Trending Repos

A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.

ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0)

ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0)

AI video processing pipeline for generating vertical shorts using LLMs, Whisper transcription, highlight detection and automated editing

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

把英文论文读成舒服的中文：本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动

An LLM + Jev workflow that changes EVERYTHING. Boost your vertebrate brain with a spine inside.

1207 public resources for Jev, TypeSafe AI's System One decision model, indexed by decision pattern. Source citations, dated link checks and scheduled call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema and platform compatibility.

🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案，并主动提示凑单陷阱。

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

魔搭紫皮书｜ModelScope Cookbook：面向开发者的开源模型应用实战指南，覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC，从跑通第一个模型到构建实际应用。

聊天悬浮窗助手（macOS）：屏幕感知 + 本地小模型判断意图与风险，按话术生成回复候选。纯只读。

Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.

Jev-compatible API endpoint based on open models (prefill-only)

Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

把 OpenCode 的免费模型摆渡给 WorkBuddy —— 隔离运行时、并发检测、判定缓存、一键导入、本机 OpenAI 兼容转发口

微信聊天分析工具，支持本地 Laya 与 API 模型，提供意图识别、情绪感知、人物画像、群聊画像、好感度分析和 MBTI 聊天推测。

Research and writing can be automated. Authorship cannot. Evidence list + agent skills for spotting AI-produced papers no human stood behind.

针对GPT 6.0,V4flash的破甲实验项目

Walk through a diff the way a senior engineer reads it. A read-only TUI that turns a git change into a guided tour.

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

Defend sound research against LLM reviewer bias through meaning-preserving rewrites.

underclass: an OpenAI-compatible pooling proxy that pins sessions to one account (prompt cache stays warm), cools quota-exhausted subscriptions until their window resets, and fails fast with the earliest Retry-After when the whole pool is dry.

Zoom any paper for your better understanding

Open-source design workspace for AI agents and humans. Cloud editing, 3D, motion, MCP, WebMCP, CLI and BYOK. MIT.

Zoom any paper for your better understanding

Build distributed, production-grade, long-running agents.

Shrinkflation detector for Codex

Build distributed, production-grade, long-running agents.

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.

Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini PC.

Jev-Mem: System-One Controlled Agentic Memory

辞达：用你选择的大模型，在 Mac 的任何地方翻译和润色文字。Translate and polish text anywhere on your Mac.

精酿 BrewReel：让 DeepSeek 这类便宜模型也能做出好看的竖版宣传片。写一份产品简报，AI 挑镜头、写文案，一条命令出片。3 种配方、6 个行业、广告法校验，开源可商用。

An autonomous AI agent framework for authorized penetration testing

Persistent work state and minimal context for long-running AI agents.

🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

A categorized directory of X accounts covering AI, LLMs, agents, and technology, with original profile bios and follower counts. Available in 7 languages.

Universal AI Charter: plain-language governance principles and a public certification registry for AI models, built on disclosure instead of a development slowdown.

👁️ Review AI generated code and plan changes

Fifty prompts for gpt-image-2.5, each with the exact frame it produced - 20 short ones and 30 full engineering briefs, plus a measured Flare-vs-Sunburst comparison

Anyone can predict the future. Almost nobody keeps the receipt. A hash-chained prediction ledger for LLMs — sealed before the answer exists, graded with proper scoring rules.

Multi-agent workflow skills for mainstream coding agents (Claude Code / Codex / Cursor): evidence-governed research fan-out, dual-channel document reading, dev delivery with independent review and visual acceptance.

Persona agents with explicit memory, retrieval, adversarial smoke tests and a practical post-training roadmap.

A memory governance engine for multi-agent cloud knowledge bases — one knowledge base shared by every agent and every device, with consistency guaranteed. Pure Markdown, nine governance automations, zero dependencies.

