Projects built with Jev

No projects found. Clear filters

A faster browser agentBreaking: 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 ↓Gregor Zunic

Computer use, sped upIf you blink you might miss it Jev + Computer use = 100x faster than any LLM @typesafeaisav

Jevmaxxing with NotteJevmaxxing on Notte browser sessions ⚡️ > Type a task, hit start, and watch Jev @typesafeai pick every actions super fast from the page's action space. > new action space every step > Notte cloud browser over CDP > step-by-step replay of everyNotte

Discord event researchI’ve done the Discord grind time to delegate As a Community Lead, Discord research keeps sending me through the same loop: @browser_use are mogging with the new model >Find the right channel >Scroll through announcements >Collect event names and dates Jev + Luna now handlesConviction1000%

Jev macOS LoopI built a Mac agent that sorts files without sending screenshots to the model. Jev macOS Loop: 9 test files into 3 folders in 7.39 seconds. Real Finder. Every file checked afterward. Pixels stay local. Text goes to Jev. Open source.Dr. Josh C. Simmons

An X scrolling agentI'm having Jev scroll Twitter for me now. Finally something that flicks as fast as a humanHarold Bracy

Automatic agent and model selectionthanks to @typesafeai jev I no longer have fill out all of those fields on prompt boxes. It picks the agent / model / computer / folder for me. - For a major rewrite it uses Fable + Claude Code. - Changes to an ios app run on one of my macsSawyer Hood

A faster Slack agentJev made our Slack agent 2x faster ⚡️ Our agent can be quite slow because it needs to read skills and figure out which tools to call. We used @typesafeai's new model to speed this up by first passing it the prompt and classifying the best skill, tool and params to use beforeJohn Yeo

A voice-controlled browserTried JEV from @typesafeai and vibe-coded a little voice-controlled browser agent. Just tell it what to do and it navigates the browser for you. Pretty crazy how fast it is 👀🤯Yatharth Verma

Voice intent to tool callsPlayed around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far,Pratim Bhosale

An offline research decision gategot early access to @TypeSafeAI (Jev). in my last post on autoresearch vs dream-rsi, the quiet bottleneck was: how do you score 28+ dreamt tree branches offline without waiting minutes on chat LLMs? tested Jev as the sub-100ms offline decision gate: left: linearOtto🐾

Ego Lite shopping decisionsego lite + Jev + DeepSeek Flash = stupid fast. ⚡ 3.71s for 20 Amazon product decisions. GPT-5.6 Sol: 54.45s Same task. Same result. 10/10 on both. Less reasoning. Faster decisions. 1× speed.ego

An assistant without a wake wordAi is evolving. Jev can be armed at all times. I can speak freely and it knows ( from probabilities ) if im asking my computer to do something or blaberring away at something else. no wake word. speed + affordability + intelligence is getting to the point where an alwaysMax Blade

Hipershopping with Agentcardbreaking: Agentcard + Jev + Kernel = Hipershopping ⚡ asking an agent to go buy stuff for you online is usually: - expensive (bc of tokens going back and forth) - slow (bc of tokens going back and forth) - unsafe (bc there's no safe/compliant way to share card info w/agents)IT guy

AgentRun reusable workflowsToday I’m excited to show you our new harness called AgentRun, built with @pidotdev and @typesafeai's Jev. It’s built for an agent to learn how to do a job, code itself a general solution, and then get out of the way.Miguel Ríos Berríos

Self-healing agent swarmsYes, but can Jev do multi-agent swarms? Enterprise solutions that self-heal live productions before clients can even refresh their browsers? (Demo slowed down for humans)Casey Lee Race

Starchild prompt routingStarchild just became the first professional-grade app to integrate Jev from @typesafeai We use Jev to help route to LLMs which gave a 20x decrease in cost and 6x increase in speed for prompt classification Here it is classifying prompts in real-time (avg time was 140ms)Starchild

Just-in-time model selection in GooseExperimentation with Jev from @typesafeai and our harness @goose_oss Use Jev to take a prompt and JIT select a model just before the turn runs. Jev and models like it will be useful in many areas and this is just early prototype code on a first ideaAlex Hancock

Phone automation with step verificationFinally got access to Jev, so I gave it a phone. Plain English in: sign in, add a ₹900 Travel expense, turn on dark mode. LLM made 10 steps once. Jev handled every step twice: what to tap + did it work. 10/10. p=1.00. ~400ms each. Entire run: $0.0006.Rudra

Instant decisions inside a SaaS agentAs an experiment, we plugged Jev by @typesafeai into the AI Agent of our SaaS. The speed is absolutely incredible. It answers faster than I can type or click and costs ~100x less than a classic LLM. 🤯 And when a request still needs a full LLM, it tells us in a third of aLennart

A dual-brain Jev and LLM agentGot access to Jev and wanted to build a proof-of-concept for amazing things it makes possible. I built a Dual-Brain agent pairing System 1 reflexes (Jev) with System 2 deliberation (LLM). In the 8x run below, you can watch both brains firing live: - Jev resolves a multi-clauseLeo Tavares

Voice-controlled Mac computer useI built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.Andy Gao

Real-time voice control for a browserwhoa this actually worked! Jev lets me control my browser in real time with my voice now > i talk > transcript sent to Jev > jev returns probabilities in ~300ms > browser clicks costs: $0.0002 per decision i'm stunned how fast this is. when i asked it to "go back", it evenMoritz Kremb

Computer use across operating systemsi built computer use using @typesafeai ! it is 155x cheaper than opus 5, ~20x faster, and generalizes across OS's more on how it works in the vid & thread below:aaron

Mac computer use with local perceptionOkay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets.Milind S

Stagehand browser control with Jevwe built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then StagehandKyle Jeong

Criteria-based model routing in EveUltra-fast, criteria-based model routing using Jev from @typesafeai.eve