New this week
548 added in 7 days · scroll for earlier daysTuesday, Oct 1327 new
fast-compact/fc for Claude Code: TypeSafe Jev picks which old tool outputs are still needed and keeps them whole, other outputs are cut to head/tail with every…Context & memory
AgentNetwork-jevEvent-driven multi-agent network where TypeSafe Jev observes live network state and assigns pending work to idle general-purpose agents each time one…Routing & model choice
jevkit (bragamat)Unofficial jev CLI (Homebrew, Scoop, install script) that puts TypeSafe Jev in a coding agent's toolbox: find/check to read less, decide/yesno/score…Coding & code review
JevTraceMCP server that cuts coding-agent token usage by retrieving only the snippets TypeSafe Jev judges relevant.Coding & code review
modelrudderFree local community preview that adds model routing to the native Codex terminal: your own TypeSafe Jev key classifies each request so the strongest…Routing & model choice
snapifRust crate and CLI that scores one agent tool call against a shipped policy and returns Auto, Review or Escalate, using TypeSafe Jev…Safety & guardrails
btx-skill-jev-judgeClaude Code plugin that hands repeated judgments to TypeSafe Jev from a tested script (redaction, rate limits).SDKs & integrations
jev-healthcare-labOpen experiment comparing TypeSafe Jev vs DeepSeek on 96 healthcare tasks across 12 scenarios (quality, latency, cost) with per-task data and…Benchmarks & research+ 19 more from Oct 13Monday, Oct 1271 new
jev-remix-cutterIndependent Agent Skill and Python CLI for local video remixing: shot awareness, beat/narration slots, TypeSafe Jev judgments, constrained assembly,…Creative & generative UI
jevdohsom (Harness for System One Models, repository jevdo) lets Jev operate a bash shell by walking a strict-allowlist decision tree of commands,…Agents & browsers
tern-chirpTiny robot voice for the Tern terminal: when a coding agent finishes or waits for you, Jev reads the end of its last message and answers six typed…Coding & code review
jevbench (Leanmcp)Open framework and dataset for benchmarking typed decision models (Jev 1.13, Liquid D1, djev, Laya, Clef, pplx-decider and others) across science,…Benchmarks & research
local-jev (ronitgupta138)An offline drop-in for the Jev API, as one Rust binary.SDKs & integrations
reasoning-routerPer-step reasoning effort for coding agents picked by a classifier (TypeSafe Jev by default in examples) without breaking the prompt cache; ships an…Coding & code review
Signal & NoiseA Chrome extension that hides the posts you do not want on your X timeline.Marketing, sales & social
DeciLabelA GitHub Action that labels issues and pull requests with a decision model.Coding & code review+ 63 more from Oct 12Sunday, Oct 1165 new
gallantA customizable linter that asks a decision model your fuzzy rules.Coding & code review
jev-harness (apixly-ai)Agent-loop runtime where Jev chooses the next tool and arguments while code executes, refreshes state and checks completion.SDKs & integrations
privatemode-decisions-benchmarkEdgeless Systems' benchmark comparing its Privatemode Decisions library (GLM-5.3-Flash in an attested enclave) with TypeSafe Jev and local Laya on…Benchmarks & research
openjev-mcpMCP wrapper for the public OpenJEV API—typed judgments, not prose.SDKs & integrations
aaazzam/jevA Python decorator that turns a Pydantic model into Jev questions: bool becomes a Noul, a Literal becomes a Choice, and a bounded int becomes a…SDKs & integrations
jev-docs-benchmarksStudy documentation and benchmark for various Jev-like products (commercial and open source).Benchmarks & research
better-call-jevA skill for integrating Jev model calls to any Claude Code session.SDKs & integrations
jev-shorts-editorA Jev-based shorts editor.Creative & generative UI+ 57 more from Oct 11Saturday, Oct 10196 new
JarvisCorePython multi-agent runtime (peer-to-peer mesh, durable state, integration atoms) with a typesafe extra that injects a shared Jev client as…SDKs & integrations
jev-opusClaude Opus 5.5 sessions where TypeSafe Jev re-picks reasoning effort every step via per-message effort statements so the Anthropic prompt cache can…Coding & code review
jevcompatTestable spec and conformance suite for Jev-compatible TypeSafe System One API servers—normalising proxy, reference mock, and GitHub Action.SDKs & integrations
Inbox ZeroOpen-source AI email assistant (Next.js, Postgres, 12k+ stars) with a decision-model layer that can run on openrouter:typesafe/jev-1.13: Jev-backed…Support & inbox
GoEventBusHigh-performance Go event bus with deterministic rules, a decision cache, and an optional JevSelector that asks Jev (via OpenRouter's Decisions API)…SDKs & integrationsgrev"Thinking coreutils": Unix filters (grev, isv, tagv, rank, sortv, pickv) that ask TypeSafe Jev typed questions, so output is always your input with…Data & extractionjev-ui-testJev-driven UI test framework: natural-language cases, pytest + Allure; TypeSafe Jev scores candidate elements instead of generating next-step prose…Agents & browsers
bekko-system-oneSmall System One decision models (17M–400M) for Yes/No, Choice, and Score (independent open weights).Benchmarks & research+ 188 more from Oct 10Friday, Oct 936 new
omarchy-laserAI focus mode for Omarchy / Hyprland on Linux: you declare a task, and Laser judges each screen against it with TypeSafe Jev (about half a second per…Everyday apps
system_one_clientElixir client for System One decision models (TypeSafe Jev, Cloudflare Clef, OpenRouter decisions, self-hosted /v1/systemone servers) that returns…SDKs & integrations
pi-subagent-jevpi package that gates subagent dispatches through a Jev System One decision model.Routing & model choice
cookbookCurriculum of Jupyter notebook recipes for building with Jev one bounded decision at a time — state in, typed choice / noul / score questions out —…Guides & docs
jevotronCLI for field-level anomaly detection in tabular, structured and text files, SQLite and DuckDB, powered by Jev, that exports a focused review queue…Data & extraction
CloakBrowser-AgentStealth browser agent where TypeSafe Jev decides each step (~0.3 s) and CloakBrowser executes human-like actions (MCP, CLI, Python API)Agents & browsers
jev-maxJev browser agent aimed at pages ordinary Jev agents miss: a piercing snapshot walks open shadow roots and same-origin iframes into one indexed…Agents & browsers
jev-mail (KirtanUgreja)Open-source Chrome/Brave extension that classifies Gmail with TypeSafe Jev — category, priority, important, needs-reply and junk as separate narrow…Support & inbox+ 28 more from Oct 9Thursday, Oct 865 new
gutsyA 0.8B local decision model on an ordinary CPU.Benchmarks & research
NucleiSniperSecurity-testing pipeline that fingerprints each authorised target and has TypeSafe Jev score every Nuclei template's relevance (0–4) in batches,…Safety & guardrails
social-risk-qwen-jevConcluded research project (Chinese, with English README) on multimodal risk moderation for Chinese social posts (LT-EDI Chinese misogyny memes):…Benchmarks & research
filamentLaravel Filament plugin that turns a sentence such as "The customer is angry." into a zero-shot table filter: TypeSafe Jev scores each row's…SDKs & integrations
ComfyUI-SystemOneA ComfyUI node pack that branches a workflow on a plain-English question.SDKs & integrations
ldraw-novaGive an agent a model idea and get a LEGO model in LDraw.Search & RAG
jevspressoAn espresso bar where a state machine sets the options and Jev picks one.Games & real time
jev-safety-gatewayGo reverse-proxy in front of LLM backends: extracts user input per request, asks TypeSafe Jev, blocks harmful traffic, passes the rest through.Safety & guardrails+ 57 more from Oct 8Wednesday, Oct 788 new
RSI-JevDecision models trained by a self-improving loop of AI agents.Benchmarks & research
jev4pgNatural-language-to-SQL and semantic operators for PostgreSQL: TypeSafe Jev answers typed questions per record while PostgreSQL handles joins and…Data & extraction
jev-risk-check-providerx402 risk-check provider: TypeSafe Jev typed decisions plus ES256-signed attestations facilitators can verify for agent paymentsSafety & guardrails
solo_jevSOLO (System One Layout Optimizer) runs a natural-language decision over every record of a table and reorders rows and fields so a prefix-caching…Data & extraction
jevlineIncident-timeline proof of concept for security analysts: start from one confirmed-malicious process and Jev scores, process by process, which other…Safety & guardrails
jev-blindspotClaude Code / Codex CLI side panel: TypeSafe Jev gates whether a prompt is worth a second look, then optional headless analysis lists blind spots…Coding & code review
jev-lint (ckorhonen)Fuzzy linter for coding agents—flags team best-practice violations while the agent is still writing, not at review.Coding & code review
browser-layaRuns the open Laya System One decision model entirely in a browser tab (ONNX on WebGPU or WASM): an npm library @wexare/laya-web and a hosted…SDKs & integrations+ 80 more from Oct 7Tuesday, Oct 659 new
jevlintA linter that checks code against plain-language rules.Coding & code review
omo-jev-pluginJev-powered decision support for OmO and senpi agents (advise/act modes).SDKs & integrations
ReJevReproducible MiniCPM5-2B post-training for Jev-style single-letter Choice decisions, with sealed holdout evaluation.Benchmarks & research
ollajevPull a System One model from Hugging Face and serve it locally.SDKs & integrations
jevernetesLive Kubernetes log analysis in a terminal or localhost dashboard: surface events worth investigating, inspect surrounding context, and copy…Coding & code review
spending-effort-with-jevJev-powered /effort advisor for Claude Code: tells you when to switch effort, per prompt.Coding & code review
jev-agent-toolsJev transport/provider layer with fail-closed validation; shared by jkudish/jev-browser and jkudish/jev-mcpSDKs & integrations
jev-codex-pluginOpen-source Codex plugin for TypeSafe Jev decision consultation, failure diagnosis, and evidence-based completion review.SDKs & integrations+ 51 more from Oct 6Monday, Oct 5173 new
Bud-Decision-EngineAn open-source LM Studio for decision models.Benchmarks & research
jev-permission-gateA Jev classifier for Claude Code auto mode, built on native mods.Safety & guardrails
dsh-jev-pluginNative DeepSeek Harness plugin that uses TypeSafe Jev as a System One layer for selection, supervision, corrections, and approvals.Routing & model choice
WaterSheepAn open, Apache-2.0 decision model with a local server that accepts Jev's /v1/systemone requests, for people who want Jev-style typed answers without…Benchmarks & research
dsh-jev-interceptorDeepSeek Harness plugin: TypeSafe Jev risk-classifies tool calls (fail-closed / shadow→enforce) and can score session-reference messages instead of…Safety & guardrails
IntentSQLLocal natural-language SQLite playground: inspectable semantic decisions, typed plans, deterministic SQL, and guarded writes via TypeSafe Jev /…Data & extraction
jev-research-pipelinePilot daily research monitor: deterministic Python harvests papers/repos, TypeSafe Jev screens each (source, question) pair, and a writing model…Documents & research
zh-decision-benchChinese-language calibration benchmark for Jev-class System One decision models (dataset CC BY 4.0; code Apache-2.0), including Jev and NeoHorse armsBenchmarks & research+ 165 more from Oct 5Sunday, Oct 414 new
azir-dispatchPython tool for coordinating coding agents in herdr: Jev (via OpenRouter) picks the agent, model, and reasoning effort for each task from your…Routing & model choice
jev-mcp-router (ini8labs)MCP gateway where TypeSafe Jev answers yes/no per server and tool, so the agent LLM only sees the tools a request needs.Routing & model choice
guardrails-mdBerget AI plugin for opencode, pi and Claude Code (plus a git pre-commit hook) that scores every bash command with a System One decision model…Safety & guardrails
JevLint-LEVS Code/Open VSX extension, CLI and MCP server that lint the questions you send to Jev (and OpenAI Decisions) offline.Coding & code review
thinkdialClaude Code mod: TypeSafe Jev sets per-task reasoning effort for the main loop, subagents, and Codex delegations (effort-only by default).Coding & code review
A group chat bot with decision room routingJev, an LLM judge or a roundtable decides which bot answers.Routing & model choiceAn X filter on Jev and ClefHides politics, soccer and crypto posts in under 100 ms.Marketing, sales & socialAskHIGJev picks which Apple HIG guides go into the agent's context.Context & memory+ 6 more from Oct 4Saturday, Oct 3238 new
WorkflowEvalsOfficial TypeSafe reproducibility harness for evals.typesafe.ai workflow benchmarks (invoice, customer service, agent traces, security incidents).Benchmarks & research
typesafe-client (haileyok)Unofficial Go and Rust clients for TypeSafe's System One API (Jev).SDKs & integrations
ex_typesafe_aiUnofficial Elixir client for the TypeSafe AI API — typed structs, Req-based HTTP with retries, and ergonomic noul/choice/score questionsSDKs & integrations
jev-ai-use-casesHands-on LangChain notebook of TypeSafe Jev patterns: support triage, model routing, reply guardrails, tool selection, and finance-inbox fraud…Support & inbox
jev-qa-demosTypeScript demos teaching QA/SDET engineers TypeSafe Jev via Vercel AI Gateway (triage, guardrail, local Ollama).Guides & docs
jevcastNative macOS launcher and window manager (Option–Space): open apps, find files, calculate, move windows, and reuse clipboard text.Everyday apps
omarchy-mailTerminal Gmail client for Omarchy; TypeSafe Jev files inbox into labels.Support & inbox
taurus-jev-sdk-goUnofficial stdlib-only Go client for TypeSafe System One / Jev: validated responses, masked credentials, redirect-safe bearer tokens, bounded retries.SDKs & integrations+ 230 more from Oct 3Friday, Oct 2186 new
OneJevMultimodal System One decision model for screens, photos, video, and text in one forward pass.Agents & browsers
jev-browser-bridgeBridge any CDP-speaking browser—cloud, local, or self-hosted, including no-render engines—into Jev browser automation, with verified runs across many…Agents & browsers
Jev by ExampleTen runnable JavaScript lessons on agent decisions between steps—memory conflicts, evidence gaps, tool-result completion, retries, context budget,…Context & memory
metisReusable GitHub Action and Python CLI/library that triage newly opened issues with TypeSafe Jev: category labels, missing-detail prompts, and…Coding & code review
DecisionKitKeep a .NET application's decision model independent of the decision provider: the domain package knows nothing about Jev, and the Jev protocol lives…SDKs & integrations
TetraJevJev-class decisions on bounded decision problems from two frozen open-weight readers — four readings per item, fit-free fusion, agreement routing,…Benchmarks & research
1 Million EmojisShared 1,000×1,000 emoji canvas where humans paint and TypeSafe Jev paints alongside them—choosing emoji and placement from the stroke’s local…Creative & generative UIDecision Index (apolinario)Reproduce the Decision Index benchmark for typed decision engines (choice/noul) locally or as one Hugging Face Job.Benchmarks & research+ 178 more from Oct 2Thursday, Oct 1114 new
muA coding agent where a small judge makes the routine calls.Coding & code review
vllm-jevNative vLLM serving for Jev-style decision models.SDKs & integrations
Awesome TypeSafeAnother collection of tools and examples.Guides & docs
Astra-AresJev sets the reasoning effort for GPT-6 during Codex tasks.Coding & code review
AbideEnforce AGENTS.md/CLAUDE.md rules on every agent edit/turn with TypeSafe Jev (or Vercel AI Gateway) per-rule probabilities on diffs.SDKs & integrations
onesieUnix-pipeable System One CLI for TypeSafe Jev (also OpenRouter/Berget): pipe text, ask a typed question, script the answerSDKs & integrations
XERJElasticsearch-compatible local search engine for AI agents (single Rust binary, MCP) with an opt-in rerank stage that sends top hits to TypeSafe Jev…Search & RAG
CLM (Contrastive Language Models)Independent open System One model (CLM-8B: Qwen3-8B embeddings plus a small contrastive state/action head) served behind a TypeSafe-compatible POST…Benchmarks & research+ 106 more from Oct 1Wednesday, Sep 3064 new
jev-code-reviewerJev ranks each change P0 to P2 and shows you only the P0s.Coding & code review
Does an open-weight decision model beat a hosted one?ASTGL compares local Laya with hosted Jev on typed decisions.Benchmarks & research
Jev Demo with CursorPatrick Desjardins wires Jev into Cursor for deterministic decisions from the public docs, with blog posts on hundreds of text rules under two…SDKs & integrations
jev-doc-searchFind answering pages in long PDFs with TypeSafe Jev Choice over a PageIndex tree (no vector DB).Search & RAG
jev-llm-guardContextual OWASP LLM Top 10 guardrail powered by TypeSafe Jev, with a Turkish interactive demo.Safety & guardrails
evidence-refereeClaude Code plugin that checks "done" claims and small judgment calls with TypeSafe Jev and keeps receipts (distinct from claude-referee).Coding & code review
Jev Harness LabEvaluation scripts, MCP tools, and a skill router built to measure where jev-1.13.0 fits in agent harnesses, with raw results under eval/.Benchmarks & research
langgraph-jevLangGraph/LangChain integration for TypeSafe Jev decision API (distinct from blacksinisterx/jev-langgraph).SDKs & integrations+ 56 more from Sep 30Tuesday, Sep 2929 new
Strands DeciderRun a small fast System One–style decision model for agentic option/score/yes-no workflows (independent of hosted Jev).Benchmarks & research
StartLux-DecisionIndependent open typed decision models (0.8B to 35B-A3B, text and images) served on the TypeSafe /v1/systemone request format, with inference code,…Benchmarks & research
OpenJev (ejhshen)OpenJev-4B open reproduction of Jev-style open-vocabulary probabilistic decisions (not TypeSafe-hosted; distinct from lookski/openjev).Benchmarks & research
Deep RecallAnswer-aware recall over a folder of Markdown notes (Claude Code plugin + Python CLI/MCP) whose pluggable reranker can be TypeSafe Jev, scoring each…Search & RAG
Fly x JevBrowser demo: MaleCNS fruit-fly connectome robot where TypeSafe Jev picks which descending neuron fires next.Agents & browsers
fr (Arindam200)Ask a codebase question and get relevant files via live parallel TypeSafe Jev relevance.Coding & code review
go-decideGo CLI that puts a choice or ordered rubric to a System One model — TypeSafe Jev by default, Cloudflare Clef opt-in — and prints a JSON outcome whose…SDKs & integrations
jev-cc-codex-routerPer-turn Codex model-routing proxy: TypeSafe Jev picks tier, rewrites the model, retries flaky upstream errors (distinct from…Routing & model choice+ 21 more from Sep 29Monday, Sep 2888 new
jevgrep (dzhng)Find code by asking what it does—Jev judges relevance across folders, files, and declarations.Coding & code review
jevosDecisions on a laptop CPU in 28 to 130 ms, behind Jev's API.Benchmarks & research
DecisSelf-hosted System One–compatible /v1/systemone server with open Laya/kev Docker images (independent of hosted TypeSafe Jev).SDKs & integrations
GatekeeperYAML rulebooks plus TypeSafe Jev Choice route Claude Code prompts/skills to the right handler (allow/route/suggest/confirm/escalate/block) before the…Routing & model choice
mysql-ailike (AILIKE)Native MySQL plugin that adds natural-language row filters and joins (AILIKE / ailike(...)) powered by TypeSafe Jev—MySQL’s counterpart niche to…Search & RAG
@receptron/layaA Node and TypeScript package that runs Convai's Laya checkpoint through ONNX Runtime, with the same system_one shape as the Python reference.SDKs & integrations
Agent StackLocal multi-agent software team stack (OpenRig + Claude Code/Codex) where TypeSafe Jev makes small typed merge/assignment decisions.Coding & code review
DuoMindOpenAI-compatible dual-system server: a small local LLM generates while TypeSafe Jev handles System One decisions.Coding & code review+ 80 more from Sep 28Sunday, Sep 2753 new
Jev-OmniA decision classifier for text, images, audio and video.Benchmarks & researchJev-Style 0.8B Decision v3Jev-style decisions on a laptop, 0.53 GB in 4-bit.Benchmarks & researchJulia 1A 144.3M-parameter decision model that edges Jev on typed decisions.Benchmarks & research
Ten Levels of JevTen levels of Jev—from one smart if statement to a coding agent that reaches for Jev on its own.Coding & code review
deepseek-harness-jev (luobosibing2)Native DeepSeek Harness plugin integrating TypeSafe Jev as a System One decision layer.SDKs & integrations
OpenDeciderOpen System One decision models (typed choice/score/yes-no) with calibrated probabilities; optional Jev-compatible /v1/systemone server—independent…Benchmarks & research
jev-router (FrancoisChastel)Route each coding-agent turn to the cheapest model that can finish it—Switchyard-style signals with TypeSafe Jev as judge.Routing & model choice
genigrepAsk a codebase question and get only answering source; TypeSafe Jev ranks candidates for coding agents.Search & RAG+ 45 more from Sep 27Saturday, Sep 2654 new
laya-phpPHP/Laravel SDK for local Laya typed Choice/Score/Noul decisions (Jev-compatible /v1/systemone alternative; self-hosted).SDKs & integrations
Mobile Agent (KYRIE66nb)Open-source on-device Android AI agent (Chinese/English) that sees and taps the screen, with an optional dedicated decision backend — TypeSafe Jev or…Agents & browsers
jev-decision-kit (kdcadmin)Local skill/plugin cabinet: an on-device Jev head selects which skills to preface before the chat model speaks.Routing & model choice
Codex-JevVS Code Codex plugin that shortens noisy tool results with Jev-gated evidence selection before Codex reads themContext & memory
graphify-jevCodebase knowledge graph with Tree-sitter topology and Jev semantic navigation.Search & RAG
jev-tool-searchBenchmark and experimental engine comparing BM25, embeddings, rerankers, and TypeSafe Jev for selecting among 525 real MCP tools.Search & RAG
android-jev (FZ2000)MCP server and skill that let an agent drive an Android phone naturally over adb with Jev action choice.Agents & browsers
here-we-go-jevLocal playground and test bench for Jev System One with mock and LLM baseline backends.Benchmarks & research+ 46 more from Sep 26Friday, Sep 2567 new
tev1 (Together)Open-weight Jev-inspired decision model (Qwen3.5-4B fine-tune) with training recipe and published results on Together.Benchmarks & research
Warren DufferIntraday Nifty-50 trading bot where TypeSafe Jev ranks names and code sizes/stops live broker orders (experimental; real-money risk).Trading & finance
Jev InboxA Chrome extension that finds and labels your important mail.Support & inbox
50 financial jobs, one modelThe Fintech Builder runs Jev on fifty financial jobs and shows where it works and where it does not.Benchmarks & research
Is Jev actually good at computer use?Steve from Builder.io tests Jev on computer use.Agents & browsers
Is Jev really better, faster and cheaper?Edward Donner puts Jev to the test against Luna.Benchmarks & research
JEV explained in 17 minutes with codecodebasics explains Jev with runnable code.Guides & docs
Jev explained with Python examplesZazenCodes works through Jev hands on in Python, from a first call to typed decisions.Guides & docs+ 59 more from Sep 25Thursday, Sep 24208 new
ValenTrain a Jev-like multimodal model yourself.Benchmarks & research
ollayaOllama for decision models: pull one by name and serve it locally.Benchmarks & research
wellposedZero-dependency linter for TypeSafe Jev requests: catches broken state paths, missing Choice escape hatches, bundled judgments, and other structural…Coding & code review
shapeshiftOne text box that morphs into the right UI (event, checklist, timer, split, convert, …) as you type: TypeSafe Jev classifies intent; deterministic…Everyday apps
Milvus ModelUse a Python reranker interface to score candidate documents with Jev and return their original indices in score order.Search & RAG
jev-guard (klauswg)Real-time risk triage gateway for exchange deposits/withdrawals: TypeSafe Jev answers risk/pattern/freeze questions; Java code owns hard rules,…Safety & guardrails
goutoujunshi-jev-chatWeChat companion (macOS source preview + Windows preview ZIP): screen-read the chat, analyze with optional TypeSafe Jev strategy judgment, and draft…Everyday apps
jev-judge-mcpTyped judgment MCP tools (verify/screen/find/classify/rerank/decide/…) over TypeSafe Jev — model judges, policy decides auto/review/escalate…SDKs & integrations+ 200 more from Sep 24Wednesday, Sep 23286 new
jev-browser (openqa-cn)Jev chooses the control, Playwright acts.Agents & browsers
sys1A System One compatible API for open decision models, in Rust.SDKs & integrations
jev-suiteFour decision-quality tools on Jev, with code keeping the final say.Everyday apps
JevTownA Jev-based AI town simulation.Games & real time
