#jev
45
2026-09-18
rorshopping/jev-on-a-laptop
B
Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.
2026-09-19
mmastrac/djev-spark
C
DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe
2026-09-19
mrnugget/jev-shell-history
C
Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)
2026-09-19
nidhi-singh02/agent-router
C
CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr
2026-09-18
sorrycc/typesafe-snake
C
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code
2026-09-19
r-ms/mini-jev
C
mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.
2026-09-18
standardagents/jevpilot
C
A playable Three.js driving simulator with Jev-powered autopilot
2026-09-26
UditAkhourii/quicksilver
C
Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
2026-09-19
kshetrajna12/reflex
C
A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.
2026-09-19
logicrw/awesome-jev-projects
D
Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync
2026-09-18
yibie/awesome-jev
C
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
2026-09-19
moritzkremb/jev-voice-browser
C
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
2026-09-19
razaanstha/ulka
C
Experimental browser agent powered by FX, Jev, and Vercel AI Gateway. Bring your own API key to read pages and automate browser tasks.
2026-09-26
YUTA-fywoo/jev-gui-delegate
C
AI-assisted Windows and Chrome GUI delegation for Codex: task contracts, local execution, Jev semantic decisions, recovery and outcome verification.
2026-09-19
jomatsu/pi-jev-auto-mode
D
Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.
2026-09-19
monteduro/killmyidea
D
Describe your startup idea. Jev decides: kill it, fix it or ship it.
2026-09-19
kavehmz/typesafe-playground
D
Interactive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.
2026-10-22
Show HN: Jev drives a browser – HN login and search in 8s for half a cent
未评级
I put this repo and site together as an educational reference for folks getting started with Jev / OpenAI Decisions API. This demonstrates how Jev can drive a browser (the idea being extract it into a skills file). On every step the page's controls are extracted into a table, and Jev picks an operation and a target, with a probability for every option. Try the HN login replay ( https://jev-browser.rovira.sh/#hackernews-login), Amazon ( https://jev-browser.rovira.sh/#amazon-cart), or run it live with your own key. Interesting bits: - Jev mean response time is 250ms (123–495 ms on the HN run). - Jev never sees the DOM, only a table of controls extracted from it ahead of time. It's in some ways, similar to the accessibility tree that good LLM browser skills use now. - Jev can't generate text (in a good way) so this need to be provided ahead of time, either by you or a complementary LLM. - Each step is stateless and costs a few thousand input tokens, under a tenth of a cent. Repo (three files, no dependencies): https://github.com/zurfyx/jev-browser-skill
2026-10-16
Amal-David/awesome-jev
未评级
Jev demos, projects, SDKs and skills, with source links and a curated X gallery.
2026-10-16
BudEcosystem/Bud-Decision-Studio
未评级
Bud Decision studio is an easy to use cross platform desktop application & serving system for Jev like models locally.
2026-10-16
OmniJev/awesome-jev-gallery
未评级
🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.
2026-10-16
agent-labs-dev/fastbrowse
未评级
A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.
2026-10-16
dorkitude/webctl
未评级
Smart web search CLI for agents, backed by Jev. Saves a lot of tokens.
2026-10-16
kyegomez/open-jev
未评级
an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch
2026-10-16
marcreichel/laya-php
未评级
Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.
2026-10-05
Show HN: Create Git workflows using Jev
未评级
Introducing Metis , A minimal clean workflow orchestrator framework to create workflows using Jev.
2026-10-05
Show HN: Jev-pages – Building landing pages real time with Jev
未评级
An experiment using Jev to generate landing pages in real time. Jev is great at picking between different options so I attempted to break down the langing page UI into a set of choices for the model to choose from. How this works: 1. Users type what kind of page they want and Jev decides what each line is (headline, fact, assertion etc.) 2. Jev makes choices for each layer of the page (opening, stage, light, depth etc.). Parameterizing design is hard (impossible?) but this took some tuning with Claude 3. A full page is constructed with a single call of about 90 questions. Of course using an LLM would be more prudent for step 1, but I wanted to check the limits of Jev's understanding (it works pretty well in my opinion!).
