正在加载视频...

视频加载失败

返回首页

introducing Jevbox: an open-source document drive that organizes itself, answers questions, and cites everything (all powered by Jev). TLDR; - upload anything and Jev categorizes and files it into the folder tree - search is hierarchical: Jev picks the folder, then the document, then the section. No embeddings, no...

kushalbyatnal's profile picture

Kushal Byatnal

7,505 subscribers

173,895 次观看 • 4 天前 •via X (Twitter)

教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

31 条评论

Kushal Byatnal 的头像
Kushal Byatnal3 天前

open source repo here:

Michael 的头像
Michael3 天前

where can i try this?

Yechan Do 的头像
Yechan Do3 天前

Cool. Jev is solving retrieval problems

Kushal Byatnal 的头像
Kushal Byatnal3 天前

if you squint, everything is a classification problem

Saad 的头像
Saad3 天前

gh repo?

Kushal Byatnal 的头像
Kushal Byatnal3 天前

here you go:

brexton 的头像
brexton3 天前

Insane

Kushal Byatnal 的头像
Kushal Byatnal3 天前

@andrewlu0 is insane

Darren Chow 的头像
Darren Chow4 天前

@ameyaajoshi the use cases with extend + jev are crazy

Josh Kaplan 的头像
Josh Kaplan3 天前

cool

Fred Dogan 的头像
Fred Dogan3 天前

this is cool, organizing folders is a pet peeve of mine. I really don't enjoy it. Notion could use a similar approach honestly. Cool use case for Jev, I have been building a tool router for machine payments with Jev it's quite interesting. Will launch soon too.

Sael 的头像
Sael4 天前

no vector db is the real flex here, cant wait to stress test the hierarchy

Aniruddha Ganesh 的头像
Aniruddha Ganesh3 天前

@theo I recall you doing something about file organisation and files not needing to be at one exact path. This seems like the most natural evolution of that ideao.

Sahibzada Allahyar 的头像
Sahibzada Allahyar3 天前

I’d use GLiDE for the folder → document → section choices. It beats Jev on Decision Index retrieval, 60.9 vs 55.4, and can reason further when two paths look plausible. That’s worth testing on the same document library.

Jack 的头像
Jack3 天前

The filing is the easy half. What actually breaks document search in a real company is that the drive holds three versions of the same policy and nothing marks which one is current. A citation only helps if somebody decided that page was still true.

flare on 的头像
flare on3 天前

Looks interesting

Mildo 🥽 的头像
Mildo 🥽3 天前

Is this a different kind of vector database? What’s the benefit over graphrag?

kartik bhardwaj 的头像
kartik bhardwaj3 天前

Retrieval-time permission checks are the part most RAG stacks get wrong, cached chunks serve after access is revoked. The failure I would eval first is miscategorization, a misfiled doc goes invisible to hierarchical search. AI engineer working on agent harnesses and evals.

Farzan Ansari 的头像
Farzan Ansari3 天前

people here are doing crazy things!

Johannes Laslo 的头像
Johannes Laslo3 天前

what problem does this solve? Is this advantageous to a local wiki style knowledgebase with vector database?

Saurabh Gayali 的头像
Saurabh Gayali3 天前

Super slick UI, but needing paid SaaS endpoints for search & parsing hurts. Wish it had native fallbacks for fast, non-autoregressive System 1 models like Laya for scoring/ranking + local OCR for files. A completely free, offline Jevbox stack would be amazing.

Crio Songo 的头像
Crio Songo3 天前

No vector DB is such a refreshing design, I’ll go check out the repo later.

Zuhayr Khan 的头像
Zuhayr Khan3 天前

What size library have you tested this on so far? Curious how many Jev calls a question spanning several folders needs.

catman 的头像
catman3 天前

The useful detail is that Jevbox checks permissions at retrieval, so losing access to a source also removes access to answers built from it.

Auspex-Aerie 的头像
Auspex-Aerie3 天前

this is amazing Great work!

Andrew Luo 的头像
Andrew Luo3 天前

@typesafeai built using the hierarchical classification cookbook ✍️

David T Kramaley 的头像
David T Kramaley3 天前

hierarchical classification is the sweet spot for auto‑organizing docs

Nirant 的头像
Nirant3 天前

I built this for HTML internally _yesterday_

Sujal 的头像
Sujal4 天前

Does it ever reshuffle the folder tree after you've already learned where things live?

