- 901android-jevMCP server and skill that let an agent drive an Android phone naturally over adb
FZ2000/android-jev · Python
20adbai-agentsandroidandroid-automationautomationclaude - 902ask-jevUltra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines
logicrw/ask-jev · Python
20agent-architectureagent-evaluationagentic-workflowai-agentsclaude-codeclicoding-agents - Decides whether a message should reach the LLM at all, using TypeSafe Jev choice probabilities.
AstrBotDevs/astrbot_plugin_reply_gate · Python
21astrbotastrbot-pluginpluginpython - 904awesome-jevA curated list of Jev / TypeSafe System One projects, SDKs, tutorials, and evaluations. English and 简体中文.
majiayu000/awesome-jev · Python
25ai-agentsawesomeawesome-listbrowser-automationmodel-routing - 905Awesome-JevA collection and survey of Jev
youzizzz1028/Awesome-Jev · TeX
21tex - Jev-powered AI agent skills for Codex and Claude Code: code review, testing, debugging, extraction and QA evidence. Open source, MIT.
Pleo2/awesome-jev-agent-skills · Python
20agent-skillsai-agentsclaude-codecode-reviewcodexdebuggingdeveloper-tools - Open-source projects built on TypeSafe's Jev decision model: open replicas, agents, dev tools, SDKs and MCP servers, apps. By type, each security-graded. English / 中文.
zhuyansen/awesome-typesafe-jev
20ai-agentsawesome-listdecision-modelmcp - Piloto de agentes de backoffice: LLM gera e raciocina, Jev (TypeSafe AI) decide, roteia e verifica
lucianoon/backoffice-agents · Python
20python - 909barruntoA Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse
elpumberto/barrunto · TypeScript
20typescript - 910calibreMeasure when to use Jev and other models on your data, then route accordingly.
FirasSX914/calibre · Python
20pythonbenchmarkcalibrationconfidence - Jev Bayes, No? Testing TypeSafe AI's Jev against Bayesian-optimal strategies, and testing if Jev can effectivly use Bayesian priors.
TomRichner/can-jev-bayes · Python
20python - 912claude-jevJev System One for Claude Code — typed Choice/Noul/Score via live TypeSafe API (mirror of opencode-openjev, live-only MCP)
darwintechlab/claude-jev · JavaScript
20javascript - Claude Code plugin + zero-dependency CLI for TypeSafe's Jev: judge items in bulk with calibrated yes/no, pick-one and rubric answers; handle the confident ends in code, review only the uncertain band.
Shakibuzzaman3104/claude-jev-funnel · Python
20classificationclaude-codeclaude-code-pluginclaude-skillsllm-toolsopenrouter - VS Code Codex Plugin for Jev-gated tool output integration
PhilippElhaus/Codex-Decision · Rust
21codexpluginpython - 915codex-jevEvidence selection and quota-aware recovery for Codex. Optional Jev reranking, local privacy controls, exact source reads. Keep your coding model.
Hyper-AI-Lab/codex-jev · JavaScript
20ai-codingcodexcontext-engineeringcontext-managementdeveloper-toolsmcpmodel-context-protocol - AI model routing for Codex subagents. Let Jev choose the model and reasoning effort for each mission, using your own task profiles.
guilhem/codex-subagent-router · JavaScript
20agent-orchestrationagentic-aiai-agentscodexcodex-pluginllm-routing - Safe Python-like script node with a System One decision model: ask yes/no, choice, and score questions via TypeSafe AI's Jev API, with local GGUF LLMs as a fallback. Multiple inputs and outputs let one node handle math, logic, text editing, conditional routing, resolution selection, filename generation, and more.
kantan-kanto/ComfyUI-ScriptFlow · Python
21python - A Taboo-style parlour game for design systems, refereed by Jev (TypeSafe System One model)
southleft/component-charades · TypeScript
20design-systemsgamenextjstypescript - A library to chain Jev calls, for the deranged and enlightened
Fox-Islam/composable-jev · PHP
20php - 920decidexIndustrial-grade Decision Foundation Layer for System One Game-Playing Models (Jev / NanoJev)
dengyie/decidex · Python
20python - 921decimaOpen, CPU-sized Jev-style (System One) decision model: situation + question + options → calibrated probabilities. 122M, ~20 ms on one CPU core, runs in your browser.
amyrmahdy/decima · Python
20calibrationdecision-modeljev-alternativemultilingualonnxtyped-decisions - 922decioTurn context into typed decisions and pre-declared actions.
youyo/decio · Go
21automationclaude-codeclidecisiongohooks - Decision circuits: typed questions to a System One model, calibrated probabilities back, gates in code. Zero-dependency Python SDK with LangChain, OpenAI Agents, and Claude Agent SDK integrations.
Barneyjm/decision-circuits · Python
21ai-agentscalibrationdecision-circuitsguardrailslangchainllmpython - Rate and spend limits for code that calls Jev and other decision models
zachlandes/decision-gate · JavaScript
21javascript - Use DeepSeek/llamacpp like Jev
lenML/deep-jev-seek · TypeScript
20apideepseektypescript - DGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and a HuggingFace training-brain flywheel.
ctaxnagomi/dgui-hypermem · TypeScript
20ai-agentscloudflare-workersd1deckerguilong-term-memorymcpmcp-server - High-performance verbatim context compaction for coding agents (Claude, Codex, Antigravity, Gemini, OpenCode)
satiricalguru/Fast-Jev-Agents · TypeScript
20ai-agentsantigravityclaude-codecontext-compactiongeminillmopenai-codex - Fork of tamaratran/fast-jev-compaction: Jev via OpenRouter with zero data retention (zdr, data_collection: deny)
ingebyd/fast-jev-compaction-openrouter · TypeScript
20typescript - 929five-linesUse Jev to review a PR diff against the ten rules of Five Lines of Code
jamescazzetta/five-lines · Rust
20clicode-reviewfive-lines-of-coderefactoringrusttree-sitter - 930FootworkA verified browser agent: a cheap Jev guard (evidence-checked completions, a destructive gate) in front of any LLM browser driver, with Jev taking the mechanical steps in dual mode. Built on browser-use; every number pre-registered and measured.
Tom-R-Main/Footwork · Python
21browser-agentbrowser-automationbrowser-usedual-processllm-agents - 931fuzzy-jevAsk Jev typed questions about text and get calibrated probabilities back, then turn them into decisions with fuzzy rules (AND, OR, NOT, hedges, Mamdani outputs) and draw the rule base as SVG. A CLI and a Rust library (native and wasm32).
dsaad68/fuzzy-jev · Rust
20agent-skillsagent-toolsclicli-toolfuzzyfuzzy-logic - 932GatewiseDecision infrastructure for autonomous software engineering, powered by typed System-1 decision models (Jev). No heuristic fallbacks - real, auditable model decisions.
ApexYash11/Gatewise · Python
20autonomous-agentsdecision-makingfastapigithub-appllmobservability - Hybrid AI Architecture on Google Cloud: Sub-100ms Gateway with TypeSafe Jev (System 1) and Vertex AI Gemini (System 2) on Cloud Run
rominirani/gcp-gemini-decisions-hybrid-gateway · Python
20html - Select Git changes for staging with a plain-language description.
ibrahemid/git-jev-stage · TypeScript
20claude-codeclicoding-agentsgittypescript - 935gitsGits is a browser extension powered by Jev to search the leads data on the Google Maps
satyawikananda/gits · TypeScript
21browser-extensionvuetypescript - 936godot-jevGodot 4.7+ addon that wraps TypeSafe AI's Jev System One HTTP API to evaluate game state.
AlvianEka/godot-jev · GDScript
20godotgodot-addongodot-enginegodot4 - 937gosys1Client for TypeSafe's SystemOne API for Jev
robertjndw/gosys1 · Go
20go - Scores public job postings against my resume using TypeSafe's jev via the Vercel AI Gateway. Daily Vercel cron.
mcgalleg/grokbot-jev-jobs · TypeScript
20typescript - 939guideme-rustJudgments from TypeSafe Jev that read like Rust control flow: a yes/no is an if, a choice is an exhaustive match, a score is a comparison.
pedro-pscunha/guideme-rust · Rust
21api-clientasyncjudgmentllmobservabilityopentelemetry
901–950 of 3054