Agents that run on Jev instead of screenshots: Browser Use, Playwright and Stagehand builds, each with the speed and cost its author reported.
181 builds · page 5 of 6
Neha Sharma
@hellonehha
As Jev (@typesafeai) is the talk of the town, and people are having fun finding new use cases for it.
I built a real-time demo of smart AI agent routing for anyone working on AI tools, agents, or products.
this is what I have done for one of my project.
https://youtu.be/c8qV0f4XnRY
Holy crap, who the hell did this?!!
Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent.
GitHub's already at 925 stars, repo's called Hermes-Jev-Skills.
You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on.
Which model answers, which skill to load, which memories matter, what survives when context gets cut.
Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too.
No dependencies, no patching Hermes core, and your API key never touches the agent
Link's right here: http://github.com/kerpopule/hermes-jev-skills
The catch? Jev itself is a paid cloud API.
The skills run on your machine; the decisions don't.
But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!
JEV IS INSANE
your coding agents forget everything the second the session ends.
Every fix. Every dead end you already hit. Every "no, not like that."
Gone. Tomorrow you teach it all over again.
Someone just open sourced the fix, and it runs on Jev.
It's called Beacon, by @asymptotelabs.
It pulls in your session history from Claude Code, Codex, Cursor, OpenCode and 20+ other agent tools and turns it into one shared memory.
But storing everything isn't the hard part.
Most agent runs are GARBAGE to learn from.
Failed commands.
Wrong turns.
One off hacks you'd never want repeated.
Save all of that and your agent just gets confidently worse.
So Beacon keeps the full history, and Jev decides what actually earns a spot in memory.
Promote it.
Send it for review.
Or throw it away.
That's a decision you need on thousands of sessions, which is exactly why it has to be cheap.
The runs that survive get turned into reusable skills.
So something Cursor figured out on Monday shows up in your Claude Code session on Tuesday.
Your agents stop starting from zero.
Every good run makes the next one smarter.
Repo: http://github.com/Asymptote-Labs/agent-beacon
Star it and save this.
follow @cyrilXBT
Your agent doesn't need a bigger brain. It needs a faster one.
Most agent decisions are tiny — urgent or not, which queue, yes/no. We run them through frontier models anyway. TypeSafe's new Jev does it in milliseconds for a fraction of the cost.
#AIAgents #Jev
En regardant Jev et Recursive Mass, je peut être sûr d'une chose les LLM ne sont pas la voie royal pour être le cerveau des agents, du moins pas pour longtemps.
Jev même n'est pas encore au top du top sur ces probabilité montre déjà ces preuves pour ses prises de décision (plus rapide que des LLMs)
Et Le Recursive Mass (pensées latentes sous forme de nombres) montrent qu'il est plus efficace pour les agents de communiquer entre eux partageant leu états internes plutôt que générer du texte compréhensible par des humains.
Une chose est clair, on ne doit pas utiliser les IAs pour nos agent commet on les utilises pour nos discussions.
Les Modèles n'ont pas fini d'évoluer :)
I LEAKED THE JEV STACK I RUN MY AGENTS ON, IT CAUGHT 11 OF THEM IN ONE NIGHT BEFORE THEY BROKE SOMETHING
Agents don't fail at writing code, they fail at deciding, which file to open, which hunk matters, whether to run that command, whether they're actually done.
Every one of those comes back as a paragraph you have to parse, and none of them come back with a number telling you how sure it was.
So I made them typed, a confidence on every answer, and a gate written in code, not in the model, that acts, holds, escalates or refuses.
Ran it on my own repo last night, 30 tasks, 4 agents in parallel, 360 judgments at 311 ms each, four cents for the whole thing.
19 shipped with nobody watching, 11 got stopped cold.
Those 11 are the whole product.
We built a Stanford Town powered by Jev.
It isn’t a game demo, there is no player.
The residents decide where to go, who to meet, and when to talk. Humans can only watch their pixel world unfold.
