REPOSITORIES
Code.
All of it.
Every GitHub repository the index points at — official SDKs, integrations, replicas, benchmarks and demos — with stars, language and last push from GitHub.
187repositories
276kstars combined
15languages
GitHub data refreshed · 185 of 187 fetched · repos.json
| Repository | Entry | Category | Lang | Stars | Pushed | License |
|---|---|---|---|---|---|---|
| vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs | vLLM PR #57250: a Gemma-based Jev-like path | repo | Python | 92k | Apache-2.0 | |
| BerriAI/litellmThe fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] | LiteLLM: Jev-driven context compaction and pass-through | integration | Python | 59k | Other | |
| trycua/cuaScale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation. | jev-use for computer use | integration | HTML | 25k | MIT | |
| pydantic/pydantic-aiHow Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. | Pydantic AI: first-class TypeSafeModel | integration | Python | 20k | MIT | |
| browser-use/jev-ultrafasti. am. speed. | Jev Ultrafast (Browser Use) | repo | Python | 14k | MIT | |
| run-llama/liteparseA fast, helpful, and open-source document parser | DocJev: document classification and splitting with Jev | repo | Rust | 12k | Apache-2.0 | |
| Arize-ai/phoenixAI Observability & Evaluation | OpenInference instrumentation for TypeSafe (Arize) | integration | Python | 12k | Other | |
| tamaratran/fast-jev-compactionClaude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. | Instant context compaction | demo | TypeScript | 5.8k | MIT | |
| NandhaKishorM/laya | Laya: the open decision model that predates Jev | replica | Python | 3.0k | Apache-2.0 | |
| TheoLeeCJ/SemIfSemantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe. | Jev-like model on a home GPU | replica | Python | 2.9k | MIT | |
| TheoLeeCJ/SemIfSemantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe. | Jev-like model on a home GPU | replica | Python | 2.2k | MIT | |
| jaredpalmer/kevtiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own | kev: a tiny Jev-like you can train on a MacBook | replica | Python | 1.9k | Apache-2.0 | |
| jarrodwatts/jev-traderOne AI trade decision every Monad block. Jev on Kuru MON-USDC. | Jev Trader: one decision per Monad block | demo | TypeScript | 1.7k | MIT | |
| lahfir/agent-desktopAgent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions stay safe to retry, instead of guessing from pixels. | Agent Desktop: reliable computer use through OS accessibility trees | repo | Rust | 1.4k | Apache-2.0 | |
| Arize-ai/openinferenceOpenTelemetry Instrumentation for AI Observability | OpenInference instrumentation for TypeSafe (Arize) | integration | Python | 1.2k | Apache-2.0 | |
| TianyuCodings/NanoJevA nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline. | NanoJev | replica | Python | 1.2k | MIT | |
| mizorewww/laya-mlxNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API. | laya-mlx / laya-coreml: Laya on Apple Silicon | replica | Python | 1.1k | Apache-2.0 | |
| vinnylarouge/jevlike | jevlike | replica | Python | 1.0k | MIT | |
| bespokelabsai/nimbleLocal typed decisions, contrastive data curation, and model evaluation. | Bespoke Nimble: open data, open model, open recipe | replica | Python | 948 | — | |
| typesafe-ai/skillsAgent skills for building with TypeSafe's System One API | Official agent skills repository | repo | — | 899 | MIT | |
| reticlehq/reticleAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications. | Reticle: machine-native runtime perception for web and desktop apps | repo | TypeScript | 796 | Other | |
| Anil-matcha/awesome-jev-by-typesafeEvidence-backed use cases, patterns, prompts, and starter code for TypeSafe Jev — a System One model for fast, typed, confidence-aware decisions in software. | Awesome Jev by TypeSafe (unofficial) | directory | Python | 747 | MIT | |
| awlevin/typesafe-computer-useComputer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS. | Computer use on Jev: OCR, classify, click | demo | Python | 709 | MIT | |