Jhon Dennis 的头像
Jhon Dennis3 天前

文档自己会归类 提问还能带出处 这活以前得专人干

Lior Strugach 的头像
Lior Strugach3 天前

Sounds expensive, how much does it cost to run it all?

相关视频

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:32

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Hanako

29,894 次观看 • 11 天前

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build
0:22

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

NO1ennn

18,445 次观看 • 8 天前

Jev has been exploding across GitHub since launch, here's what people have already built with it if you have API access and don't know where to start, copy this: jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars jev-ultrafast - browser agent that picks every click itself, only calling a text model when it actually needs to type something. 16,758 stars jev-doom-agent - real Chocolate Doom compiled to WebAssembly, two engines running the same map, Jev picking the tactical macro every frame jev-t-rex-runner - the Chrome dinosaur game you've procrastinated with a hundred times, now played entirely by Jev picking jump, duck, or keep running typesafe-chess - Jev vs a real search engine, two games, colors swapped. the search won both, but overruled Jev's first instinct on roughly half the moves jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back none of these ten generate a single word of text. every one of them returns a number against an answer someone already defined full setup below, then run the three-question test from the article before you build an eleventh
0:24

Jev has been exploding across GitHub since launch, here's what people have already built with it if you have API access and don't know where to start, copy this: jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars jev-ultrafast - browser agent that picks every click itself, only calling a text model when it actually needs to type something. 16,758 stars jev-doom-agent - real Chocolate Doom compiled to WebAssembly, two engines running the same map, Jev picking the tactical macro every frame jev-t-rex-runner - the Chrome dinosaur game you've procrastinated with a hundred times, now played entirely by Jev picking jump, duck, or keep running typesafe-chess - Jev vs a real search engine, two games, colors swapped. the search won both, but overruled Jev's first instinct on roughly half the moves jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back none of these ten generate a single word of text. every one of them returns a number against an answer someone already defined full setup below, then run the three-question test from the article before you build an eleventh

Ryven

276,722 次观看 • 13 天前

Another insane Jev use case! Traditional database filters need precise, predefined conditions. But many questions are semantic: - Is this article mainly about software engineering? - Which topic best describes it? - How technically deep does it appear? These usually require moving rows into application code, invoking a model, parsing its output, and writing the result back. pg-jev is an open-source Postgres extension that exposes Jev through SQL functions. - jev() works inside WHERE - jev_prob() returns a probability - jev_choice() selects a label - jev_score() ranks rows across ordered levels. It needs no vector column or embedding index. Under the hood, pg-jev batches rows, sends them to Jev, and returns typed answers that SQL can filter, sort, group, and combine with exact predicates. The recording below runs it against real Hacker News stories stored in Postgres. It first shows the rows, then asks Jev to find software-engineering stories, classify them by topic, and rank them by technical depth. The final query reports requests, tokens, cost, and cache hits from the database session. GitHub repo: (don't forget to star it ⭐) Postgres keeps the data and controls the query, while Jev handles the part SQL cannot express as a deterministic condition. If you want to understand what Jev is doing under the hood, I also wrote a hands-on guide to building a Jev-style model with open models, entirely locally. Read it below.
0:28

Another insane Jev use case! Traditional database filters need precise, predefined conditions. But many questions are semantic: - Is this article mainly about software engineering? - Which topic best describes it? - How technically deep does it appear? These usually require moving rows into application code, invoking a model, parsing its output, and writing the result back. pg-jev is an open-source Postgres extension that exposes Jev through SQL functions. - jev() works inside WHERE - jev_prob() returns a probability - jev_choice() selects a label - jev_score() ranks rows across ordered levels. It needs no vector column or embedding index. Under the hood, pg-jev batches rows, sends them to Jev, and returns typed answers that SQL can filter, sort, group, and combine with exact predicates. The recording below runs it against real Hacker News stories stored in Postgres. It first shows the rows, then asks Jev to find software-engineering stories, classify them by topic, and rank them by technical depth. The final query reports requests, tokens, cost, and cache hits from the database session. GitHub repo: (don't forget to star it ⭐) Postgres keeps the data and controls the query, while Jev handles the part SQL cannot express as a deterministic condition. If you want to understand what Jev is doing under the hood, I also wrote a hands-on guide to building a Jev-style model with open models, entirely locally. Read it below.