DSH Web 插件 · 提示词优化器（SPEC v0.5 依据驱动架构）：把用户的一句话补成『带依据的执行指令』——依据只搬不造（原话／会话上下文／项目文件，每条事实带出处），只补五类缺口（指代定位／验收判据／约束边界／隐含决定／入口锚点），档位＝依据预算，默认面向 PTC 执行体。不写形式模板与验证套话。

A local app that rents a GPU in your own Colab account and serves Qwen3.8 on it: 27B on an A100-40G, or Flash-Next (125B-A6B MoE) on an A100-80G. The cost is shown before it starts; chat with images; Codex or any OpenAI client uses a fixed local /v1. Auto-stop, CU ledger, live prefill/decode. Windows, macOS, Linux.

GPT Image 2.5 prompts, verbatim and credited: 150 community prompts across 9 use cases, each with the author who wrote it and their post. Free to run.

pi-loop-studio/orchestra — evidence-driven, recoverable multi-agent engineering runtime with XState, SQLite WAL, isolated worktrees, independent review, and single-writer publication.

The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev

Native macOS GUI for Pi Coding Agent

vLLM based inference framework for agentic workload.

A Qualifying Exam for Coding Agent as Robot Learning Engineers

On-demand Higgsfield API image and video generation for coding agents, with model-specific docs and resumable jobs.

Best Browser Aim Trainer for CS2 and Valorant Practice 2026

Best Open Source CS Aim Trainer 2026 Web Based Headshot Practice Tool

Implementation of the recurrent looped transformer proposed by Yifan Zhang of Princeton

Your coding agent starts every session knowing nothing about your project. One line, and it writes its own memory from your real code, then grades itself.

由 LLM 驱动的可交互智能体：有记忆、有性格、有自己的日程与作息

Turn a repository into a safe, specific operating contract for AI coding agents.

面向企业合同全生命周期的生产级 AI Agent 平台，支持合同解析、条款结构化、风险审查、HITL 人工确认、版本管理、客户回传 Diff、谈判辅助及 PDF/Email 交付；基于 LangGraph + RAG + ContractPolicy + Agent Workflow，实现可追溯、可恢复、可审查的合同智能处理闭环

code agent

Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex and your own API calls.

Local model verification, cache and latency monitoring for coding agents — macOS, Windows and CLI

Give the agent "this" and he gets a real PC.

Portable snapshot of a pi coding-agent setup + backup/restore tooling. Clone to rebuild 22 extensions on another machine. Excludes secrets, cache, and machine state.

Source-backed GPT Image 2.5 prompts in nine languages, with quality-first curation, required inputs, visual examples and original creator links.

Rust rewrite of CLIProxyAPI: drop-in compatible proxy for Claude, Codex, Gemini and OpenAI-compatible providers

端到端智能体平台：把本机的 AI Agent 变成人人可用的 Web 产品（Vue 3 + Flask + Go WS 网关 + Docker 部署）

Your Claude, ChatGPT and Gemini subscriptions as one fast API. A single Rust binary with OpenAI, Anthropic and Gemini compatible endpoints, WebSockets and a built-in dashboard.

Give the agent "this" and he gets a real PC.

Ecossistema de Engenharia de Estudos com IA Fundamentada (NotebookLM + Gemini Estudantes). Metodologia N.A.G. (Nucleo de Aprendizagem Guiada) com 19 Prompts calibrados, Raio-X estatistico de bancas e Metodo MIT.

Three trap-laden fix-it tasks with hidden graders for testing an AI coding agent's judgment. Sandbox setup, prompts, answer key, and results for Qwen3.8-Flash, Qwen3.6-35B and Claude Opus 5.

TemplatesGrokBot.com is a library of 3,000+ ready-made Grok Bot templates. Search by task or job title, install any bot in Grokbot in minutes, and connect the whole catalog to your agents via MCP. Made by Jeroen / Nexibeo.com to help anyone build a full team of AI agents for their job.

Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files

A way of running a project with coding agents. A team of roles, a loop with a stop in it, and rules your agent cannot ignore. Text files and small Python programs, no dependencies.

Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.

A local image workspace for generating, editing, and comparing AI images with Codex, OpenAI, and Google. Bring your own accounts and API keys.

Switch between your own Claude Code and Codex logins, and see how much each one has left.

Execution posture harness for Claude Code. Your coding agent stops one step early; Castra is the step.