laya-jev-GraphRAGGraphRAG with swappable System One models.Search & RAG
stuntdA local proxy that answers typed LLM decisions with a Laya head.SDKs & integrations
JevEmbedTurn embeddings into choices, scores and judgments.Search & RAG
go-jevA Go SDK and CLI for typed Jev decisions.SDKs & integrations+ 278 more from Sep 23Tuesday, Sep 22272 new
jev-chat-jarvisA reply co-pilot for phone chat apps: it reads the screen and drafts, you send.Everyday apps
AnyJevTurn any LLM into a Jev-style decision model, with no training.Benchmarks & research
discernUncertainty-aware pattern matching and control flow for Effect.SDKs & integrations
prompt2jevTurn a prompt, or the code that runs one, into a Jev decision.Coding & code review
json-renderVercel Labs’ generative UI framework, with a Jev composer behind a flag.Creative & generative UI
agent-desktopDesktop control from the accessibility tree, with Jev picking the operation.Agents & browsers
Jev-cuA computer-use repository built around Jev.Agents & browsers
Jev Chat WindowsA WeChat reply helper for Windows: screenshot, local OCR, three drafts.Everyday apps+ 264 more from Sep 22Monday, Sep 21260 new
jev-test-filterScore every test against a git diff, then emit the runner arguments.Coding & code review
jevalWorks out what a Jev confidence score is actually worth.Benchmarks & research
pi-jev-router (philippdubach)A Pareto-optimal OpenRouter router for Pi, decided by Jev.Routing & model choice
jev-feelsSemantic decisions as ordinary Ruby: feels?, decide, score.SDKs & integrations
taste-lintCatches AI slop in a diff before it ships.Coding & code review
dsh-jev-pruneContext compaction for DeepSeek Harness, judged by Jev.Context & memory
TipTourA pointer companion for the Mac, with Jev driving the cursor.Agents & browsers
jev-docs-zhChinese System One/Jev cookbook: notebooks, 18 recipes, docs translation (CC BY-NC-SA 4.0 — free educational / non-commercial; not OSI open source).Guides & docs+ 252 more from Sep 21Sunday, Sep 20206 new
NanoJevA 0.6B replica: parallel decisions in one forward pass, no decoding.Benchmarks & research
hermes-jev-skillsModel routing, memory, compaction and skill selection for Hermes agents.Routing & model choice
CannyA warden that will not let a coding agent finish on a claim.Coding & code review
jev-cli (shaharia-lab)Ask Jev from a shell, and get an exit code back.SDKs & integrations
agent-chaperoneScreen an agent's tool calls with Jev before they run.Safety & guardrails
jev-studioOne-stop kit for experimenting with TypeSafe Jev: a jev CLI for verify/screen/classify/extract/match/route flows plus an MCP server that exposes…SDKs & integrations
jev-oas-sentinelOpenAPI compatibility checks, structural and semantic.Coding & code review
jev-skillOscar Wu’s collection of Jev use cases, workflows and agent skills, gathered in one repository.Guides & docs+ 198 more from Sep 20Saturday, Sep 19186 new
jev-align (Sutro)Turns human labels into calibrated Jev classifiers with GEPA.Benchmarks & research
jev-prunerTrims long Bash output with Jev before Claude reads it.Context & memory
jev-commitpre-commit hook that makes one Jev call per commit to judge whether the commit message matches the staged diff, and flags filler messages, debug…Coding & code review
jev_antispam_botA Telegram bot that deletes only the spam Jev is sure about.Safety & guardrails
jevkitA Rust CLI for Jev, with a linter that checks questions before you pay.SDKs & integrations
kevA tiny Jev-like model on Qwen2.5-0.5B that trains and runs on a MacBook.Benchmarks & research
vonA sub-15 ms local drop-in alternative to Jev.Benchmarks & research
SupercovCode quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.Coding & code review+ 178 more from Sep 19Friday, Sep 18221 new
Fast Jev CompactionDecide which tool interactions to retain.Context & memory
jev-searchWeb search where a decision model picks the sources and ranks them.Search & RAG
JevRouterOne typed Choice question picks the model, tool or subagent.Routing & model choice
snifftestA prose linter for AI writing tells: regex rules plus Jev for judgment.Documents & research
is-maliciousA codebase scanner that helps you not run malicious code.Safety & guardrails
pi-heedChecks every side-effecting tool call against what you asked for.Safety & guardrails
simple-jevAn open-source library that turns any Hugging Face model into a Jev-style endpoint.SDKs & integrations
awesome-jev-projects思维怪怪’s source-backed radar of the open-source ecosystem, in English, Chinese, Japanese and Korean.Guides & docs+ 213 more from Sep 18Thursday, Sep 17457 new
JevlikeExplore training a small option-scoring model.Benchmarks & research
Jev ReviewAdd decision checks to a code-review workflow.Coding & code review
jev-router (gargpratyush)Routes each Claude Code task to the cheapest model that can do it.Routing & model choice
mobile-jevA mobile agent on a real Android phone, with Jev making each decision.Agents & browsers
jev-mcp (jkudish)An MCP server with claim checks, screening and ranking built on Jev.SDKs & integrations
