devwithjev
reading now views
Submit a build

Browse builds

210 builds · page 5 of 6

tamaratran@tamaratran
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
0369GitHub·Tools & appsOriginal source ↗
Butochnikov@Butochnikov
Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.
0353GitHub·Tools & appsOriginal source ↗
AboveColin@AboveColin
Home Assistant integration for TypeSafe Jev. Ask a question about your house and get a probability, a choice or a score as an entity.
0311GitHub·Tools & appsOriginal source ↗
mrnugget@mrnugget
Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).
0307GitHub·Tools & appsOriginal source ↗
realZachi@realZachi
Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
0304GitHub·Tools & appsOriginal source ↗
vercel-labs@vercel-labs
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
0259GitHub·Tools & appsOriginal source ↗
JoshuaSP@JoshuaSP
Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results.
0230GitHub·Tools & appsOriginal source ↗
razorback16@razorback16
Open, Jev-compatible System One decision server on DiffusionGemma.
0217GitHub·Tools & appsOriginal source ↗
tinyhumansai@tinyhumansai
An integration with jev by typesafe.ai in Rust.
0205GitHub·Tools & appsOriginal source ↗
kunobi-ninja@kunobi-ninja
Rust client for the TypeSafe System One API (Jev).
0203GitHub·Tools & appsOriginal source ↗
binnash@binnash
PHP & Laravel SDK for TypeSafe AI's JEV Model series.
0201GitHub·Tools & appsOriginal source ↗
anilsenay@anilsenay
Unofficial Go client for TypeSafe's System One API and its model, Jev.
0179GitHub·Tools & appsOriginal source ↗
AboveColin@AboveColin
Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
0178GitHub·Tools & appsOriginal source ↗
fgn@fgn
Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation.
0177GitHub·Tools & appsOriginal source ↗
mateonunez@mateonunez
Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.
0175GitHub·Tools & appsOriginal source ↗
alterhq@alterhq
Dependency-free Swift 6 client for Jev Choice, Score, and Noul questions, with strict concurrency, retries, and offline transport tests.
0174GitHub·Tools & appsOriginal source ↗
Gaurav-Gosain@Gaurav-Gosain
Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text.
0173GitHub·Tools & appsOriginal source ↗
Kevthetech143@Kevthetech143
A small, extensible decision-to-action harness for TypeSafe Jev.
0172GitHub·Tools & appsOriginal source ↗
inanna-malick@inanna-malick
Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels.
0148GitHub·Tools & appsOriginal source ↗
dannote@dannote
TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.
0146GitHub·Tools & appsOriginal source ↗
pithings@pithings
A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
0143GitHub·Tools & appsOriginal source ↗
Eugene Boondock 🌍2️⃣Eugene Boondock 🌍2️⃣@eugeneboondock𝕏
I taught SQL to ask questions using jev: SELECT * FROM tickets WHERE jev_bool(body, 'Is this customer angry?') No embeddings. No keyword list. No LLM writing SQL. jevsql: natural-language predicates, a typed control plane that never lets an LLM touch your data... @typesafeai https://t.co/JtqOsiYoIl
0130X posts·Tools & appsOriginal source ↗
franfran@fran_rimoldi𝕏
made a color palette generator using jev, because why not? given the input, jev returns probabilities over ten hue families, scores for warmth / light / energy, and a font pick. code maps that onto oklch and paints the page. https://t.co/lAe0TlYKdz
0129X posts·Tools & appsOriginal source ↗
Gavin McKewGavin McKew@gavinmckew𝕏
Every company writes copy rules. Nobody enforces them after launch week. So I made the reviewer that never gets tired. It reads your marketing site on every PR and names each sentence that makes a claim with no evidence beside it. It's using Jev from @typesafeai It doesn't know your facts. It knows what a claim without proof looks like. https://t.co/bHrzAWVicC @MParakhin don't hate me
0125X posts·Tools & appsOriginal source ↗
Tim CheungTim Cheung@timche_𝕏
tenet using Jev is up to 275x cheaper and 104x faster than Claude agents 🤯 Same 2,000-line diff, same rules. tenet: 1.5 s, $0.0036. One Claude Fable 5.1 call: 157 s, $0.99. Your agent fixes its own review findings before you ever see the diff. https://t.co/Rr1BpU53ak
0116X posts·Tools & appscost$0.0036time1.5 sOriginal source ↗
Nikhil BafnaNikhil Bafna@zodvik𝕏
Created a one-off Chrome extension to remove low quality posts (filtered using Jev) from Twitter, and posts with videos. Feed has become so much better.
0108X posts·Tools & appsOriginal source ↗
Tim CheungTim Cheung@timche_𝕏
Spent a day building tenet, a review gate for code that agents write. It judges each commit, commit message and PR against rules written in plain language, using Jev by @typesafeai. The rules come from @poteto's unslop skill, @hvpandya's stop-slop, @dillon_mulroy's anti-slop and @mattpocockuk's new /pr skill. It also generates rules from your AGENTS.md or CLAUDE.md, and you can write your own rules and presets. Here an agent trips four of them, gets blocked in 1.07 s for $0.0003, and fixes its own findings.
0107X posts·Tools & appscost$0.0003time1.07 sOriginal source ↗
AMP⚡️AMP⚡️@arisetyo_v2𝕏
My first real experiment with Jev: project scorer. It takes the specs, source code, and graph (Graphify output) from a codebase, then analyzes them using Jev, Lizard, and Networkx to create project "quality metrics" based on a configurable rubric. https://t.co/lCryvd749u
0106X posts·Tools & appsOriginal source ↗
Ivan CamposIvan Campos@ivancampos𝕏
Using Jev to detect and classify a statement against 50 logical fallacies only takes a few hundred milliseconds and costs $0.000128 per 3k input token request. The response times make the UX feel instant! https://t.co/pwh2b7crGV
0102X posts·Tools & appscost$0.000128 per 3k input token requesttimea few hundred millisecondsOriginal source ↗
Brian ViaBrian Via@BrianVia𝕏
Guys I made an extension for LinkedIn using Jev from @typesafeai to remove anything it classified as ai-slop and this is what it left me - did it in under 200ms btw and only cost me a fraction of a penny. https://t.co/0falPlXy0N
0100X posts·Tools & appscosta fraction of a pennytimeunder 200msOriginal source ↗