2026-09-29
Show HN: Decide – Jev decisions in the shell, scripts, and agent skills
未评级
All software makes decisions. Code handles the deterministic ones. Decision models like Jev handle the judgement calls. A decision model takes context and questions with a fixed set of choices, and returns answers with a calibrated probability. No prose, nothing to parse. Decision models are 200x faster and 400x cheaper than LLMs making comparable judgements. I wanted to play around with decision models in more places and without writing code or manually calling APIs. I wanted scripts to read like natural language and agents to be able to pick up the tool and use it after simply reading the help output. brew install vsekhar/tap/decide decide --set-config --model typesafe:jev-latest --api-key API key: <paste your API key> decide "Is Atlanta the capital of Georgia?" yes # Choose from among options decide "What kind of weather is typical in Florida?" \ --option rainy \ --option sunny \ --option snowy sunny # Provide context (32k context window) decide --context @ticket.txt \ "Which team handles this ticket?" \ --option shipping \ --option billing \ --option returns billing # Pick a level, least to most, explain each to the model decide --context @ticket.txt \ "How urgent is this ticket?" \ --level not_urgent="Customer feedback or feature request" \ --level somewhat_urgent="Customer problem, not blocked" \ --level urgent="Customer blocked" somewhat_urgent # Multiple questions in one call, name questions for easier parsing decide --context @ticket.txt \ "Which team handles this ticket?" \ --name team \ --option shipping \ --option billing \ --option returns \ "How urgent is this ticket?" \ --level not_urgent \ --level somewhat_urgent \ --level urgent \ "Should we issue a refund?" team=billing somewhat_urgent yes # Script-friendly exit codes if decide --context "$body" "Is this message spam?" -q; then mv "$file" spam/ fi Other features: - Confidence: gate on the model's confidence in its answer with --min-confidence and --fallback - Question files: load questions from a file, useful for detailed questionnaires under version control - Scriptable: 0 is decided or yes, 1 is no, 2 is unsure, 10 is your mistake, 11 is network/model problem - Agent skill: agents can get cursory information about files quickly and cheaply before or instead of reading them (example skill included in the repo) - token efficient, no MCP - Statistics and distribution: output the model's confidence and probabilities across your choices - JSON: read context as JSON objects, write decisions as JSON objects - Streaming: decide once per line from stdin using --each (for JSONL pipelines) - Economical: two orders of magnitude cheaper than LLMs (Jev: $0.042/Mtok input, free output) - Fast: typical latency of 200ms end-to-end (400 token context with 5 questions) - Scalable: unlimited questions per call, processed in parallel Limitations: - Typesafe or OpenRouter API key required - macOS 26+ pre-built via Homebrew; macOS 15 and Linux build from source (requires Swift 6.2) - Jev only (so far the only publicly available decision model) See also: - DecisionModels ( https://github.com/vsekhar/DecisionModels): Swift library for static and dynamic decision model calls, inspired by Apple's FoundationModels library, and powering decide. - llm-typesafe ( https://github.com/simonw/llm-typesafe): JSON-oriented input and output, integrated into the general purpose (and very popular) llm command by simonw which is written in Python and has 14 runtime dependencies. Swift 6.2, Apache 2.0 What do you think about the command line model? How are you plugging decision models into your systems?
2026-09-24
Show HN: I Built a GIF Decider with Jev
未评级
Hey everyone! I wanted to try out a fun use case for Jev and had this idea before where I could use AI to decide what GIF is best to use, LLMs truly suck at this. I built this just an hour ago with the TypeSafe AI skills and I am routing it through Cloudflare AI Gateway. Have a look here: https://gifdecider.com/
2026-09-24
Show HN: Open Code for Jev
未评级
Hi everyone, I built this TUI for jev with the main goal to make Jev immediately accessible and to be able to have decision templates similar to how we have skills for LLMs. Additionally I wanted to have a dashboard for our own software displaying the usage of Jev and being able to improve the decisions over time by giving jev feedback in the context. I really love the look and feel of early open code so this is what I went with. Please let me know what you think about it.
2026-09-24
Show HN: Local Software Factory – running multiple coding agents in parallel
未评级
Hi, as I kept getting confused by having multiple Claude sessions open, last weekend I decided to combine two of my favorite emerging technologies and give it a try: Software Factory and JEV. The idea is simple, inspired by GitHub Actions, I wanted a way to "queue" agent work on my local laptop, with the ability to define different pipelines via YAML. Each pipeline runs in its own Git worktree, so it's isolated from the others. I'm using some pipelines: dev: code → test → commit plan: plan → human review → code → test → commit security: code → human review → test → security review → commit frontend: code → React test → build → commit A request can move up and down the pipeline and be reworked if an agent or JEV flags it! I'm also using JEV to check if a potential secret is leaked, if the coding agent output asks for human review, etc. The real magic happens when you take a single Agent session as the main driver. You can then plan and queue multiple features at once. I think it worked out pretty well, so I open sourced it: https://github.com/stratonext/software-factory You can try it yourself with: uv tool install software-factory Note: You need a JEV key if you want to use the judging steps.
2026-09-24
Show HN: Jev-mice – mouse colony simulation using Jev and deterministic engine
未评级
I built this as a "hello world" for exploring TypeSafe Jev as an alternative to local classifiers. There's a link to the detailed design write-up on the demo page, and that write-up in turn has a link to the repo. I formed some opinions on Jev from this exercise, and am interested in others' perspectives. And am sharing this in the hope it might be useful to someone else.