断。 普通大模型需要一个 token 一个 token 往外生成,Jev 则可以并行给出多个结果。TypeSafe 还用新的 RLCD

Reply