Avi Chawla

289,304 次观看 • 3 天前

ANTHROPIC LEAKED A $4.2M FILE WHERE 4 AGENTS BUILD THE JEV SYSTEM IN 60 MINUTES, DOING $100K A MONTH four agents cost $0, and the system they assemble in an hour generates $100K a month scout → builder → critic → operator → JEV every agent is pinned to one exact model version, and none of them runs on "latest" the scout on Haiku 4.5 reads the market, the builder on Sonnet 5 builds everything, the critic on Opus 5 decides what ships the operator runs Haiku through the batch API at half price - the one agent that never has to hurry the builder takes 59% of the whole hour, because it's the one writing, and writing costs 5x more than reading short answers are cheap answers - and the whole economics rests on that one rule pin the versions in ROOT.md and next month JEV behaves exactly the same point it at "latest" and the model underneath updates quietly, no error, and the answers start to drift $100K a month is 334 customers at $299 four versions, one system - pin them and JEV stays JEV save this and paste it into Claude Code - let it build you these 4 agents ↓
1:28

ANTHROPIC LEAKED A $4.2M FILE WHERE 4 AGENTS BUILD THE JEV SYSTEM IN 60 MINUTES, DOING $100K A MONTH four agents cost $0, and the system they assemble in an hour generates $100K a month scout → builder → critic → operator → JEV every agent is pinned to one exact model version, and none of them runs on "latest" the scout on Haiku 4.5 reads the market, the builder on Sonnet 5 builds everything, the critic on Opus 5 decides what ships the operator runs Haiku through the batch API at half price - the one agent that never has to hurry the builder takes 59% of the whole hour, because it's the one writing, and writing costs 5x more than reading short answers are cheap answers - and the whole economics rests on that one rule pin the versions in ROOT.md and next month JEV behaves exactly the same point it at "latest" and the model underneath updates quietly, no error, and the answers start to drift $100K a month is 334 customers at $299 four versions, one system - pin them and JEV stays JEV save this and paste it into Claude Code - let it build you these 4 agents ↓

Sprytix

37,977 次观看 • 15 天前

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
4:17

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

CJ (Coding Garden)

114,987 次观看 • 19 天前

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren’t sure how to start experimenting with it, just copy this checklist: 1. agent-desktop Desktop automation. Read the system's accessibility tree, judge which button, menu, or input field to click next. 2. typesafe-mario Have Jev play Super Mario. No screenshots—just read the structured state in the emulator's RAM, then decide to run, jump, or dodge. 3. jev-drone Use Jev to control a drone. The underlying flight control still handles stability and safety; Jev just does higher-level judgments like climbing, braking, and navigating obstacles. 4. OneVOneJev 1v1 FPS in the browser. Every decision tick, judge movement, view angle, aiming, firing, and jumping. 5. jev-trader High-frequency market making on Monad testnet. Jev judges the next buy or sell based on spreads and trade direction, with model latency around 81ms. 6. Prism Doesn't directly have Jev place orders. It judges states like toxic flow, market pressure, mean reversion, etc., then hands off to the original strategy. 7. neo4jev Stuff Jev into a knowledge graph. At each node, judge the most worthwhile edge to take next, then follow it all the way. 8. jev-curate Use Jev to screen training data. For JSONL / Parquet, first judge quality, relevance, and risk, then decide which ones go into the next training round. 9. Canny Prevents Coding Agents from stubbornly claiming they're done. Look at tool outputs, code diffs, and test results, then judge if the completion claim is reliable. 10. killmyidea Input a startup idea, and Jev scores it from multiple angles, finally giving you KILL, FIX, or SHIP. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:24

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren’t sure how to start experimenting with it, just copy this checklist: 1. agent-desktop Desktop automation. Read the system's accessibility tree, judge which button, menu, or input field to click next. 2. typesafe-mario Have Jev play Super Mario. No screenshots—just read the structured state in the emulator's RAM, then decide to run, jump, or dodge. 3. jev-drone Use Jev to control a drone. The underlying flight control still handles stability and safety; Jev just does higher-level judgments like climbing, braking, and navigating obstacles. 4. OneVOneJev 1v1 FPS in the browser. Every decision tick, judge movement, view angle, aiming, firing, and jumping. 5. jev-trader High-frequency market making on Monad testnet. Jev judges the next buy or sell based on spreads and trade direction, with model latency around 81ms. 6. Prism Doesn't directly have Jev place orders. It judges states like toxic flow, market pressure, mean reversion, etc., then hands off to the original strategy. 7. neo4jev Stuff Jev into a knowledge graph. At each node, judge the most worthwhile edge to take next, then follow it all the way. 8. jev-curate Use Jev to screen training data. For JSONL / Parquet, first judge quality, relevance, and risk, then decide which ones go into the next training round. 9. Canny Prevents Coding Agents from stubbornly claiming they're done. Look at tool outputs, code diffs, and test results, then judge if the completion claim is reliable. 10. killmyidea Input a startup idea, and Jev scores it from multiple angles, finally giving you KILL, FIX, or SHIP. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

