Projects built with Jev

No projects found. Clear filters

Claude Code context compactionI got access to Jev and immediately plugged it into Claude Code to see if it actually FIXES the biggest pain of agent workflows: context compaction > result: pretty wild Quick context for those who missed it: Every Claude Code session has a context window that fills up fastkaize

Cascade Search typed query filtersA search bar that knows when it doesn't know. cascade-search is a 27K-parameter model that parses queries like "open bugs from sam since last week" into typed filters, in your browser, in 0.25 ms. When it isn't sure about a word, it asks Jev. Only that word.Zaid

Fast pull-request walkthroughsOkay, I see the vision @typesafeai This problem has been plaguing me for months. LLMs on their own were taking ~5+ minutes to generate review walkthroughs of even small PRs. With Jev? A few seconds at most. GAMECHANGER.thud

An npm package gate for coding agentsi used Jev to decide whether a coding agent should ingest an npm package. paste a name. fetch the real README and agent files. jev returns allow or refuse. code does the rest.Hatif

Tenet review gates for agent-written codeSpent 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 andTim Cheung

Native Rust network-traffic monitoringWhat if an AI watched your computer’s traffic and told you when something looked unusual? Couldn’t do it with an LLM. Too slow. @typesafeai’s Jev is fast enough. I wired it into a native Rust app. Built a Rust SDK while I was at it. 🦀Phillip

Parallel adversarial browser testingthanks to @typesafeai's Jev we now have massively parallel browser-based adversarial testing suite that tries to break each release. and it costs pennies.Rafal Wilinski

Judgment cache vs semantic cachegot access to @typesafeai Jev, and my first use case was building a judgement cache. I compared it with a semantic cache. One uses cosine similarity with a >0.90 threshold. The other uses Jev.ᴮᴷ

Predicting the next shell commandJev picking the next command from shell historyThorsten Ball

A semantic circuit breaker for agentsJev unlocked a new way to stop AI agents from spinning. Agents do not always repeat the same action. Sometimes they try different things based on the same wrong assumption. I built a semantic circuit breaker around that. In one stuck run: 12 model calls -> 4 19.9K tokens ->Ashutosh Mathore

RADAR ranks relevant developer resourcesdevelopers keep asking “has anyone solved this?” so I built a test for @typesafeai Jev: RADAR finds the repos, packages, issues + papers jev ranks what’s relevant / actionable / worth opening first Codex one-shotted the whole test and came up with the idea first case: passkeysTedOS

Jevcal confidence-threshold calibrationEveryone picks Jev confidence thresholds by vibes. 0.95? 0.5? I built jevcal. Give it your data and say "I need 99% accuracy". You get the exact threshold, how much Jev can handle, and how much still needs an LLM. Open source, one command. @typesafeaiAbhishek kothari

AIBackends Jev API integrationAIBackends web API now supports Jev by @typesafeai If you need some abstraction from your main app where you can customise the integration, you can use this API layerMelvin Vivas

Skill Router for Claude CodeJust hacked a fun little project - Skill Router (Open source) using Claude and Jev @typesafeai Why? I have ~ 90 Claude Code skills installed and use maybe five. The rest are fine, I just forgot they existed, and Claude won't reach for a skill on its own unless you call it. SoLomesh Dutta

Nanocode with selective memory compactioni added Jev compaction to a small agent with searchable memory. this is a fork of nanocode with some extra tools to grep a memory.md file + use Jev compaction to remove unnecessary memories.Kyle Jeong

Touchpress mobile end-to-end testingmy mobile e2e testing library powered by @agent_device and AI sdk now supports Jev from @typesafeai Same test, same loop: Jev: 29s, $0.003 Haiku 4.5: 37s, $0.07Robert Soriano

Intelligent ordering for code diffsI tried using Jev as an intelligent ordering tool for diffsJustin Garcia

Fourteen checks for every pull requestgot Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to @typesafeai → 14 typed checks come back as probabilities: hardcoded secret, sqlPaolo Rosson

Natural-language queries inside PostgreSQLI think I just cooked something 🔥 jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function. WHERE jev(people, 'could work from home') or WHERE jev(people, 'name sounds european') 129 rows judged in ~1sZachi

A codebase complexity classifieri built a codebase classifier with Jev and this might be the solution to overengineered code that agents create what should I test Jev on next?vogel

Email fraud detection with Jev and KimiJev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails toHassan

Jev as a QA testerYou can hire Jev from @typesafeai as your QA testerKrzysztof

Jev inside a security pipelinethese are results of using jev on one of our security pipelines. we already have to use smaller (and dumber) models to make it economic and this model does it over 5x cheaper, faster and while maintaining much higher accuracy. i don't normally hype over new model releases butGreg Pstrucha

Jev-review feedback for coding agentsbuilt `jev-review` @typesafeai it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇Niaz Morshed