claude-code-templates
davila7/claude-code-templates
A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.
★ 31,082
Agent tooling 158
openwork
different-ai/openwork
Open-source Claude Cowork alternative whose eval testkit can use Jev as a typed verification judge for agent-produced work.
★ 23,696
fast-jev-compaction
tamaratran/fast-jev-compaction
Claude 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.
★ 6,295
jev-review (devagrawal09)
devagrawal09/jev-review
Reviews a Git diff or a codebase in stages and displays review leads in a local dashboard.
★ 544
Community additions 156
Laya
NandhaKishorM/laya
Open alternative: non-autoregressive decision model that answers `choice`, `score`, and `noul` questions with RLCD-trained calibrated probabilities in a single ~35 ms forward pass, published on PyPI and Hugging Face.
★ 16,260
DeepSearcher stopping-policy experiment
zilliztech/deep-searcher
Agentic search: a standalone evaluation uses Jev Noul judgments on accumulated evidence to decide whether to stop or continue within a search-round budget, comparing stopping behavior, evidence recall, and decision cost.
★ 8,278
laya-mlx
mizorewww/laya-mlx
Local runtime: independent MLX port of the Laya checkpoints that runs typed decisions natively on Apple Silicon — 13.4 ms median end-to-end per short English decision, 7.4 ms with the multilingual checkpoint, and zero output tokens, with no PyTorch, Transformers runtime, or cloud API.
★ 5,389
fx
vercel-labs/fx
Coding agent: ships a `typesafe_permission_reviewer` builtin so the agent's permission decisions run through Jev rather than an LLM call.
★ 3,126
Benchmarks & research 99
NanoJev
TianyuCodings/NanoJev
Open 0.6B Jev replica with parallel decisions, complete probability distributions, training pipeline, weights, dataset, and live demos.
★ 1,988
jevlike
vinnylarouge/jevlike
Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.
★ 1,231
decider
Mapika/decider
One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.
★ 311
jev-visual
hr98w/jev-visual
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
★ 240
Browser & computer use 72
cua
trycua/cua
Cua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.
★ 25,977
Jev Ultrafast
browser-use/jev-ultrafast
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
★ 17,985
agent-desktop
lahfir/agent-desktop
An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
★ 1,506
celesto
CelestoAI/celesto
Agent-computer platform with a runnable pull-request review lab where Jev judges whether findings are introduced, supported, and actionable.
★ 966
Applications 72
jev-chat-jarvis
jev-chat/jev-chat-jarvis
Android conversation copilot where Jev interprets chat context and helps rank candidate replies before the user inserts one.
★ 3,660
jev-trader
jarrodwatts/jev-trader
A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.
★ 2,050
tax-doc-classifier
kyotofin/tax-doc-classifier
A tax-document page classifier that uses Jev to choose from predefined IRS form and page categories.
★ 396
notra
usenotra/notra
Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions.
★ 213
Games & simulations 70
typesafe-mario
fhshaik/typesafe-mario
An experimental NES Mario controller that gives Jev structured emulator RAM and telemetry instead of screenshots.
★ 352
embodied-jev
FBddcz/embodied-jev
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs
★ 186
jevpilot
standardagents/jevpilot
A browser driving simulator where Jev chooses among locally generated paths and speeds.
★ 168
jev-drone
RomanSlack/jev-drone
A MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.
★ 131
Routing & Cost Optimization 58
litellm
BerriAI/litellm
AI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing.
★ 59,424
oh-my-pi
can1357/oh-my-pi
Coding agent with a TypeSafe judgment provider that uses Jev for typed checks, routing, and workflow decisions.
★ 32,765
openchamber
openchamber/openchamber
OpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.
★ 10,318
firstmate
kunchenguid/firstmate
Firstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.
★ 7,002
Frameworks & integrations 53
litellm
BerriAI/litellm
AI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing.
★ 59,424
oh-my-pi
can1357/oh-my-pi
Coding agent with a TypeSafe judgment provider that uses Jev for typed checks, routing, and workflow decisions.
★ 32,765
json-render
vercel-labs/json-render
A Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.
★ 18,086
eve
vercel/eve
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
★ 5,316
SDKs & clients 50
advocaat
pithings/advocaat
A small TypeScript client for asking Jev multiple typed questions about the same data.
★ 89
ruby_decision_model
obie/ruby_decision_model
A Ruby decision-model client for Jev through TypeSafe’s native API or OpenRouter.
★ 50
pi-typesafe
DevMortimer/pi-typesafe
A Pi Jev extension providing a decision tool, terminal playground commands and an API for other extensions.
★ 41
jev (dannote)
dannote/jev
TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.
★ 30
MCP & Integrations 49
vellum-assistant
vellum-ai/vellum-assistant
An optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.
★ 1,303
jev-mcp (jkudish)
jkudish/jev-mcp
Eight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.
★ 282
typesafe-mcp
itsmostafa/typesafe-mcp
An MCP server that lets Claude Code, Claude Desktop, Codex and Pi ask Jev typed questions.
★ 258
jev-review (NiazMorshed2007)
NiazMorshed2007/jev-review
A local MCP code-quality reviewer returning structured scores to coding Agents.
★ 203
Demos & playgrounds 46
killmyidea
monteduro/killmyidea
A startup-idea evaluation demo assigning KILL, FIX or SHIP labels from Jev scores.
★ 97
typesafe-ai-playground (BunsDev)
TypeSafeAI/typesafe-playground
Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.
★ 20
jev-me
jon-devlapaz/jev-me
A grill-me style interrogation of your idea, with Jev doing the grilling.
★ 13
jev-autopilot
arielweinberger/jev-autopilot
This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.
★ 9
CLI & Pipelines 37
ai-cli
vercel-labs/ai-cli
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
★ 811
orchestkit
yonatangross/orchestkit
OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.
★ 283
skillranker
Dicklesworthstone/skillranker
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
★ 113
formanator
timrogers/formanator
CLI and MCP server for Forma benefit claims that can use Jev to classify receipt line items into reimbursement categories.
★ 99
Jev-like models 34
kev
jaredpalmer/kev
Trainable family of small Qwen-based Jev-like decision models with typed primitives, datasets, evaluation tools, and local inference.
★ 4,081
SemIf
TheoLeeCJ/SemIf
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
★ 3,808
Bespoke Nimble
bespokelabsai/nimble
Open data, training recipe, and a 9B model for Jev-style choice and true/false decisions on Apple Silicon or NVIDIA GPUs.
★ 1,619
LocalJev
githubnext/localjev
Local Jev-compatible System One API that converts typed questions into DiffusionGemma classification prompts and probabilities.
★ 728
Other lists 29
awesome-jev (yibie)
yibie/awesome-jev
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
★ 1,294
awesome-jev-by-typesafe
Anil-matcha/awesome-jev-by-typesafe
Evidence-backed Jev use cases, patterns, prompts, and starter code.
★ 802
awesome-typesafe-jev
AbdelStark/awesome-typesafe-jev
Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.
★ 465
jev-skill
wuyoscar/jev-skill
An awesome collection of Jev use cases, workflows, and agent skills.
★ 425
SDK & Decision Frameworks 20
composio
ComposioHQ/composio
An optional TypeSafe provider for Composio that uses Jev to choose among tools and bounded argument options.
★ 30,288
ai
vercel/ai
The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.
★ 26,899
eliza
elizaOS/eliza
An optional TypeSafe HTTP adapter in Eliza’s source, not registered with the Agent runtime by default.
★ 19,409
langchainjs
langchain-ai/langchainjs
An optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.
★ 18,220
High-Frequency & Simulation 19
jev-trader
jarrodwatts/jev-trader
A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.
★ 2,050
jevpilot
standardagents/jevpilot
A browser driving simulator where Jev chooses among locally generated paths and speeds.
★ 168
jev-trade
aowang-ai/jev-trade
An experimental Hyperliquid trading bot using Jev to choose long or short and whether to open, close, or hold.
★ 109
Jev-Trades
zadescoxp/Jev-Trades
A dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.
★ 27
Context GC & Filter 17
fast-jev-compaction
tamaratran/fast-jev-compaction
Claude 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.
★ 6,295
hermes-jev-skills
kerpopule/hermes-jev-skills
Hermes plugin and skill suite using Jev for model routing, skill selection, memory filtering, compaction, and GUI actions.
★ 518
jev-pruner
tamaratran/jev-pruner
A Claude Code output-pruning plugin filtering selected Bash output before it reaches the main model.
★ 140
NeuroLink
juspay/neurolink
Unified AI SDK whose TypeSafe decide API supplies typed judgments for model routing, compaction, tools, and retrieval planning.
★ 138
Security & Guardrails 16
litellm
BerriAI/litellm
AI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing.
★ 59,424
agentgateway
agentgateway/agentgateway
A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.
★ 4,986
Agent
AgentiLoop/Agent
An optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.
★ 629
jev-experiments
dabit3/jev-experiments
A collection of Jev developer-tool experiments, including Commit Sentry for semantic checks on staged diff hunks.
★ 369
Voice & Conversation 13
jev-chat-jarvis
jev-chat/jev-chat-jarvis
Android conversation copilot where Jev interprets chat context and helps rank candidate replies before the user inserts one.
★ 3,660
vellum-assistant
vellum-ai/vellum-assistant
An optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.
★ 1,303
jev-voice-browser
moritzkremb/jev-voice-browser
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
★ 244
OpenWhisper
Knuckles92/OpenWhisper
A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.
★ 187
Browser & OS Action 8
Jev-cu
Sac-Y/Jev-cu
A Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act.
★ 577
omg.dev
BennyKok/omg.dev
An omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.
★ 535
aside-jev
himomohi/aside-jev
An MCP server and skill adding Jev decisions to Aside browser Agents.
★ 7
jev-clerk
stas4000/jev-clerk
A macOS desktop clerk that books supplier invoices: Jev picks each click from a closed action list; a deep model only rewrites the playbook.
★ 6
Evaluation & Observability 8
taskuary
ldbumble/taskuary
An optional Jev judgment module in Taskuary for checking user-defined conditions on task state.
★ 118
Canny
qkal/Canny
Keeps an execution ledger for Claude Code and Codex CLI to check for passing validation after edits.
★ 42
goodwatch-monorepo
alp82/goodwatch-monorepo
A film-and-TV attribute-scoring experiment inside GoodWatch comparing Jev question designs and batch sizes.
★ 38
jev-playground
mizchi/jev-playground
A MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages.
★ 19
Domain & Vertical Tools 6
ai-hedge-fund
virattt/ai-hedge-fund
An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.
★ 63,671
JevScout
hqman/JevScout
A demo job-search Skill for coding Agents that browses company careers pages in Chrome, uses Jev to screen AI and software-engineering roles, and saves the results.
★ 32
jevscan
jevbook/jevscan
An EVM Token screening tool with library, CLI and MCP interfaces for market-feature-based risk judgments.
★ 3
jevsume
unownone/jevsume
A resume-review app that checks general writing and structure or compares a resume with a specific job description.
★ 2
Official 6
TypeSafe agent skills
typesafe-ai/skills
Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.
★ 1,806
System One adapter (Python)
typesafe-ai/system-one-adapter-python
Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.
★ 263
TypeSafe JavaScript SDK
typesafe-ai/typesafe-sdk-js
The JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.
★ 226
TypeSafe Python SDK
typesafe-ai/typesafe-sdk-python
Official TypeSafe Python SDK with synchronous and asynchronous clients for Jev System One, plus question and answer types.
★ 202
SDK & Integrations 3
langchain
langchain-ai/langchain
An optional Jev classifier integration for Python LangChain workflows.
★ 146,884
pydantic-ai
pydantic/pydantic-ai
An optional TypeSafe provider and Jev model integration for Pydantic AI.
★ 20,117
jev-resilience
Vicente-MD/jev-resilience
A Spring WebFlux integration that detects error messages hidden in HTTP 200 response bodies.
★ 2
Data & Search 2
kody
kentcdodds/kody
Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.
★ 665
jevsome-projects
ozers/jevsome-projects
A Jev project directory and discovery pipeline that stores integration evidence and can use Jev for classification.
★ 1
Creative Tools 2
jevthoven
cocktailpeanut/jevthoven
Turns a music prompt into editable multitrack MIDI by asking Jev to choose instruments, harmony, and bar patterns.
★ 12
jev-music-theory-1
adammichaelwood/jev-music-theory-1
Explores Jev on harmony exercises and music-theory questions, alongside a piano demo driven by chord choices.
★ 1
Codebase & Graph Pathfinding 2
PiJ
tonyzdev/pijev
A Pi-based terminal coding Agent whose main model handles reasoning, edits and tools while Jev provides advice.
★ 4
leanest
baronunread/leanest
Adds Jev-based selection before an existing test runner using diffs and test source.
★ 3
Decision Tools 2
jevchat
kt3k/jevchat
A chat-style Jev demo whose answers are selected from predefined or custom options rather than generated prose.
★ 1
turing-jail
bugkiwi/turing-jail
Interactive three-level AI interrogation game powered by TypeSafe Jev; write responses and pass plea, logic, and paradox verdicts to earn release.
★ 0
Community (New) 251
jev-chat-jarvis-mac
jev-chat/jev-chat-jarvis-mac
A macOS floating-window companion (documented in Chinese) for WeChat that reads the screen and uses a local small model to judge an incoming message's real intent and risk level, then drafts reply candidates — strictly read-only, with no injection into or hooking of WeChat itself.
★ 248
agent-jev
malevrigns/agent-jev
AgentJev-0.6B, a fast open 'System One' decision model for AI agents that takes unstructured state (diffs, traces, logs) plus structured questions and returns calibrated probability distributions from a single roughly 50ms forward pass, with no output tokens decoded.
★ 235
jevharness
tianyucodings/jevharness
A framework where an LLM authors a task-specific harness for Jev — turning raw observations into features, constructing Jev questions, and combining the answers into actions — which can then be run, inspected, and optionally improved using reward signals and full execution traces.
★ 147
jev-leftpad
f/jev-leftpad
A joke npm package that left-pads a string by calling TypeSafe's Jev model to do it, deliberately using a model call for a task that a single `padStart()` line could already handle.
★ 82