346,644 次观看 • 14 天前

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇
1:11

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

unicode

20,745 次观看 • 13 天前

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:24

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

202,492 次观看 • 15 天前

If you didn't feel the ongoing revolution, here is my second project I built with jev. Your software is drastically outdated. It contains a lot of instructions your CPU executes one by one. Why if we can simply ask Jev for the next instructions to execute Introducing Jevassembler! It is a new approach to execute something on CPU. You don't need to wait for code to be written, you don't need to compile anything and YOU DON'T NEED CODE. You just give it a task and Jev predicts the next instruction to execute. In runtime. who needs compilers if you have AI
0:28

If you didn't feel the ongoing revolution, here is my second project I built with jev. Your software is drastically outdated. It contains a lot of instructions your CPU executes one by one. Why if we can simply ask Jev for the next instructions to execute Introducing Jevassembler! It is a new approach to execute something on CPU. You don't need to wait for code to be written, you don't need to compile anything and YOU DON'T NEED CODE. You just give it a task and Jev predicts the next instruction to execute. In runtime. who needs compilers if you have AI

Dmitriy Kovalenko

224,757 次观看 • 17 天前

I got a rubik's cube to solve itself with TypeSafe AI 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!
0:34

I got a rubik's cube to solve itself with TypeSafe AI 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!

Paolo Rosson

207,767 次观看 • 19 天前

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: 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!
0:31

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: 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!

Archive

16,841 次观看 • 6 天前

this is pure f*cking treasure Engineer at TypeSafeAI just mapped 389 public Jev builds in one list: skills, MCP servers, SDKs, agents, benchmarks and guides ROUTING > jev-router sends every Claude Code task to the cheapest model that can do it > Switchboard picks the model and reasoning effort per task, then keeps it stable so the prompt cache survives > jev-oncall triages alerts: 418 ms p50, $0.04 per 1,000 alerts GUARDRAILS > jev-axi gates shell commands for Claude Code and Codex, 44/44 on its labeled set > hermes-jev-approvals: 8.7x faster approvals, 4.4x fewer prompts to the user > Sniff Test lints AI slop out of your writing at 182 ms a paragraph AGENTS > Jev Ultrafast: Jev picks every click, a small LLM only types > fast-jev-compaction scores your context instead of summarizing it > jev-browser-use reports 5 to 10x faster browser runs inside Codex SEARCH & RAG > jev-retrieval placed 2nd of 90 models on a reranking leaderboard > jevsearch: 83% Hit@1 against 41% for keyword search alone SDKs & MCP > clients for Swift, Go, Rust, Kotlin, Ruby, Elixir, .NET, Laravel and Spring > MCP servers for Claude Code, Cursor and Codex > Jev inside SQLite, DuckDB and Postgres, straight from SQL EVALS > pytest-jev checks LLM replies in 5.3 s where Claude took 27.1 s > a medical hallucination check at 92.9% accuracy, 204 ms, $0.03 per 1,000 OPEN MODELS > Laya answers in one ~35 ms forward pass > kev trains and runs on a MacBook GAMES, ROBOTS, TRADING > Jev plays Mario, Pokemon and chess > it drives a robot arm and a drone > it trades on Monad with 81 ms decisions 389 builds. one decision layer. go steal the ones you need
0:24

this is pure f*cking treasure Engineer at TypeSafeAI just mapped 389 public Jev builds in one list: skills, MCP servers, SDKs, agents, benchmarks and guides ROUTING > jev-router sends every Claude Code task to the cheapest model that can do it > Switchboard picks the model and reasoning effort per task, then keeps it stable so the prompt cache survives > jev-oncall triages alerts: 418 ms p50, $0.04 per 1,000 alerts GUARDRAILS > jev-axi gates shell commands for Claude Code and Codex, 44/44 on its labeled set > hermes-jev-approvals: 8.7x faster approvals, 4.4x fewer prompts to the user > Sniff Test lints AI slop out of your writing at 182 ms a paragraph AGENTS > Jev Ultrafast: Jev picks every click, a small LLM only types > fast-jev-compaction scores your context instead of summarizing it > jev-browser-use reports 5 to 10x faster browser runs inside Codex SEARCH & RAG > jev-retrieval placed 2nd of 90 models on a reranking leaderboard > jevsearch: 83% Hit@1 against 41% for keyword search alone SDKs & MCP > clients for Swift, Go, Rust, Kotlin, Ruby, Elixir, .NET, Laravel and Spring > MCP servers for Claude Code, Cursor and Codex > Jev inside SQLite, DuckDB and Postgres, straight from SQL EVALS > pytest-jev checks LLM replies in 5.3 s where Claude took 27.1 s > a medical hallucination check at 92.9% accuracy, 204 ms, $0.03 per 1,000 OPEN MODELS > Laya answers in one ~35 ms forward pass > kev trains and runs on a MacBook GAMES, ROBOTS, TRADING > Jev plays Mario, Pokemon and chess > it drives a robot arm and a drone > it trades on Monad with 81 ms decisions 389 builds. one decision layer. go steal the ones you need

