Updated

Desk

Repos

GitHub projects this digest has already cited. A week-one roundup lists more catalogs than this page repeats. For the full URL list, see sources.

Local stand-ins

TheoLeeCJ/SemIf

Formerly OpenJev. Reads option logits from Qwen3.5-4B. JevBench 74.6 versus Jev 75.3. Independent; not affiliated with TypeSafe.

SemIf JevBench

githubnext/localjev

Bun server that speaks POST /v1/systemone and prompts a local model on oMLX for JSON probabilities. GitHub Next. Not a logit read.

LocalJev

logan-markewich/jeff

Self-hosted System One API on GLiFormer. 1,600 public items against live Jev.

jeff

bespokelabsai/nimble

9B Qwen LoRA trained to imitate Jev-style answers. 90.12% on 324 synthetic labels.

Nimble

Heman10x-NGU/Verdict-open-jev

151M encoder that runs in a browser tab. Cited next to Nimble, not as its own story.

Nimble

NandhaKishorM/laya

Apache 2.0 ModernBERT-sized encoder, three checkpoints, a Router. JevBench 70.1. Author Banking77 0.425 versus a published Jev 0.870.

Laya JevBench laya-mlx

mizorewww/laya-mlx

Apache 2.0 MLX port of the Laya checkpoints. M3 Max one-question median 13.42 ms (421M) and 7.39 ms (322M). Selected answers matched upstream on 63 of 63 validation questions. Not a new JevBench row.

laya-mlx

jaredpalmer/kev

Apache 2.0 LoRA plus pointer head on Qwen. Serves POST /v1/systemone. Author new-source: Kev-8B 79.6% versus Jev 85.7%. JevBench kev 0.6B 66.7.

Kev JevBench

Davipar/djev-dev

Apache 2.0 local POST /v1/request on DiffusionGemma plus patched vLLM. Hosted API is Maisa's djev.dev. JevBench 74.3.

djev JevBench

Zefan-Cai/Open-Jev

MIT source. Qwen3.5-2B and 9B LoRA plus a decision head, Apache 2.0 adapters. 231 public JevBench tasks: 9B 179/231, Jev 200/231, Astra 231/231. Different project from SemIf.

Open-Jev JevBench

featherless-ai/simple-jev

Apache 2.0 classifier server. Reads next-token logits from a Hugging Face chat model. JevBench Qwen3.8-27B 67.3.

SimpleJev JevBench

NakliTechie/llamacpp-jev

MIT. POST /v1/systemone in front of unmodified llama-server, text and images. Raw label softmax. Fresh 448 image, four questions, 526 ms median on an idle M4 Pro.

llamacpp-jev

Loops

browser-use/jev-ultrafast

Browser Use's indexed action-space agent. Zurich to London Google Flights at 7.1 seconds in the repo notes.

Flights

jkudish/jev-browser

Stagehand-related browser loop. Cited in the computer-use story.

Stagehand

jcpsimmons/jev-macos-loop

Native Mac window controls. Finder batch of nine files in 7.39 seconds through Vercel.

macOS Loop

jaewgwon/jevis

Flutter integration_test package. Rank registered widget actions. Strings come from the test author.

Jevis

maxlibin/jev-rubiks

MIT browser cube. Kociemba solves in code. Jev decides whether the coach speaks. A removed test of 18 turns, forty times, left the distance at 22.

jev-rubiks

idovmamane/dejevu

MIT browser loop. One JSON action to a chat model. Groq flights median 5.63 s against jev-ultrafast's published 7.09 s. The Jev path in the repo is untested.

dejevu

Jinzhengxu/poker-table

GPL-3.0 Hold'em table. Jev reads the opponent in one request. Code picks fold, call, or raise. Spot-bank median about one second on 46 spots.

Poker

standardagents/jevpilot

Three.js driving sim. Jev picks among sampled steering paths.

JevPilot

Routers and filters

yusukebe/hono-jev-router

Hono Worker that asks Jev whether a request looks like spam, an agent, or an angry customer.

Hono

tamaratran/fast-jev-compaction

Score tool-call blocks and drop them instead of summarizing.

Compaction

GhalebDweikat/winnow

Similar filter ahead of Claude Code.

Compaction

SamSaffron/term-llm#1150

GPT Live control plane. Shadow mode on. Fail open to steer.

term-llm

m-mizutani/semgate

Go net/http middleware. Asks Jev about each request. Default sends every header, including Authorization and Cookie.

semgate

KranzL/Jevflake

dbt package plus Terraform. Snowflake SQL functions for noul, choice, and score. Calls TypeSafe's API; row content leaves the warehouse.