Jev DroneExplore control decisions for a quadrotor.Creative & generative UI
Neo4jevChoose the next relationship in a graph traversal.Data & extraction
BlinkExplore a repository with Jev-backed search.Coding & code review+ 449 more from Sep 17Wednesday, Sep 1629 new
Jev UltrafastChoose browser actions from the current page.Agents & browsers
Jev TraderInspect an experimental trading decision loop.Everyday apps
Computer UseTranslate screen text into mouse actions.Agents & browsers
DuckDB classifierClassify records in tables and local data files.Data & extraction
Computer use built on JevAaron Levin: 155x cheaper than Opus 5, about 20x faster, and it generalizes across operating systems.Agents & browsers
Stagehand + Jev browser useBrowser tasks for about a tenth of a cent each.Agents & browsers
Vercel AI GatewayAccess Jev through Vercel’s model gateway.SDKs & integrationsA hype-free explanation of JevNathan Flurry: Jev does not replace GPT or Claude.Guides & docs+ 21 more from Sep 16Tuesday, Sep 1522 new
TypeSafe launchRead the company’s introduction to Jev.Guides & docs
System One adapterCompare the interface with other providers.SDKs & integrations
QuickstartMake your first typed decision request.Guides & docs
JavaScript SDKCall TypeSafe from JavaScript or TypeScript.SDKs & integrations
Python SDKUse synchronous or asynchronous Python requests.SDKs & integrations
Patent classificationNavigate a taxonomy using several small decisions.Data & extraction
Smart home demoSee parallel questions drive household actions.SDKs & integrations
PrimitivesUnderstand yes/no, choice, and score outputs.Guides & docs+ 14 more from Sep 15Latest projects
4,153 projectsTuesday, Oct 13
Benchmarks & researchMicaA 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.GitHub · ★ 37 · akivet
Games & real timeMulti-UAV-JEVCamera-observed UAV pursuit in MuJoCo with Jev decisions, RGB/depth HUD, replay and episode collection.GitHub · ★ 16 · YongLDContext & memoryfast-compact/fc for Claude Code: TypeSafe Jev picks which old tool outputs are still needed and keeps them whole, other outputs are cut to head/tail with every…GitHub · ★ 6 · NodarDavituri
SDKs & integrationsjev-phoneJev 多模态手机自动化：面向 Android、iOS、HarmonyOS 的独立 Python 点击 SDK，毫秒级本地处理。 Jev-powered multimodal mobile automation: a standalone Python tap SDK for Android,…GitHub · ★ 6 · dongxinsuperman
Benchmarks & researchawesome-jev-papers📄 Research papers on Jev, TypeSafe's System One model, and the open models built in its shape.GitHub · ★ 5 · OmniJev
Search & RAGjev-keyboardJev-powered candidate reranking for Rime on macOS, with Windows support planned.GitHub · ★ 4 · Ideny42Routing & model choiceAgentNetwork-jevEvent-driven multi-agent network where TypeSafe Jev observes live network state and assigns pending work to idle general-purpose agents each time one…GitHub · ★ 3 · Kelly-LeeeeCoding & code reviewjevkit (bragamat)Unofficial jev CLI (Homebrew, Scoop, install script) that puts TypeSafe Jev in a coding agent's toolbox: find/check to read less, decide/yesno/score…GitHub · ★ 3 · bragamatCoding & code reviewJevTraceMCP server that cuts coding-agent token usage by retrieving only the snippets TypeSafe Jev judges relevant.GitHub · ★ 3 · 123wwwa
Games & real timeJev-like_snake_playground本地贪吃蛇。每步由代码给出合法走法的事实，Qwen 在封闭选项里做一次前向并选出下一步。判断来自 RJMSWD/QwenJev。GitHub · ★ 3 · mtxcjnb
Benchmarks & researchjev-typesafe-real-financial-use-casesFifty real-world financial use cases for TypeSafe's Jev model: typed, structured LLM answers over ledgers, fraud, portfolios, trades and filings,…GitHub · ★ 3 · IslamBaraka90Routing & model choicemodelrudderFree local community preview that adds model routing to the native Codex terminal: your own TypeSafe Jev key classifies each request so the strongest…GitHub · ★ 2 · cybrkingSafety & guardrailssnapifRust crate and CLI that scores one agent tool call against a shipped policy and returns Auto, Review or Escalate, using TypeSafe Jev…GitHub · ★ 2 · snapif
Agents & browsersdocent_chrome_pluginA pluign for TypeSafe AI's Jev.GitHub · ★ 2 · yepher
Routing & model choicejev-orcMy JEV Orchestrator to supply my needs.GitHub · ★ 2 · hiyoku
Safety & guardrailsjev-sec.github.ioJev IDS website: one flow.GitHub · ★ 2 · jev-secSDKs & integrationsbtx-skill-jev-judgeClaude Code plugin that hands repeated judgments to TypeSafe Jev from a tested script (redaction, rate limits).GitHub · ★ 1 · bitranox
Routing & model choicejev-gateway (dragpk247)Sub-300ms intelligent LLM router with Zero-Leak privacy sandbox, Obsidian RAG, and multi-tier local GPU & cloud offloading.GitHub · ★ 1 · dragpk247Benchmarks & researchjev-healthcare-labOpen experiment comparing TypeSafe Jev vs DeepSeek on 96 healthcare tasks across 12 scenarios (quality, latency, cost) with per-task data and…GitHub · JuneYaooo
Agents & browsers@sideform/browser-agentGoal-driven browser agent library in TypeScript (controller, step policy, browse_task loop) whose step policy uses a System One decision client such…GitHub · dan-rozhkov