NO1ennn

25,798 次观看 • 9 天前

Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For example, you can give it a set of possible choices, and Jev will classify the input text based on those choices, including a confidence score for each. Best of all: Jev is really fast and cheap, so you can use it in all sorts of applications. The first thing I built with it is a classifier to pick the hotels I want to visit. I use Apify to collect thousands of reviews, then classify them with Jev based on specific criteria I care about. You just couldn't do this reliably, but now you can. Link to the repository:
6:57

Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For example, you can give it a set of possible choices, and Jev will classify the input text based on those choices, including a confidence score for each. Best of all: Jev is really fast and cheap, so you can use it in all sorts of applications. The first thing I built with it is a classifier to pick the hotels I want to visit. I use Apify to collect thousands of reviews, then classify them with Jev based on specific criteria I care about. You just couldn't do this reliably, but now you can. Link to the repository:

Santiago

17,898 次观看 • 8 天前

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!
1:30

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

David Villalón

43,078 次观看 • 17 天前

you should spend an afternoon building a second brain with jev... here's how i'd set it up: > create one inbox for saved posts, articles, meeting notes and ideas... give your agent access to it > give jev your active projects and interests so it can sort incoming material into categories that mean something to you > have your agent find similar notes, then use jev to flag duplicates and spot which ones add something new > save everything with its original link and date so you can always check where it came from > whenever you start a task, have your agent search the archive and let jev score which notes are relevant > feed those into your writing agent before it starts working... your customer conversations, examples and previous decisions are already there writing a proposal? bring back what the customer said on the call and the case study that answers their objection. working on a post? pull up the idea you saved three weeks ago alongside your own notes on the topic. start with one project and the material you've already collected for it. ask your coding agent to build that workflow, then check what it brings back on your next real task.
0:23

you should spend an afternoon building a second brain with jev... here's how i'd set it up: > create one inbox for saved posts, articles, meeting notes and ideas... give your agent access to it > give jev your active projects and interests so it can sort incoming material into categories that mean something to you > have your agent find similar notes, then use jev to flag duplicates and spot which ones add something new > save everything with its original link and date so you can always check where it came from > whenever you start a task, have your agent search the archive and let jev score which notes are relevant > feed those into your writing agent before it starts working... your customer conversations, examples and previous decisions are already there writing a proposal? bring back what the customer said on the call and the case study that answers their objection. working on a post? pull up the idea you saved three weeks ago alongside your own notes on the topic. start with one project and the material you've already collected for it. ask your coding agent to build that workflow, then check what it brings back on your next real task.

J.B.

13,511 次观看 • 17 天前

Jev dropped barely a week ago and traders are already doing some wild sh*t with it. live order books. real-time signals. trading bots. entire AI hedge funds. here's what happened: > jev-trader · every ~0.3s asks Jev “buy or sell?” on Monad and trades > jev-trade · reads Hyperliquid order book -> Jev picks -> code sends the order > beebots · 3 OKX trading “bees”; every choice is Jev (paper trading by default) > QuantDinger · full AI trading OS; optional Jev gate = “should we trade at all?” > ai-hedge-fund · multi-agent “fund” with a Jev adapter for fast yes/no calls and that’s the funny part: Jev isn’t here to think. it’s here to make the call. the market moves -> Jev picks LONG / SHORT / HOLD -> code executes. no essays. no chain of thought. no expensive model debating every tiny market move. big models figure out the strategy. Jev handles the split-second calls. code makes it real.
0:27