Jevflake

BerriAI/litellm

Proxy pass-through at /typesafe/v1/systemone in v1.103.0-rc, plus a typesafe compaction guardrail at relevance_threshold 0.2.

LiteLLM

Nasrallah-AL/jev-cli

npm jevctl, command jev. verify, screen, classify, compact, batch. TypeSafe, OpenRouter, or Cloudflare. compact keep-threshold 0.5.

jevctl

jerryjliu/docjev

Apache 2.0 classify and split for PDF, DOCX, PPTX. LiteParse locally, hosted Jev for the decision. 40/40 classify, 7/8 split versus Luna.

DocJev

khmuhtadin/n8n-nodes-jev-classification

MIT n8n community node. Classify, Score, Check, Ask Questions. One output per category plus Needs Review. Self-hosted; n8n declined to verify it.

n8n

mejiasd3v/pg-jev

MIT PostgreSQL extension. prompt_jev returns jsonb from TypeSafe, Vercel, or Cloudflare. No scored set in the README. One HTTP call per row.

pg-jev

backant-io/jevelry

MIT npm runtime. A JEVEL.md holds the questions and the act / mark / fall_back thresholds. Last live note: three calls in 2.49 seconds on jev-1.13.0.

jevelry

prasanthj/duckdb-jev

Apache 2.0 native C++ DuckDB extension. Batches and streams Jev from SQL. Live Choice: 2,049 rows in 0.887 s. Row text leaves DuckDB.

duckdb-jev

colliber/duckdb-jev

Separate MIT native DuckDB extension. Bind-time ENUM and STRUCT result types. One request per row. Related work on the Prasanth story.

duckdb-jev

kylemclaren/jevsearch

MIT shadcn registry block. Keyword hits first, then Jev re-ranks the top 20. Author bench 83% Hit@1 on TypeSafe docs.

jevsearch

keltokhy/jsort

MIT pairwise ranker, command jsort. Bradley-Terry scale from Jev Noul comparisons. CommonLit r 0.824. Fed script is 95 statements.

jsort

vercel-labs/jev-ai-sdk-form-router

MIT Next.js template. Accepts Jev at confidence 0.95. GPT-5.6 Luna Fast decides the rest from the submission alone.

Form router

syumai/jevyoumean

MIT Go wrapper, command jym. Unknown subcommands become one Jev Choice against help text. Valid commands do not call the API.

jym

vinilana/jev-gateway

MIT local proxy, npm jev-gateway. Jev picks the tool for Codex, Claude Code, OpenCode, or Gemini CLI. Direct mode can skip the language model when every argument is closed.

jev-gateway

spring-ai-community/spring-ai-typesafe

Apache 2.0 Java SDK and Spring AI advisors. Judge, guardrail, document filter, tool index. Blog pins 0.1.0. README quick start still shows 0.1.0-SNAPSHOT.

Spring AI

use-agent-os/agent-os#3316

Opt-in Jev strategy for Pilot Router. Not the default. Chart on 121 labeled turns: Jev accuracy 0.901, local MiniLM 0.355. high_risk at 0.7 floors the turn at c3.

Pilot Router

Measurements and catalogs

Robertzu43/system-one-security-triage

Recorded 100-case security demo. Jev, Terra, Opus, five passes. Dashboard serves 2026-09-19-public-v5.

Security triage

fstandhartinger/jevbench

JevBench harness and frozen tasks. Interactive table at benchmarkheaven.com/jev-models. Not affiliated with TypeSafe.

JevBench

danielgshea/jev-as-a-judge

LangChain weather-agent judge eval. Frozen traces, oracle labels, 100-repeat variance.

Judge

onlyoneaman/jev-eval

Public half of Kumar's 16,000-call write-up: cases, per-item answers, scoring.

Filter

SREGym/SREGym

SREGym-Lite harness. 20/50 without Jev, 24/50 with it, on 10 problems times five attempts.

SREGym-Lite

elvisun/newsjack

News Desk Dealer demo. 384 headlines versus Opus 5.

384 headlines

jarrodwatts/jev-trader

Monad/Kuru buy-or-sell loop. Mock model unless you set a key.

Trader

hellogumbo/awesome-jev

Community directory. Week-one story lists a slice of it. Counts keep moving.

Week one

vinilana/jev-gateway-bench

Chess-engine sessions, routing on and off. 120 runs in the gateway README. Astra and Sol bug-fix output -57%. Opus 5 feature task +83% time.

jev-gateway