| milind-soni/tiptour-macosOpen-Source fast local computer use | TipTour: a local pointer companion for macOS | demo | Swift | 630 | Other | |
| githubnext/localjev | LocalJev by GitHub Next: a Jev-compatible local API | replica | TypeScript | 578 | MIT | |
| Sac-Y/Jev-cu | Jev-cu: the fastest computer use inside Codex | integration | JavaScript | 530 | — | |
| yibie/awesome-jevA curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions. | yibie/awesome-jev | directory | Python | 485 | — | |
| devagrawal09/jev-reviewA staged code-review workflow and local dashboard built with TypeSafe Jev. | jev-review: staged code review with a local panel | repo | TypeScript | 451 | MIT | |
| featherless-ai/simple-jevTurn any open model into a classifier/jev endpoint | simple-jev | replica | Python | 433 | Apache-2.0 | |
| AbdelStark/awesome-typesafe-jevAwesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations. | awesome-typesafe | directory | CSS | 417 | MIT | |
| thruwire/foremanSoftware factory foreman based on TypeSafe's Jev model | Foreman: a supervisor for coding agents | post | Python | 416 | MIT | |
| superagents-lab/jev-searchSearch the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API. | Jev Search | repo | TypeScript | 359 | MIT | |
| kerpopule/hermes-jev-skillsJev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex) | hermes-jev-skills: routing, memory, compaction, GUI clicks for Hermes | integration | Python | 358 | MIT | |
| kyotofin/tax-doc-classifierTax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page. | Got Jev — now what? A real deployment list | roundup | TypeScript | 323 | Apache-2.0 | |
| fhshaik/typesafe-marioA TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state. | Jev plays Super Mario Bros from telemetry | demo | Python | 319 | — | |
| droidrun/mobile-jev | mobile-jev: an Android agent on Jev | repo | JavaScript | 307 | MIT | |
| cobanov/awesome-jevA curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions. | cobanov/awesome-jev | directory | — | 300 | CC0-1.0 | |
| gargpratyush/jev-routerRoute to the cheapest model in claude code for your task using jev-router | jev-router for Claude Code | repo | JavaScript | 295 | MIT | |
| shhivv/third-handcomputer-use assistant w/ decision models | third-hand: computer use with no LLM at all | demo | Swift | 274 | MIT | |
| realZachi/pg-jevAsk your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev. | pg-jev | repo | Shell | 271 | Other | |
| ekzhang/openjev-sglangJev-compatible API endpoint based on open models (prefill-only) | openjev-sglang | replica | Python | 246 | — | |
| langfuse/langfuse-docs🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform. | Langfuse: using Jev for evals | article | MDX | 243 | MIT | |
| sutro-sh/jev-alignBuild calibrated AI classifiers from human feedback using Jev and GEPA. | jev-align: calibrate Jev to your decision criteria with GEPA | integration | Python | 223 | Apache-2.0 | |
| mizorewww/laya-coremlLocal Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks. | laya-mlx / laya-coreml: Laya on Apple Silicon | replica | Python | 219 | Apache-2.0 | |
| rokbenko/quackdOne CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain, Jev for cheaper steps. Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot or any ROS base. Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM. Simulator, .duck safety contracts, MCP, memory between runs, flocks. | quackd: one CLI for all your robots, Jev for the cheap steps | integration | Python | 219 | Apache-2.0 | |
| ielab/llm-rankersDocument Ranking with Large Language Models. | llm-rankers: checking Jev's calibration with TREC judgments | benchmark | Python | 211 | Apache-2.0 | |
| jkudish/jev-mcpFast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools. | jev-mcp | repo | TypeScript | 207 | MIT | |
| rmalde/minecraft-agentAstra planner and JEV controller for Minecraft, with native recording, tested routes, and run verification. | minecraft-agent: Astra planner, Jev controller | demo | JavaScript | 205 | — | |
| AnotiaWang/awesome-jevA curated list of awesome Jev / TypeSafe System One applications, libraries, and resources. | AnotiaWang/awesome-jev | directory | — | 204 | CC0-1.0 | |
| coldteadotai/abideMake your coding agent abide by all your project rules | abide: make your coding agent follow project rules | integration | TypeScript | 192 | MIT | |
| logan-markewich/jeffA self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer. | jeff: a self-hosted Jev API on GLiFormer | replica | Python | 191 | MIT | |
| razorback16/openjevOpen, Jev-compatible System One decision server on DiffusionGemma | openjev: a Jev-compatible decision server on DiffusionGemma | replica | Python | 184 | Apache-2.0 | |
| typesafe-ai/system-one-adapter-pythonDrop-in TypeSafeClient replacement backed by LLM APIs | System One adapter for LLM APIs | repo | Python | 184 | MIT | |
| itsmostafa/typesafe-mcpmcp connector to give your AI agent direct access to typesafe ai's jev model | typesafe-mcp: Jev in Claude Code, Claude Desktop, Codex and Pi | integration | Go | 182 | MIT | |
| typesafe-ai/typesafe-sdk-jsThe official TypeScript/JavaScript library for the TypeSafe API | @typesafe-ai/sdk (TypeScript) | repo | TypeScript | 173 | MIT | |
| hr98w/jev-visualAn educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos. | jev-visual: Jev-like visual inference on Apple Silicon | replica | Python | 167 | MIT | |
| jerryjliu/docjev | DocJev: document classification and splitting with Jev | repo | Python | 158 | Apache-2.0 | |
| kitze/unclutterWXT browser extension: Jev-powered page clutter removal with reusable template rules. | Unclutter: Jev-powered clutter blocker | integration | TypeScript | 157 | MIT | |
| Heman10x-NGU/openJev-verdict-2.0Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE) | openJev-verdict 2.0: a 151M calibrated decision engine | replica | Python | 155 | Other | |
| 0xNatoshi/jev-codex-routerPer-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn. | Jev Codex Router | repo | Python | 140 | MIT | |
| typesafe-ai/typesafe-sdk-pythonThe official Python library for the TypeSafe API | typesafe-sdk (Python) | repo | Python | 138 | MIT | |
| tamaratran/jev-prunerClaude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it | jev-pruner: trim tool output before the LLM sees it | repo | TypeScript | 131 | MIT | |
| dbreunig/building-with-jev-skillA skill for writing and improving programs that call Jev, TypeSafe's System One model | Building with Jev skill | repo | — | 128 | — | |
| MaxBittker/runebenchBench mark long horizon problem solving in an MMO | jevscape: RuneScape benchmark harness for Jev | benchmark | TypeScript | 125 | — | |
| hellogumbo/awesome-jevA community directory of projects built on Jev, TypeSafe AI's System One model. | Awesome Jev | directory | JavaScript | 115 | CC0-1.0 | |
| mmastrac/djev-sparkDiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe | djev-spark: DiffusionGemma NVFP4 decisions on a DGX Spark | replica | HTML | 115 | — | |
| RomanSlack/jev-droneCamera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz | jev-drone: quadrotor obstacle course in MuJoCo | demo | Python | 103 | MIT | |
| devagrawal09/stanley-codeBounded TypeSafe Jev workflows for coding agents. | Stanley: a Jev-first, self-evolving coding agent | repo | TypeScript | 98 | MIT | |
| kshetrajna12/reflexA small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5. | reflex: a small open decision model with a WebGPU build | replica | Python | 95 | MIT | |
| pithings/advocaatA small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev. | advocaat: a small type-safe client | integration | TypeScript | 88 | MIT | |
| daseinlabs/open-jevOpen Jev implementation with custom finetuning | open-jev (MLX, Apple silicon) | replica | Python | 84 | — | |
| giuliosmall/pg_typesafePre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification | pg_typesafe: Jev from SQL (C extension) | integration | C | 81 | MIT | |
| ChetasLua/jevmeterPut a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit | jevmeter: live fact-checking of spoken content | demo | Python | 78 | MIT | |
| trungdq88/youtube-sponsor-detectionDetect youtube sponsor segment with live audio and transcript powered by Jev | Live YouTube sponsor detection | repo | JavaScript | 74 | — | |
| Bodila51/grok-bot-jevConnect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples | Jev as a decision layer for Grok Bot | integration | Python | 70 | MIT | |
| wfzyx/vonThe open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev. | von: a CPU-only local decision model | replica | Python | 68 | Apache-2.0 | |
| AppitStudio/awesome-jevCurated Jev resources and runnable examples for typed AI decisions. | AppitStudio awesome-jev: community project directory | directory | Python | 67 | Other | |
| savka777/jev-useSay it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model | jev-use: a Mac computer-use harness without a vision model | demo | Swift | 64 | MIT | |
| jexp/neo4jevTypesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships | neo4jev: graph navigation with Jev | demo | Jupyter Notebook | 62 | MIT | |
| danielgshea/jev-as-a-judgeUsing Jev as an evaluator. | Jev as a Judge: decision model vs LLM judges for evals | benchmark | Python | 57 | — | |
| irfndi/prism-liquidity-agentAutonomous LP trading agent - auto-rebalancing with backtested strategies - Currently support Meteora DLMM | prism-liquidity-agent: autonomous LP rebalancing on Meteora | demo | TypeScript | 57 | MIT | |
| monteduro/killmyideaDescribe your startup idea. Jev decides: kill it, fix it or ship it. | Kill My Idea | product | TypeScript | 50 | — | |
| obie/ruby_decision_modelRuby client for decision models such as Typesafe Jev | ruby_decision_model gem | integration | Ruby | 48 | MIT | |
| zostaff/agent-arena | agent-arena: a Jev bouncer for Degen Village | demo | TypeScript | 48 | MIT | |
| EliaAlberti/jev-rulesJev picks which of your rules apply to each prompt, so Claude only sees the ones that matter. | jev-rules for Claude Code | repo | JavaScript | 45 | MIT | |
| ikermoel/open-alternative-jevOpen-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks | open-alternative-jev: typed decisions from any open-weights LLM in one pass | replica | Python | 45 | Apache-2.0 | |
| kbhuw/jev-siftClassify first. Read selectively. A portable agent plugin and MCP tool for batch text classification. | jev-sift: classify first, read selectively | integration | JavaScript | 45 | — | |
| skeptrunedev/jev-recruiterA Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief. | jev-recruiter: LinkedIn recruiting agent | demo | Python | 44 | MIT | |
| achimala/jev-paintUse Jev to make art! | jev-paint: use Jev to make art | demo | JavaScript | 41 | MIT | |
| AboveColin/HA-JevAsk your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist. | HA-Jev: Home Assistant integration | integration | Python | 40 | MIT | |
| r-ms/mini-jevmini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench. | WTF is Jev? Nine things people are already building | roundup | Python | 40 | MIT | |
| yusukebe/hono-jev-routerRoute HTTP requests by meaning. A semantic router for Hono powered by Jev. | hono-jev-router | integration | TypeScript | 40 | MIT | |
| GhalebDweikat/winnowA calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context. | winnow: a calibrated context sieve for Claude Code | integration | Python | 38 | MIT | |
| ellipsis-dev/blinkCodebase search powered by Jev from @typesafe-ai | blink: codebase search with Jev-scored paths | repo | TypeScript | 37 | — | |
| iammrduncan/typesafe-ai-benchmarkThis is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. | Needle 3 vs Jev: an 'imposter Jev' gateway benchmark | benchmark | TypeScript | 34 | MIT | |
| Heman10x-NGU/Verdict-open-jevNon-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground | openJev-verdict 2.0: a 151M calibrated decision engine | replica | Python | 33 | Other | |
| DanRWilloughby/snifftestA prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model. | Sniff Test: a prose linter where Jev is the judge | repo | TypeScript | 25 | MIT | |
| h100envy/nerve | nerve: a Jev gate in front of an onchain trading agent | demo | Python | 24 | MIT | |
| mithalouni/system-one-openOpen replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal) | system-one-open | replica | Python | 24 | Other | |
| PyModel/typesafe-mcp | typesafe-mcp: Jev as an MCP server for a local GLM agent | integration | Go | 23 | MIT | |
| rorshopping/jev-on-a-laptopUnofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo. | jev-on-a-laptop: parallel constrained decoding on MLX | replica | Python | 23 | Other | |
| sgoedecke/system-oneBatched single-token choice inference for open language models, compatible with TypeSafe | system-one: batched single-token choice inference | replica | Python | 23 | — | |
| JoshuaSP/open-jevTyped JSON inference with DiffusionGemma, with Every and Jev benchmark results | open-jev with DiffusionGemma | replica | Python | 22 | MIT | |
| mizzlelover/jev-hubJEV HUB · X 上关于 TypeSafe AI「系统一模型」Jev 的长文与演示视频聚合（保留原链与作者）｜ 谁是专家 出品 | JEV HUB: 216 demo videos and 214 long posts, categorised | directory | CSS | 21 | Other | |
| Argos1111/jev_localReplicating Jev with a local LLM | jev_local: TypeSafe-compatible adapter over LFM2.5 | replica | Python | 20 | — | |
| Zaious/jev-capability-atlasIndependent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙語 repo。 | Jev capability atlas | benchmark | Python | 20 | Other | |
| braintrustdata/braintrust-sdk-pythonPython Tracing & Evals library for Braintrust | Braintrust: Jev as a typed scorer for agent responses | integration | Python | 19 | Apache-2.0 | |
| krzyzanowskim/TypeSafeTypeSafe SDK in Swift | TypeSafe SDK in Swift (krzyzanowskim) | integration | Swift | 19 | MIT | |
| kieranklaassen/ruby_llm-typesafeTypeSafe structured-output provider for RubyLLM 2 | ruby_llm-typesafe | integration | Ruby | 18 | MIT | |
| colliber/duckdb-jevDuckDB extension: typed Jev answers as real SQL types | duckdb-jev | integration | C++ | 17 | MIT | |
| qkal/CannyStops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies. | Canny: stop coding agents from claiming work is done without evidence | integration | TypeScript | 17 | MIT | |
| sharziki/semdecideTyped semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev. | SemDecide: typed semantic decisions for Unix pipelines and CI | integration | Python | 16 | MIT | |
| oso95/x-scannerChrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter | x-scanner: label X posts on five dimensions | integration | TypeScript | 15 | MIT | |
| sensahin/transcript-lensYouTube transkriptlerini anlamına göre keşfedin. Türkçe arayüz, Jev analizi, altyazı dışa aktarma ve Vercel kurulum rehberi. | transcript-lens: explore YouTube transcripts by meaning | demo | TypeScript | 15 | MIT | |
| chopratejas/invalidateThe invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev. | invalidate: memory-lease invalidation with Jev | integration | Python | 14 | Apache-2.0 | |
| TypeLLM/TypeLLMType-Safe Decoding for Autoregressive LLMs | TypeAR: Jev-inspired type-safe decoding | replica | Python | 14 | Apache-2.0 | |
| TypeLLM/TypeLLMType-Safe Decoding for Autoregressive LLMs | TypeAR: Jev-inspired type-safe decoding | replica | Python | 14 | Apache-2.0 | |
| AbdelStark/jev-benchmarksProbability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks. | Jev vs GLiNER2.5 benchmark | benchmark | Python | 13 | Apache-2.0 | |
| kishida/llama.cppLLM inference in C/C++ | llama.cpp jev branch: local decisions on Qwen and Gemma | repo | — | 13 | MIT | |
| kavehmz/typesafe-playgroundInteractive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs. | Self-driving simulation with typed decisions | demo | JavaScript | 11 | — | |
| kylemclaren/jevqlSemantic SQL for Postgres, powered by Jev | jevql: semantic predicates for vanilla Postgres | integration | Go | 11 | MIT | |