Everyday appsAI, SI, or WhateverChrome extension that lets TypeSafe Jev choose AI / SI / alternating / custom webpage terminology per page.GitHub · SjJ1017
Coding & code reviewBaton Agent OrchestratorIdea-to-reviewed-code pipeline on your git repo (jev CLI): TypeSafe Jev picks the agent, model and effort at each step across Claude Code, Codex CLI…GitHub · Gane2506
SDKs & integrationscpa-plugin-typesafeCLIProxyAPI plugin that adds a native TypeSafe/Jev typed API path with OpenAI-compatible chat and private settings.GitHub · EcoRayDev
Agents & browsersLathAgent loops that pay for model calls over a Tempo payment channel with every call recorded on Solana; a separate TypeSafe Jev decision answers…GitHub · lath-agents
Support & inboxreflex (Alertmanager router)Alertmanager webhook receiver that asks TypeSafe Jev one Choice question per alert group to send it to an urgent or informational Discord channel,…GitHub · Starttoaster
Marketing, sales & socialseo-jev-analyzerMeasures how closely each page matches the search intent you set, using TypeSafe Jev with a calibrated noise band.GitHub · matthelam
Agents & browsersvoice-browsermacOS command bar that drives Chromium, Dia, Arc or Chrome from plain English; TypeSafe Jev (or SubQ Snap) picks clicks and targets for fast single…GitHub · ken-code-wqMonday, Oct 12
Creative & generative UIjev-remix-cutterIndependent Agent Skill and Python CLI for local video remixing: shot awareness, beat/narration slots, TypeSafe Jev judgments, constrained assembly,…GitHub · ★ 13 · gnipbaoAgents & browsersjevdohsom (Harness for System One Models, repository jevdo) lets Jev operate a bash shell by walking a strict-allowlist decision tree of commands,…GitHub · ★ 4 · gi-dellav
Documents & researchPaperRadarLocal web app to browse conference papers (ICML, ICLR, CVPR, NeurIPS and more), filter by research tags and export to Zotero; new tagging runs use…GitHub · ★ 4 · eyad-al-shami
Benchmarks & researchtypesafe-jev-ecosystemExplore the TypeSafe Jev ecosystem: open-source integrations, compatible decision models, SDKs, agent tools, and research.GitHub · ★ 4 · VoltAgentCoding & code reviewtern-chirpTiny robot voice for the Tern terminal: when a coding agent finishes or waits for you, Jev reads the end of its last message and answers six typed…GitHub · ★ 3 · Noctivoro
Benchmarks & researchBeelineBenchHow well do decision models plan across a multi-step problem?GitHub · ★ 3 · kyle-pena-nlp
Home, robots & devicesjev-fault-diagnosis-pocFault Diagnosis PoC replays real compressor telemetry through an emulated Modbus device, spots suspicious behaviour with plain code, and asks a…GitHub · ★ 3 · meddle-connectBenchmarks & researchjevbench (Leanmcp)Open framework and dataset for benchmarking typed decision models (Jev 1.13, Liquid D1, djev, Laya, Clef, pplx-decider and others) across science,…GitHub · ★ 2 · LeanmcpSDKs & integrationslocal-jev (ronitgupta138)An offline drop-in for the Jev API, as one Rust binary.GitHub · ★ 2 · ronitgupta138Coding & code reviewreasoning-routerPer-step reasoning effort for coding agents picked by a classifier (TypeSafe Jev by default in examples) without breaking the prompt cache; ships an…GitHub · ★ 2 · robertn702Marketing, sales & socialSignal & NoiseA Chrome extension that hides the posts you do not want on your X timeline.GitHub · ★ 2 · icpmacdo
Safety & guardrailsclaudetiquetteClaude Code plugin that rewrites a hostile prompt into a plain request.GitHub · ★ 2 · zahlekhan
Benchmarks & researchFastJEVOfficial inference code for FastJEV, a training-free approach to compact candidate evaluation in JEV models.GitHub · ★ 2 · JieMaMagic
Coding & code reviewjev-mswMock Jev API decisions with MSW for deterministic tests without real API calls or credits.GitHub · ★ 2 · royalpinto007
Games & real timeminecraft-jev-agentEmbodied Minecraft Java agent: a Typed Decision Plane (Jev / Liquid d1) chooses among grounded transitions, a V4.1.2 kernel owns authority, leases…GitHub · ★ 2 · souta-lab
Data & extractionomp-jevifyOh My Pi skill plugin: rubric-first bulk classification with judge_batch (Jev).GitHub · ★ 2 · ericjutaCoding & code reviewDeciLabelA GitHub Action that labels issues and pull requests with a decision model.GitHub · ★ 1 · EvanProgramming
Benchmarks & researchjev-benchConfigurable classifier workbench for repeatable latency and accuracy experiments on TypeSafe Jev (Banking77 accuracy, OpenRouter comparisons) with a…GitHub · ★ 1 · cocodedk
Search & RAGSmart FindCtrl+F, but for questions.GitHub · ★ 1 · eduardoalba00
SDKs & integrationstypesafe-dotnet-sdk (mehdihadeli)Community-maintained C# SDK for the TypeSafe System One API: send text or JSON state with named Noul, Choice and Score questions and read typed…GitHub · ★ 1 · mehdihadeli
Everyday appsaxo-launcherMinimalist Android launcher (Portuguese docs): text-only home, grayscale screen and delays for distracting apps; quick-capture phrases are classified…GitHub · ★ 1 · axolutionsNo matches. Try “browser”, “rerank” or “Rust”.