Save your GPT-6 Astra tokens. Let Luna do the dirty work.

Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients

Local-first skill manager for AI coding agents: one canonical skill directory, symlinked into every agent.

Free Robotics & AI learning resources, including courses, books, lectures, research papers, tutorials, projects, and more.

PromptForge: An enterprise-grade, multi-platform Prompt Engineering framework for AI Agents. Featuring 56 structured templates across 9 domains, 118 ready-to-use presets, and native adapters for Cursor, ZCode, DeepSeek Harness, Claude, and OpenAI. Built with FastAPI Web UI & Typer CLI.

Open-source personal AI assistant that lives in your WhatsApp: email, calendar, group plans, reminders and errands. Self-hosted, and it asks before it sends anything as you.

Budget caps, runaway-loop detection and circuit breakers for AI agents. Zero dependencies, framework agnostic.

Sub2API 0.2.7 OpenAI OAuth 插件：Excel2API BPS 隧道、Codex CLI 工具目录、请求时区与并行降智检测。

本地 Coding Agent 桌面工作台与终端集成中心

An AI-assisted compliance dashboard for accelerating customer onboarding, featuring automated document verification and PEP/sanctions risk screening workflows.

A Minesweeper benchmark for LLM agents. One identical board, up to nine models in parallel, one clock, one tool layer.

Contentqueen App im Test: Der ultimative KI-Textgenerator für Marketer & Creators im deutschsprachigen Raum. Schluss mit Schreibblockaden! 🚀

Explorations into the Recurrent Transformer proposed by Costin-Andrei Oncescu et al. of Harvard University

Free Robotics & AI learning resources, including courses, books, lectures, research papers, tutorials, projects, and more. A curated collection of resources to help learners build strong foundations and progress toward advanced Robotics and AI concepts.

Evidence-grounded academic research agent with claim verification, prior-work analysis, and persistent research workspaces.

Prompt as Spec — 2,383 GPT-Image-2.5 prompts, each a complete design specification. Installable as a Claude Code plugin. By Devault.

Status bar for Codex CLI and Claude Code: context, 5h/weekly quota with reset times, tokens.

Source codes for the paper "SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators"

Awesome GPT Image 2 API: curated links for the gpt image 2 api - docs, OpenRouter and kie.ai endpoints, pricing.

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.

Tactical Identity Operator for Linux & Hybrid Active Directory

This GitHub repo is a powerhouse collection of AI APIs you can start using immediately to ship real products — from LLM tools to computer vision and agents. One of the most valuable AI API lists on GitHub.

Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for prompt injection, jailbreaks and secret/PII leaks.

Unofficial guide to the gpt image 2 api: access via OpenAI, OpenRouter or kie.ai, pricing, parameters, gotchas.

Use GPT-6-Astra from local Codex for free - no paid plan, no API key, just a signed-in prism.openai.com session

Prompts for GPT Image 2.5, written against the capability areas in OpenAI's announcement — each shipped with the image it actually produced.

Implementation of the procedure in Language Models Can Control Their Own Attention, from Namgyu Ho et al. of KAIST AI

The universal AI agent engine for PHP. Tools, memory, guards, and a ReAct loop already built. Works with Laravel, Symfony, WordPress, Drupal, Magento, Joomla, OpenCart, PrestaShop. Any LLM provider. Zero framework deps in core. MIT.

Explorations into Survival Reinforcement Learning, proposed by Tiofack et al. of Inria earlier this year

把小爱音箱接入任意 OpenAI 兼容大模型：多音箱隔离、网页管理、语音切模型、保存即生效、多架构 Docker 镜像

Live Benchmark for long Horizon tool using Agentic Systems

一键诊断并修复 Codex / ChatGPT 桌面版「正在重新连接 1/5 → 5/5」| The Codex Rust backend ignores the Windows system proxy unless respect_system_proxy = true

Unofficial DLSS 5 Neural Rendering filter for OBS Studio. runs NVIDIA DLSS 5 NR (NGX feature 18) on any video source (Game Capture, Media Source, Webcam, …) with a Default / Natural / Cinematic style selector

网页版登录态 → OpenAI 兼容本地反代：DeepSeek / Qwen / Doubao 免费额度驱动 ZCode。Web login → OpenAI-compatible local API.