| madeye/pi-jevJev-assisted file retrieval and request caching for faster Pi workflows | pi-jev: Jev-assisted file retrieval and request caching for Pi | integration | TypeScript | 11 | MIT | |
| Twister915/typesafe-aiTyped TypeSafe AI clients for Rust, with async and blocking backends and observable retries. | typesafe-ai: Rust bindings for the System One API | integration | Rust | 10 | Apache-2.0 | |
| ainame/swift-typesafeUnofficial Swift SDK for TypeSafe | swift-typesafe: an unofficial Swift SDK | integration | Swift | 9 | MIT | |
| emrickgarrett/OneVOneJev1v1 Jev quickscope arena — Three.js + TypeSafe System One | OneVOneJev: a 1v1 quickscope arena on Three.js | demo | TypeScript | 9 | — | |
| marc2332/findmejev + fs = findme | findme: jev + fs | demo | Rust | 9 | — | |
| matthewp/flue-jev-demoFlue agent routing with TypeSafe Jev through Cloudflare AI Gateway | Flue agent + Jev via Cloudflare AI Gateway | demo | TypeScript | 9 | — | |
| AkashPriyadarshii/jev-curateHigh-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul). | jev-curate: sift pretraining datasets at 1,500+ rows/sec | integration | Rust | 8 | MIT | |
| fornhere/hafiza-osLinux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı Mem0/Jev. | hafiza-os: a sourced second brain with optional Jev | integration | Python | 8 | MIT | |
| ranjan2829/AskJevAskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude) | Got Jev — now what? A real deployment list | roundup | TypeScript | 8 | MIT | |
| reachjalil/jevlogsOpen-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis. | jevlogs: score log signal before the expensive LLM pass | integration | TypeScript | 8 | MIT | |
| walidboulanouar/awesome-jev-use-casesThings built with Jev (TypeSafe), plus patterns, documented limits, and unbuilt ideas | awesome-jev-use-cases: demos, patterns, limits, unbuilt ideas | directory | — | 8 | CC0-1.0 | |
| bohutang/siftChrome extension that labels every post on X (Substance · Humor · Chit-chat · Promo · Junk · AI-written) with TypeSafe Jev, and hides the ones you don't want. | Sift: label every X post with Jev and hide the junk | product | JavaScript | 7 | MIT | |
| intikhab49/open-jev-typed-decision-engineOpen reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min. | open-jev: a 150M non-LLM typed decision engine | replica | Python | 7 | Apache-2.0 | |
| Skyvern-AI/jevscapeRuneBench harness for TypeSafe's Jev: bounded action catalog, tick-mode controller and a live dashboard | jevscape: RuneScape benchmark harness for Jev | benchmark | TypeScript | 7 | — | |
| GiesN/typesafe-jev-workflow | LangGraph email workflow with Jev | demo | Python | 6 | — | |
| prismhq/jev-routerOpen-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM | jev-router on LiteLLM | integration | Python | 6 | MIT | |
| Reindeer-AI/pi-jev-guardCheck Pi code edits against repository Markdown rules with TypeSafe Jev | pi-jev-guard: check Pi code edits against repo rules | integration | TypeScript | 5 | — | |
| hotchpotch/jev-rerankerJev-powered relevance filtering and reranking for RAG in Python. | jev-reranker: relevance filtering and reranking for RAG | integration | Python | 4 | MIT | |
| zhuyansen/jev-search-rerank-evalDoes a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured. | Jev as a reranker: graded-relevance eval | benchmark | Python | 4 | MIT | |
| ajensenwaud/hermes-jev-pluginTypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate | hermes-jev-plugin: decision tools for Hermes Agent | integration | Python | 3 | MIT | |
| akash-kamat/system-one-gemmaOpen-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev. | system-one-gemma | replica | Python | 3 | — | |
| iapp-technology/openthai-systemoneOpenThai-SystemOne: open Thai + English System One decision model (0.8B, 256-way slot head, Apache-2.0) | OpenThai-SystemOne: an open Thai + English decision model | replica | Python | 3 | Apache-2.0 | |
| jamesward/zio-typesafe-ai | zio-typesafe-ai: a Scala ZIO client | integration | Scala | 3 | Apache-2.0 | |