Demo + code:
github.com/NevaMind-AI/je…
#Jev #AIAgents
Jev Founder, Diogo Amogo, just released 12-page PDF on building a Jev Harness for coding agents
this is a 10-step blueprint on how to make your coding agents 200× faster and 400× cheaper:
step 1 → meet Jev: the LLM writes, the harness executes, Jev decides what each turn sees, where it routes and whether it runs
step 2 → ask the question that breaks every agent: how would you design one if LLMs had no KV cache?
step 3 → stop routing blind: Opus → Sonnet → Opus costs 6.19 vs 4.15 for pure Opus, because handing back reprocesses the whole context
step 4 → follow the tokens: reading and searching take 56.2% of tool turns and 46.5% of tokens. Writing code is under 10%
step 5 → score every chunk per query: hide, short summary, long summary or full. Compress after the question, not before
step 6 → disclose tools in tiers: one-line snippets for 100s of tools, schema on demand, docs for one-off queries. Batteries stop costing context
step 7 → load instructions by condition: touching *.tsx loads the style guide, billing/ loads its gotchas file, and compaction can't erase either
step 8 → route by trust, not just difficulty: secrets and infra stay on first-party frontier models, public docs go to the cheapest one
step 9 → share one retrieval pass: cross-model review, eval generation, ELI5 explainers and live progress pages all run read-only in the background
step 10 → gate every command: programmable allow / ask / deny policies that read a script before it runs, not just its name
Send this PDF and the article below to your Claude Code or Codex instance and start shipping 200× faster.
Great minds! I've been building a stylized SF with Opus too, just without the pets. My cars follow rules on the real street network, lanes and traffic lights included. Jev driving pedestrians is tempting though. How many agents can it run at once?
What stands out to me in the Jev + Grok Bot setup is the division of work:
Jev decides. Grok Bot acts. Human stays in control for anything irreversible.
That’s a much cleaner agent architecture than asking one model to do everything.
Cheaper, faster, and easier to reason about.
@typesafeai @grok
Jev has been blowing up lately.
If you already have API access but don't know where to start, just copy this checklist:
1. jev-browser
Drives a real headless browser through MCP, CLI or a library. Jev picks one action per step from the page's clickable and typeable elements, and scores whether the goal is met or the run is stuck. https://github.com/jkudish/jev-browser
2. jev-browser-agent
Per-step browser decisions at about a second. One request asks "which operation" and "which target" together, and confidence under 0.6 escalates to a bigger model or to you. https://github.com/smartdio/jev-browser-agent
3. typesafe-jev-bridge
Zero-dependency OpenAI-compatible bridge. Use typed yes/no, choice and score judgments from Claude Code, Cursor, Cline or any OpenAI SDK, over CLI or HTTP. https://github.com/RevocGG/typesafe-jev-bridge
4. pilot-typesafeai-jev
Jev inside LangGraph and Deep Agents. One request asks three questions, plain code picks the route, and only the winning route spends chat model tokens. https://github.com/jyje/pilot-typesafeai-jev
5. building-with-jev-skill
An agent skill for writing programs that call Jev: question design, state structure, thresholds, and how to diagnose a question that answers wrong. https://github.com/dbreunig/building-with-jev-skill
6. jev-skill
Guided setup plus evaluation workflows, with a read-only presence check and no silent provider switches or fabricated probabilities. https://github.com/wuyoscar/jev-skill
7. awesome-jev
Source-backed catalogue of what people actually shipped, sorted by category, with limitations noted per entry. https://github.com/yibie/awesome-jev
8. awesome-typesafe-jev
Field guide with SDKs, live demos, agent tools and independent evaluations, including where the vendor numbers came from. https://github.com/AbdelStark/awesome-typesafe-jev
9. awesome-jev-by-typesafe
Evidence-backed use cases, patterns and starter code, with the 70 to 500 ms latency claim marked as vendor-reported. https://github.com/Anil-matcha/awesome-jev-by-typesafe
10. awesome-jev (cobanov)
The widest catalogue right now: SDKs in Go, Java and JS, MCP connectors, guardrail experiments and studies. https://github.com/cobanov/awesome-jev
Copy these complete Jev blueprints - then read the full Jev setup below ↓
Built Cortex, a local MCP server: Claude plans, a fast layer does the clicking.
Same Mac-app task: computer use 23 s → Cortex 0.8 s
One action: ~5 s Claude round → 0.25 s, no model
24 tools: browser, Mac apps, GitHub search, safety gate
Measured on my Mac. @typesafeai #JEV