GitHubCoding and code review
gallant
A customizable linter that asks a decision model your fuzzy rules.
madxmike
4Updated Nov 10, 2026
The newest builds with Jev
855 projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.
- 855builds
- 181guides
- 21use cases
Diogo Almeida
@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 cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
Newest first, 33–65 of 1072. All 1072 in curated order
GitHubCoding and code review
DeciLabel
A GitHub Action that labels issues and pull requests with a decision model.
EvanProgramming
1GitHubOpen source
local-jev
An offline drop-in for the Jev API, as one Rust binary.
ronitgupta138
2< 18msGuidetypesafe.ai
Jev 1.14.0 + experimental features for dreamers
TypeSafe’s JevDay post: jev-1.14.0 as jev-preview, image input on 1.13 and 1.14, the Box type and opt-in long context, all behind headers and none of them production-ready yet. jev-latest moves to 1.14 a week after 14 October.
GitHubOpen source
Dex
An open-source, Jev-compatible decision model on an Ettin-1B encoder.
CanadaOrNaw
171.4%GitHubAgents and browsers
LevelDez
A 3D interior level designer where a yes/no model presses the buttons.
yeme-oss
0
Ian
@dumbfook
take control of your timeline back with an open source chrome extension I just released, power with jev or any other decision model you would like github.com/icpmacdo/signa…
GitHubSocial feeds
Signal & Noise
Our guidemadewithjev.com
Jev question types: Choice, Score and Noul
Choice picks one of up to 255 options, Score places text on 2 to 10 levels you describe, and Noul returns the probability of yes. Plus Box, the Jev 1.14 bounding box in preview. How to write each question, and the mistakes TypeSafe documents.
yessir
@JanahYsr
ran microsoft-decision-1 on my private eval suite (n=3000). Microsoft-Decision-1: 60% F1 VS Jev-1.13: 90% F1 draw your own conclusions but @CompleteSkeptic is right about public benchmarks @satyanadella just put the jev in the bag please
XBenchmarks and evals
Microsoft-Decision-1 against Jev on a private eval
- Microsoft-Decision-1
- 60% F1
- Jev 1.13
- 90% F1
- Cases
- 3,000
cola_runner · AI experiments
@cola_runner
Microsoft Decision 1 vs Jev 1.13 playing Contra. Same gameplay settings: same prompt and starting state, 30 lives, 6 frames/action, 600 decisions each. Microsoft on the left, Jev on the right. No lookahead or action overrides. Jev got farther. Neither cleared Stage 1.
Stanislav Sorokin
@stas_sorokin_
Jev raised $870M at $7.5B yesterday. On 262 of our real decisions it beat Claude Haiku 5.5, 204 to 177. TypeSafe's decision model got that valuation weeks after launch, in the same week Anthropic shipped Haiku 5.5 at $0.10 per million input tokens. So we checked whether a cheap general model can do the deciding. Haiku 5.5 got the labeled holdout cases from 17 decision systems we run every day, with the same instructions, word for word. → Right picks: Jev 204/262, Haiku 5.5 177/262 → By system: Haiku won 1, tied 5, lost 11 → Cost of the 262 calls: $0.058 on Haiku, $0.022 on Jev (2.7x) → Median answer: 1.16 s vs 375 ms → Biggest gap: "which builder gets this task" 6/12 vs 10/12 The twist: the one system Haiku won is the one that asks for judgment. "Did the agent really finish the task": Haiku 11/11, Jev 9/11. One caveat: those instructions were tuned on Jev for weeks. Haiku read them cold. Would you put a general model or a decision model behind your agent's routing? Repost this now, because "Haiku is cheap enough for everything" is turning into a default nobody measured. Follow @stas_sorokin_ for numbers from AI systems running in real production.
XBenchmarks and evals
Jev against Claude Haiku 5.5 on 262 real decisions
- Jev
- 204 of 262
- Claude Haiku 5.5
- 177 of 262
- Cost, Jev
- $0.022
- Median answer, Jev
- 375 ms
Guidedocs.typesafe.ai
Images
TypeSafe’s reference for image input: the TypeSafe-Danger-Zone-Images header, PNG and JPEG only, 16 MiB per file, 256 to 1568 pixels per side, 32 MiB per request, and images billed as input tokens with no separate charge.
Avi Chawla
@_avichawla
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: https://github.com/realZachi/pg-jev (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.
XDocuments and OCR
Semantic database filters
David K 🎹
@DavidKPiano
I mixed Jev + an espresso (state) machine. Turns out, Jev's a pretty good barista ☕ Introducing Jevspresso: XState determines what's possible, Jev decides the next move. Order in plain language, or break stuff and watch Jev cope. Try it: jevspresso.dev
Nate Berkopec
@nateberkopec
I liked this idea, so I built my own version which uses Jev + Luna to make this basically free for any Pi session. github.com/nateberkopec/d…
GitHubContext and memory
A You Should Know plugin for Pi, on Jev and Luna
Our guidemadewithjev.com
Jev confidence: when to act, ask or escalate
Jev's confidence comes from the answer's own probabilities, and a Noul has none. How it is computed, the thresholds TypeSafe's cookbooks used, the lines builders drew, and how to set yours from what a mistake costs.
