Skip to content
JevDirectory.org
CommunityRepos & SDKs5 starsVerified 2026-09-22

jev-tree

A TypeScript library that walks a taxonomy and calls Jev once per level, so a choice can cover thousands of leaves despite Jev's 255-option limit per question.

Open github.comreachjalil/jev-tree
Category
Repos & SDKs
Published by
Community
Author
reachjalil
Added
2026-09-22
Tagscommunitytypescriptsdkclassificationtaxonomy

Highlights

  • Defaults to 32 options per Jev call and allows maxFanout up to 255; oversized sibling lists are partitioned into labeled buckets.
  • Node ids need not be legal Jev choice keys: the library sends o0, o1, and so on, then maps results back to your ids.
  • Timeouts and provider failures return reason unavailable instead of inventing a leaf; maxDepth 16 and maxCalls 64 also stop the walk.
  • On a 320-leaf incident catalog with 180 labeled tickets, truncating to 255 captured 0% of the tail while the authored tree recovered it.

Quickstart

bash
npm install jev-tree
npx jev-tree                         # offline demo, no key
npx jev-tree --live --shape taxonomy.json --state "the record"

Watch out

MIT-licensed. Live calls need an AI_GATEWAY_API_KEY for Vercel AI Gateway, not an OpenAI key, and the evaluation dataset is synthetic rather than production tickets.

More like this

eve
5.3kGitHub stars
A filesystem-first framework for durable AI agents whose auto model router defaults to Jev through Vercel AI Gateway and whose evaluate helper asks typed Choice, Score, and Boolean questions inside tools.
Repos & SDKs#community#typescript#agents
Communityeve
Simple Jev Project
475GitHub stars
A local server and Python package that runs open models with Hugging Face Transformers or PyTorch and returns Choice, Score, and Noul answers read from next-token logits instead of generated JSON.
Repos & SDKs#community#python#open-models
Communitysimple-jev
tax-doc-classifier
376GitHub stars
Text-only classifier for 261 federal tax forms that sends each PDF page's text to Jev, which returns a probability over forms and page kinds behind a confidence gate; no model is trained.
Repos & SDKs#community#typescript#classification
Communitytax-doc-classifier
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter

700 leads scored for $0.09

Beating Gemini Flash Lite on an eval

Browser Use Ultrafast, powered by Jev