Skip to content
JevDirectory.org
CommunityCookbooks & Demos0 starsVerified 2026-09-22

jev-bfs

A terminal Wikipedia link-race tool: Chromium fetches article pages, Jev ranks their outgoing links by expected remaining hops, and Python runs a beam search without a search API or a controller model.

Open github.comkomikat/jev-bfs
Category
Cookbooks & Demos
Published by
Community
Author
komikat
Added
2026-09-22
Tagscommunitypythonclisearchdemo

Highlights

  • Each Jev request receives the target query, link titles, and URLs but not article text, and it scores up to 128 candidates with five requests in flight.
  • The default beam search keeps the five highest-ranked links per level and has no hop or page limit unless --depth and --max-pages are set.
  • The README states plainly that beam selection can remove the shortest route, so runs report observed paths rather than proofs of shortestness.
  • Runs are inspectable: --save writes the path, scores, timing, and API usage, and --json emits machine-readable output with distinct exit codes.
  • Installs with uv and Playwright's Chromium and calls the model alias jev-latest.

Quickstart

bash
uv tool install git+https://github.com/komikat/jev-bfs.git
jev-bfs --install-browser
export JEVON_KEY="YOUR_API_KEY"
jev-bfs "Coffee" "Black hole" --width 5 --depth 6

Watch out

MIT-licensed. Needs Python 3.11+, uv, a Playwright browser install, and a TYPESAFE_API_KEY or JEVON_KEY; every run spends TypeSafe API credits from your account.

More like this

neo4jev
85GitHub stars
A demo application that navigates a Neo4j graph one hop at a time: Jev gets the outgoing relationships as a Choice plus a goal Noul in one system_one call, and beam search follows the probabilities.
Cookbooks & Demos#community#python#neo4j
Communityneo4jev
EmbodiedJev
181GitHub stars
A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.
Cookbooks & Demos#community#python#robotics
Communityembodied-jev
Laya vs Jev
71GitHub stars
A side-by-side T-Rex game where local Laya runs on Apple Silicon through MLX and hosted Jev uses the TypeSafe API, showing choices, latency, survival streaks, and crash replays on one course.
Cookbooks & Demos#community#python#games
Communitylaya-vs-jev
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A million judged questions

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post

Trading bot, one decision per block

Classifying 1,500 real emails

vogel
vogel
Anomaly
@ryanvogel
·

this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 69 replies