Sumanth
@Sumanth_077
I built a data analyst agent with Jev as the review layer! Qwen handles the main agent work, Jev acts as the review layer, and Vercel eve runs the agent loop, tool execution, and human approval flow. The agent takes a plain-English question about the data, inspects the database schema, writes the SQL, runs the query, and explains the result. The interesting part is what happens around that main loop. Qwen is responsible for generating the SQL and the final answer, while Jev reviews the parts where semantic judgment is actually useful. Anything that can be checked reliably with code stays deterministic. Jev reviews the agent at three points: - Before the agent starts, it checks whether the user's question is clear enough to answer from the available data. - After Qwen generates the SQL, it checks whether the query actually represents what the user asked. - After the query runs, it checks whether the final explanation is grounded in the returned rows. For example, we tested it with: “Who is our best customer?” The question sounds simple, but “best” could mean highest revenue, most purchases, highest average order value, or something else. Instead of letting Qwen silently choose a metric, Jev flagged the question as ambiguous and asked for clarification. The same separation applies to SQL execution. Qwen can propose a query, but it cannot decide whether that query is safe to run. The tool accepts only a single read-only `SELECT`, SQLite runs in read-only mode, results are capped at 200 rows, and queries without a `WHERE` clause can require human approval before execution. Those checks do not need another model call. But a query can be completely safe and still answer the wrong question. A deterministic rule can verify that the SQL is read-only. It cannot reliably judge whether a query for “revenue last month” accidentally calculates revenue across all time. That is where Jev comes in. It reviews the proposed SQL against the original question and schema before execution. After the rows come back and Qwen writes the explanation, Jev reviews that answer again to check whether the claims are actually supported by the returned data. The project uses a local SQLite sales database, Qwen through the Vercel AI Gateway, Gradio for the interface, and only two database tools: "inspect_schema" and "run_sql". No single model is responsible for everything. Qwen generates, Jev reviews, deterministic code controls execution, and Vercel eve manages the agent loop and approval flow. GitHub Repo: https://github.com/Sumanth077/Hands-On-AI-Engineering/tree/main/ai_agents/nl_data_analyst_agent 100% open source.
XAgents and browsers
A data analyst agent with Jev as the review layer
Kevin
@kevincodex
meet jev spider . it decides the size, color and position of any website components and rearrange them base on its preference powered by jev jev-spider.fly.dev
Live siteUI
jev spider
Madison Rickert
@MadisonJRickert
Anthropic released native mods for customizing Claude Code yesterday, so I did the obvious thing and built a Jev-based classifier for auto mode! 2x faster permission checks! github.com/madisonrickert… #ClaudeCode #Jev
Diogo Almeida
@CompleteSkeptic
Types Beyond Decisions: box We’re also releasing a new type that is somewhere in the gray area of decisions: a single bounding box. We warned you there’s a reason we call them System One Models! (only on jev-preview)
Guidex.com
Types beyond decisions: box
Diogo Almeida of TypeSafe on the new Box type: one bounding box per question, somewhere in the grey area of decisions, and only on jev-preview.
Paone
@paonx_eth
i sent a crawler through github's new ai repos from the last 30 days. this is what it looks like 1 crawler turns into 128 2,000 repos, every readme, every word it steps on each one goes to jev with one question: is this worth your time? 99.3% got thrown out. wrappers, copies, empty readmes, lists of lists 9 survived: 01 colibri · runs a 744b model on 16gb of ram and a big ssd. slow, but it's yours 02 voicebox · clone a voice from a few seconds of audio. 23 languages, nothing leaves your machine 03 BrowserSkill · tencent. claude code or codex works in your logged-in browser while you keep working 04 security-audit-skill · the skill cloudflare's bug-hunting harness grew from 05 open-code-review · alibaba's internal ai code reviewer. ~1/9 the tokens of claude code on the same model 06 agent-skills · 25 senior-engineer workflows: /spec /plan /build /test /review /ship 07 OpenResearch · turns claude code or codex into a research agent: papers, hypotheses, experiments 08 WeKnora · tencent. drop in your docs, get rag answers, an agent and a wiki that maintains itself 09 ECC · 68 agents and 293 skills for claude code, codex and cursor. 272k stars 4 of the 9 come from alibaba, cloudflare and tencent. big tech is open-sourcing the ai tools it runs on itself links in the reply. save this
XDocuments and OCR
2,000 new AI repos, one question each
- Repositories read
- 2,000
- Thrown out
- 99.3%
- Crawlers
- 128
koha
@kohawithstuff
I made Jev AI control the NPC in this game 👉🏼 gta.koha.wtf
Live siteGames and real time
Jev controls the NPC
Burak Karakan
@burakkarakann
I built a query layer that automatically routes the queries to one of the configured query engines using Jev, all running on top of Iceberg. Fast decision models unlock interesting use cases indeed. Should we open-source this?