| mateonunez/jodSemantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers. | jod: semantic schemas over Jev | integration | TypeScript | 3 | MIT | |
| mizchi/jev-lexerLanguage-agnostic syntax highlighter: split like gpu-lexer, classify every part with Jev, render Shiki-compatible tokens, HTML and ANSI | jev-lexer: syntax highlighting with no language knowledge | demo | TypeScript | 3 | MIT | |
| WiktorB2004/llama-index-jevLlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge. | LlamaIndex reranker and selectors for Jev | integration | Python | 3 | MIT | |
| 0xtrou/rubikjevChallenge the Jev's intelligence in Rubik Cube puzzles | Jev solves the cube | demo | TypeScript | 2 | — | |
| adtyavrdhn/pydantic-jev-examplesPydantic AI capabilities made stronger with Jev: small runnable demos, one file each | Pydantic AI: first-class TypeSafeModel | integration | Python | 2 | — | |
| caiovicentino/jev-shieldSemantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check. | jev-shield: semantic MCP firewall | repo | JavaScript | 2 | MIT | |
| FirasSX914/JanusMeasure when to use Jev and other models on your data, then route accordingly. | Janus (formerly calibre): confidence-routed fallback study | benchmark | Python | 2 | MIT | |
| gholtzap/jev-codex-model-and-effort-router | A Jev-based model and effort router for Codex | integration | Python | 2 | — | |
| iamvatsalpatel/tiershiftShift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python. | tiershift: policy-bounded LLM cost router | integration | TypeScript | 2 | MIT | |
| kotoba-lang/typed-decisionsJev-shaped typed-decision model (state + Choice/Score/Noul questions -> calibrated probabilities, one pass) on ModernBERT / DeBERTa / LLaDA-MoE, with measured latency, accuracy, calibration and training cost | open-jev-deberta-v3-large (Kotoba Labs) | replica | Python | 2 | Other | |
| morinokami/hunk-triageRead the important changes first. | hunk-triage: read the important changes first | integration | TypeScript | 2 | MIT | |
| RiskAverseTech/toolgateOpen auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook | toolgate: a tool-call firewall for agents | repo | TypeScript | 2 | MIT | |
| shunshunNi/redmine_jevAsks Jev whether a Redmine issue's tracker fits, while you fill in the form | redmine_jev: does this issue's tracker fit? | integration | Ruby | 2 | MIT | |
| TenzinDhonyoe/bevBev: the slowest classifier in the world, at Jev prices. npx bev-ai | bev: the slowest classifier in the world, at Jev prices | demo | TypeScript | 2 | MIT | |
| TypeSafeAI/clarity-judgeMulti-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence. | Clarity Judge: seven writing checks | demo | TypeScript | 2 | — | |
| 4esv/jev-evalBenchmark TypeSafe Jev against any OpenRouter model on your own labelled classification data: accuracy, calibration, latency, cost | Jev vs GPT-5.6 Terra head-to-head | benchmark | Python | 1 | — | |
| AdamPippert/granite-decisionsGraniteJev... | granite-decisions: a Granite 4.1 3B RHCD model | replica | Python | 1 | MIT | |
| altryne/twitter-timeline-analyzerChrome extension to analyze and filter your Twitter/X timeline using AI-powered topic detection with W&B Weave observability | Got Jev — now what? A real deployment list | roundup | JavaScript | 1 | — | |
| choxos/jevchessJev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates. | JevChess: Jev vs LLMs, Stockfish or you | demo | JavaScript | 1 | MIT | |
| markfive-proto/typesafe-vs-deepseekTypeSafe (Jev) vs DeepSeek-flash: side-by-side speed/token/cost/accuracy comparison across invoice extraction, email classification, and reranking | Jev vs DeepSeek-flash side by side | benchmark | Python | 1 | — | |
| muse0509/jev-preflightA bounded Jev risk check for Claude Code: eight risk axes, one request, one optional reinspection. | jev-preflight: a bounded risk check for Claude Code | integration | Go | 1 | MIT | |