Jev dropped barely a week ago and traders are already doing some wild sh*t with it. live order books. real-time signals. trading bots. entire AI hedge funds. here's what happened: > jev-trader · every ~0.3s asks Jev “buy or sell?” on Monad and trades > jev-trade · reads Hyperliquid order book -> Jev picks -> code sends the order > beebots · 3 OKX trading “bees”; every choice is Jev (paper trading by default) > QuantDinger · full AI trading OS; optional Jev gate = “should we trade at all?” > ai-hedge-fund · multi-agent “fund” with a Jev adapter for fast yes/no calls and that’s the funny part: Jev isn’t here to think. it’s here to make the call. the market moves -> Jev picks LONG / SHORT / HOLD -> code executes. no essays. no chain of thought. no expensive model debating every tiny market move. big models figure out the strategy. Jev handles the split-second calls. code makes it real.

kiosa

106,526 次观看 • 5 天前

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.
0:31

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

291,608 次观看 • 15 天前

He is 18 teaching AI at Stanford making $2.2M on agents - and in 60 minutes revealed how to repeat it from zero: 00:30 - 5% who build agents will replace the 95% who just use them 38:33 - Jev Engineering is the only thing you need to make $2.2M on an agent 52:47 - Claude + Jev 10x cheaper and faster right now after watching I built my first agent with Jev in 15 minutes and sold it to a million dollar company for $100k: save & watch - the article below shows how to use Jev Engineering to make Claude 10x cheaper and build a $2.2M agent.
1:11:34

He is 18 teaching AI at Stanford making $2.2M on agents - and in 60 minutes revealed how to repeat it from zero: 00:30 - 5% who build agents will replace the 95% who just use them 38:33 - Jev Engineering is the only thing you need to make $2.2M on an agent 52:47 - Claude + Jev 10x cheaper and faster right now after watching I built my first agent with Jev in 15 minutes and sold it to a million dollar company for $100k: save & watch - the article below shows how to use Jev Engineering to make Claude 10x cheaper and build a $2.2M agent.

Noisy

13,207 次观看 • 14 天前

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a browser agent built for speed ↳ 2. Fast-JEV-Compaction - squeezes your context down ↳ 3. JSON-Render - UI generated on the fly ↳ 4. Typesafe-MCP - plugs Jev into any client ↳ 5. JEV-MCP - a toolkit for judgment calls ↳ 6. Semdecide - a classifier right in your terminal ↳ 7. JEV-Codex-Router - sends every task to the model that fits it ↳ 8. Winnow - clears the junk out of your context ↳ 9. JEV-Review - sorts code reviews by what needs eyes first ↳ 10. Blink - finds your way around any repo ↳ 11. Agent-Desktop - runs your desktop for you ↳ 12. Typesafe-Mario - an agent playing Super Mario ↳ 13. JEV-Drone - flies a drone ↳ 14. OneVOneJev - a shooter in your browser ↳ 15. JEV-Trader - high-frequency market making ↳ 16. Prism - spots liquidity signals ↳ 17. Neo4Jev - walks a knowledge graph ↳ 18. JEV-Curate - screens training data ↳ 19. Canny - confirms a task is really finished ↳ 20. KillMyIdea - scores a startup idea before you sink time into it ↳ start where your work is: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone pick one, build on it this week, and you'll be the person on your team who actually knows Jev engineering when it gets asked for
0:24

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a browser agent built for speed ↳ 2. Fast-JEV-Compaction - squeezes your context down ↳ 3. JSON-Render - UI generated on the fly ↳ 4. Typesafe-MCP - plugs Jev into any client ↳ 5. JEV-MCP - a toolkit for judgment calls ↳ 6. Semdecide - a classifier right in your terminal ↳ 7. JEV-Codex-Router - sends every task to the model that fits it ↳ 8. Winnow - clears the junk out of your context ↳ 9. JEV-Review - sorts code reviews by what needs eyes first ↳ 10. Blink - finds your way around any repo ↳ 11. Agent-Desktop - runs your desktop for you ↳ 12. Typesafe-Mario - an agent playing Super Mario ↳ 13. JEV-Drone - flies a drone ↳ 14. OneVOneJev - a shooter in your browser ↳ 15. JEV-Trader - high-frequency market making ↳ 16. Prism - spots liquidity signals ↳ 17. Neo4Jev - walks a knowledge graph ↳ 18. JEV-Curate - screens training data ↳ 19. Canny - confirms a task is really finished ↳ 20. KillMyIdea - scores a startup idea before you sink time into it ↳ start where your work is: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone pick one, build on it this week, and you'll be the person on your team who actually knows Jev engineering when it gets asked for

Mr. Buzzoni

11,667 次观看 • 6 天前