XRouting and model choice
A query router on top of Iceberg
Our guidemadewithjev.com
Jev pricing
What Jev costs and what that buys: $0.042 per million input tokens, output free, and a median of $0.000065 per decision across 15 published runs. As of Oct 2026 new signups do not get free credits.
Dr. Shawn
@aroogle
I’ve built an AI system using Jev and Groq that turns your speech into powerful visual slides, charts and animations as you talk with 70-300ms latency. Should I open source it or charge people to use it so that I can buy more hedera-hashgraph:native ? Kind of love the addictive feeling of open sourcing things… just feels so legendary
Mastra
@mastra
Last week, we launched: 1/ Classifiers with Jev 2/ Jira, GitLab and incident.io integrations for Mastra Factory 3/ Memory hooks 4/ VPC-isolated Postgres for Mastra platform + a lot of smaller improvements.
XSDKs and integrations
Classifiers with Jev in Mastra
Pedro Martins
@nikuscs
Having some fun doing my own Grok Bot @bot ( Dots, Muse ) alternative with @tan_stack start, @pidotdev + @Cloudflare durable objects! 💅 - Multi-harness Support - Multi Decision Room Routing ( Jev, LLM Judge, Roundtable ) - Memory for Bots, Rooms & Global - Reactions 👍 - Daemon runs locally + web on cloudflare - File Support with R2, Room data & Bot Data exportable on CF durable. Will open-source next week hopefully, so give a follow & stay tunned. I was going to use some open-source alternatives or fork them, but most of them are damn sloppy, my ideia is to use this for myself since OpenClaw & Hermes lack group collaboration & a proper mobile / responsive design. Dots is not available in EU, Grok is "locked" to grok models but for me its still the best in terms of UX/UI overall so congrats to Cursor & Xai Team :p
XRouting and model choice
A group chat bot with decision room routing
Alex Warren
@exrhizo
New @typesafeai Jev capabilities! Some decision models can ask questions about images but can they ask questions with images? 🧵 How to get the most out of the new Jev launch
Guidex.com
How to get the most out of the new Jev launch
Alex Warren’s thread on asking questions with images, not only about them, and how to get the most out of Jev 1.14.
NatashaTheRobot
@NatashaTheRobot
I built a small AskHIG CLI tool + agent plugin to help the agent load only the RELEVANT HIG guides into context via an /askHIG command. It uses @typesafeai Jev to decide which guides, so all you need is a personal typesafe API key and you're all set! I would open source it, but don't want to get in trouble with 🍎... If you'd like access, reply with your github username in the comments and I'll add you to the repo!
XContext and memory
AskHIG
Ayush Gupta
@madmecodes
Found this pretty interesting repo: herdr + jev = agent router You give it a coding task, and it routes it to the right agent + model + reasoning effort based on the task and your available quota. Supports Cursor, Claude Code, Codex, and OpenCode. Basically a load balancer for your coding agents. https://github.com/nidhi-singh02/agent-router Thanks @nidhisinghattri
XRouting and model choice
herdr + jev, an agent router
Simon Shg
@ShengSSX
2 AI colleagues just booked us a demo off someone's random post online Ava and Owen are the two agents running our prospecting in @Parall_HQ. they live in our @Parall_HQ workspace like everyone else on the sales team, and @typesafeai Jev makes the quick judgement calls for them > Jev reads every post, Ava wakes up only for the ones that fit us > Jev rates every account, Ava only works the best ones > Owen writes the email, our human AE approves > Jev sorts the replies, Owen only chases the interested ones you don’t need to hand them leads. jevable makes it possible for proactive agents to own a job at 86% less cost than agents that check in every 30 min
GitHubAgents and browsers
Jevable
- Always-on cost
- 86% lower
- Caught of what mattered
- 85%
- Benchmark events
- 334
Our guidemadewithjev.com
How do I get Jev access?
How to get Jev access as of October 2026: TypeSafe signup and console keys, or a gateway key from Vercel, OpenRouter, Cloudflare, Netlify, LiteLLM or Pydantic. Signups are open; new accounts get no free credits.
Aditya Rao
@dev_adityarao
Catching AI agents that secretly collude usually means reading their minds. I just read their chat instead, using Jev by TypeSafe AI It named the colluders 85% of the time. Built for the AI Swarm Dynamics Hackathon by @grove_research & @aidigest_. Thanks for letting people join online, I really enjoyed it!
The newest Jev builds, by the day they were added
Same directory, different order: the entries added most recently, rather than the curated order the home page opens in. The date on a card is the day it was added here, not the day its author published it — this directory is newer than most of the work in it.