| TheEleventhAvatar/triage-botReal-time support triage + response bot Jev routes the ticket to a specialist agent (general / account / billing / technical) and decides whether a human should take it instead — all as typed data, no text to parse. Cerebras then drafts the reply using whichever agent Jev picked. The script times both calls separately so you can see the split. | triage-bot: real-time support triage with Jev and Cerebras | demo | TypeScript | 1 | — | |
| TokenTrim/jev-routing-experimentBenchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena | Jev as an LLM router: a mostly negative result | benchmark | Python | 1 | Apache-2.0 | |
| zadescoxp/kadeconsoleKade console is a bloomberg terminal type of analytical tool. | kadeconsole: a terminal-first stock analytics tool | product | Python | 1 | — | |
| 0x963D/last-exitA cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts. | Last Exit: a checkpoint game judged by Jev | demo | JavaScript | 0 | Other | |
| 0xArx/jevegisGuardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT. | Jevegis: guardrails API on Jev | product | TypeScript | 0 | MIT | |
| DomMonte/n8n-nodes-typesafe-ain8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities | n8n community node for the System One API | integration | TypeScript | 0 | MIT | |
| enderkus/zammad-jev-dispatcherAI ticket triage for Zammad using Jev (TypeSafe AI) - classifies and routes new tickets into the right service group automatically. | Zammad ticket dispatcher on Jev | integration | Ruby | 0 | MIT | |
| gopalanj/chess-jev | ChessJev: a System One model for chess | replica | Python | 0 | MIT | |
| HackSing/jev-report发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表 | Chinese-language fact-check of the 193.6x / 444.6x claims | benchmark | Python | 0 | MIT | |
| JacobLinCool/jev-paper-judgeFeedback on your paper in seconds. | Jev Paper Judge | demo | TypeScript | 0 | MIT | |
| jagenaujagenau/ground-truthGround News style bias check for the article in your current tab. | Ground Truth: news-framing browser extension | integration | TypeScript | 0 | MIT | |
| m-mizutani/semgateSemantic request filtering and routing for Go HTTP, powered by TypeSafe AI. | semgate: semantic request filtering for Go HTTP | integration | Go | 0 | Apache-2.0 | |
| MANISH007700/tab-bouncerChrome extension that closes the tabs you don't need, judged by TypeSafe's Jev in one call. Tell it what you're doing; it shows the rest the door. | Tab Bouncer: close the tabs you don't need, judged in one call | product | JavaScript | 0 | MIT | |
| pedroknigge/mcp_jevOpen MCP server to run TypeSafe Jev (System One) packs locally — Choice / Noul / Score for Cursor & agents | mcp_jev: local MCP server with Jev packs | integration | TypeScript | 0 | MIT | |
| rimusz/jev-mcpProof of concept MCP for Typesafe's new Jev AI model | jev-mcp | repo | TypeScript | 0 | MIT | |
| teyhouse/jev-secret-detectionMeasures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets | Secret detection test with Jev | demo | Python | 0 | — | |
| torumitsutake/jev-page-verdict | Page Verdict: classify web pages by purpose and stance | product | JavaScript | 0 | MIT | |
| TrainLCD/Functions👷 Cloudflare Workers for the TrainLCD mobile app. | TrainLCD: Jev re-ranking in a production train app | integration | TypeScript | 0 | — | |
| Wizhill05/typesafe-image-diffusionDiffusion-style pixel art out of a general classifier (TypeSafe Jev): 256 parallel pixel questions + refinement passes | Jev as a pixel-art generator | demo | HTML | 0 | — | |
| zsoXi/agent-handoff-gateAn experimental protocol for evidence-aware agent handoffs, bounded worker continuation, and TypeSafe/Jev-assisted review, with reproducible evaluation. | Agent Handoff Gate | integration | Python | 0 | MIT | |
| y0usaf/pi-jev | pi-jev (y0usaf): a measured tool-call gate for Pi | integration | — | — | — | — |
| ying-kai-liao/jev-browser | jev-browser: the LLM plans, Jev decides — library, CLI and MCP | integration | — | — | — | — |
No repositories match.
Stars and dates come from the public GitHub API via npm run refresh-github; redirected repositories show their current name.