For following a line of research that augments attention with a differentiable stack, beginning with DuSell et al. at ETH Zurich

Fast, typed, calibrated evaluations for LLM and agent outputs, powered by Jev — with simple, framework-agnostic Python APIs

gpt realtime examples: environment check, model picker and a docs fetcher for the OpenAI realtime voice models.

Self-hosted multi-model agent with JitRL memory, auditable council runs, SSH operations, live server screen, and macOS/Windows desktop client

LangChain.js 中文入门电子书 · 9 章 38 个可运行示例。本书适合：会 JavaScript / TypeScript，但没接触过 LangChain；想用 JS/TS 构建 AI 应用：聊天机器人、知识库问答、智能体……；希望边读边跑代码，而不是只看理论。另有 VitePress 站点：https://cleversnail.github.io/lang-chain-js-cn/

OpenAI-compatible bridge for OpenCode free-tier models — no account required

ИИ под названием Vortex для любых задач. Сейчас уже доступна рабочая версия проекта, которая ежедневно улучшается

Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.

A system prompt against AI sycophancy, backed by 42 sources on why models tend to agree with you.

Portable offline AI assistant for SAP/ABAP learning, code drafting, debugging, and development planning. Runs locally with lightweight models, streaming responses, personal note retrieval, and optional GPU acceleration.

MorrowCache — skip the chat call when the question is the same. OpenAI-compatible proxy. npm: @kushalicious/jevcache

inertia-ai: a desktop workspace for AI agents. Chat, built-in tools, MCP and OpenAPI integrations, Docker/Daytona sandboxes with a live desktop, routines and memory. Bring your own model and keys.

New bio inspired AI

Codex 官方插件中文市场：自动同步 openai/plugins · 无损汉化(机器可证) · 每日更新 · 可视化中文导航站

100% Free, Offline, 8GB RAM Computer-Artificial Intelligence + Formal Safety (Gate + Ledger + Council + Shadow Mode) — Free alternative to $200/mo OpenAI Operator / Perplexity Computer / ClawBot / Claude Computer

Implementation of the proposed CCBP (Continuous Continual BackProp) in Pytorch

Your favorite picture, changing with the day. Native macOS wallpaper app.

Sub2api State Guard：sub2api 插件，为 OpenAI OAuth 账号自建 x-codex-turn-state 算力票池，按模型铸票并在转发时注入，不依赖任何外部服务端

Open source release of Data Science Agents that can analyze and transform datasets as well as train and infer models to augment your data scientists.

A comprehensive reinforcement learning course covering core concepts, classical algorithms, deep RL, PPO, RLHF, DPO, GRPO, and modern AI agents through intuitive explanations, equations, analogies, and visual diagrams.

Implementation of EmbeddingGemma 2, Google DeepMind's 740M parameter multimodal embedding model, in Pytorch

迹录 Tracord ——基于本地小模型多智能体的智能旅行规划助手 / AI travel planner with local SLM multi-agents — light up visited cities on a map, log expenses with one sentence, and generate executable day-by-day itineraries from plain language.

GPT-6 Astra viral demos with receipts (original author links + traction), community projects & benchmark deep dives. English | 简体中文

Free, open-source desktop assistant for live conversations. Real-time transcription and contextual help via global shortcuts or automatic hints. No typing required.

12 个主流 Coding Agent 的 Computer Use / Browser Use 能力逆向图谱：ZCode/Codex/Claude/Cursor/MiniMax/Synara/Kimi/Qoder/Grok/Devin/Goose/MiMo——架构、工具面、安全模型与可复用源码。在线主站：https://freeall12.github.io/computer-use/

The open-source brain for personal AI agents. One agent for every user of your app, with memory, schedules, tools and approvals, on a hyperscale serverless architecture where idle agents cost only storage.

QuotaCrew for Codex - multiple accounts, quota monitoring, automatic switching and experimental conversation continuation in Codex Desktop and VS Code. Open-source Windows app.

Codex 国内使用与报错速查：安装、登录、手机号验证、终端代理、断线重连、额度用完、上下文满了。按报错原文查原因和处理步骤，每条附官方出处；含中英界面对照和 AGENTS.md 中文模板。

Eight-market data collection, quantitative analytics, technical structure, and Hermes AI forecasting system

The Electrocheck fact-checker

AI-powered website builder that uses multi-agent orchestration to generate production-ready websites from natural language prompts.

A beginner-first guide to how language and multimodal models work — from language models and Transformers to LLMs, VLMs, audio, video, and modern model families.

Meridian AI for learners: multi-agent procurement audit and RAG document Q&A (FastAPI, LangChain, Gemini, Vertex AI, Cloud Run). Code, README and deploy guide.

Community-curated workflows, rules, plugins, and guides for OpenAI dots

Tutoring material for the Introduction to AI course @ UniTS

pxchat plus 增强 | nonebot-plugin-pxchat 的增强补丁：修复稳定性问题（调用超时/上下文污染/模型过滤自动切换/长文本处理/并发加速）。关键词：pxchat plus nonebot插件 聊天插件 增强补丁。

An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.

Hands-on LangChain learning repository covering Chat Models, Prompt Templates, Chains, RAG, Agents, and Tools with practical Python examples.

LLM-led e-commerce content review with rule-based safeguards, tenant-isolated MySQL, Redis workers, and auditable publication decisions.

RaDUO turns live radio broadcasts into multilingual STT datasets for ASR research. It records stations in parallel, splits streams into clips, transcribes audio, extracts quality features, and stores searchable metadata. Includes 16 kHz mono WAVs, transcripts, station info, languages, and optional word timings.

A biological neural network, digitized and trained to play chess. Powered by the open-source fruit fly connectome (164k neurons), PyTorch, and Dopamine RL.

Compile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code. Install: npm i -g jev-compiler

Implementation of Self-Play Pretraining with Zero Data

Discover campus events, find teammates and stay connected. A bilingual full-stack app with Spring Boot, MySQL, LangGraph support and Docker Compose.

HEIMEL Intent. Realized. HEIMEL is open infrastructure for the transition from intent to consequence.

Claude & Codex usage tracker for Android: live 5-hour and weekly limits for Claude Pro/Max, Claude Code and ChatGPT Codex, with alerts, a reset planner and home-screen widgets. Free, open source, no servers.

An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.

In-flight circuit breaker & loop recovery for LangGraph, LangChain, OpenAI & Anthropic agents. Catches reasoning loops, prevents runaway LLM costs with budget hard caps, and auto-injects Reflect & Pivot prompts.

一个可复现和可控的学术论文写作工具链，用于规划和起草学术论文。它能够对引用、论点强度、行文表达以及 LaTeX 完整性进行系统性检查。A reproducible and controllable toolchain to plan, draft, and gate an academic paper draft. It performs systematic checks on citations, claim strength, prose, and LaTeX integrity.

AI digital twin and academic assistant

Persistent AI-assisted binary analysis with Ghidra, Rust, gRPC-Web, and a TanStack workbench.

Adaptive Prototype Memory: a small prototype learner benchmarked against backprop, plus a chat demo where it learns from a local LLM.

Distributed GitHub backup automation & AI telemetry platform with PostgreSQL vector indexing, live WebSockets, and LangChain incident observatory. (Proprietary / Closed-Source)

Read scientific documents in any language, with realtime translation, on any platform. / 实时翻译任何语言的科学文献，适用于任何平台。

Implementation of a transformer whose attention operates in quasimetric space

A curated list of resources, guides, tools and use cases for OpenAI Dots — always-on proactive agents (DevDay 2026). Unofficial.

Turn a statute book into Akoma Ntoso: acquisition, transcription, anchor-driven structuring, retrieval and comparison for legal text. Apache 2.0.

An MIT-derived license permitting human development while restricting AI-assisted modification and AI-assisted derivative works. Experimental, not legal advice