Havuz

Self-hosted Chess.com alternative: Game Review for your Chess.com & Lichess games, play vs Stockfish or a friend, lessons + opening trainer,

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loa

Open-source home design and floor plan editor in Rust (a Sweet Home 3D alternative) with a built-in MCP server: your AI agent draws walls, f

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

斯坦福 CS329Z《Engineering AI Agents》中文学习站 · 35 篇论文逐段中英对照全译(2035 段/45 万字)+ 14 篇博客规范全译 + 讲义同步 | 在线阅读 cs.xuyili.com

Official plugins (Ghosts) for Cindy — source, review standards, and auto-publish to the plugin marketplace · Cindy 官方插件源码仓：欢迎提交你的插件，合入即自动上架插

🐟 大肥鱼：QQ AI 伙伴 + 小红书浏览与草稿测试版 | macOS 原生 / Windows WSL2 Web · 自定义人格 · 独立记忆 · 表情与识图生图 · Photos 图库 | QQ 可用，微信测试中，持续迭代

Proxy MCP: one server that runs Playwright, Figma, Chrome DevTools, Shopify Dev and Context7 behind a single connection - and cuts their tok

Omo Space: real AI agents at desks inside Minecraft. Hermes, Claude Code and Codex terminals on the walls, real web pages, agent players tha

Tura, coding agent’ların birden çok araç adımını tek bir runtime-managed command graph içinde çalıştırarak tekrar eden LLM çağrılarını azaltmayı hedefleyen açık kaynak bir agent runtime harness’tir.

Neden yükseliyor · 83 günde 644 yıldız ve son 28 günde 18 commit dikkat çekiyor; token tasarrufu vaadini karşılaştırmalı benchmark’larla desteklemesi de ilgiyi artırmış olabilir. Ancak son 28 gündeki 2 farklı yazar, katkı tabanının hâlâ sınırlı olduğuna işaret ediyor.

Reverify, AI agent’larının reverse engineering ve kod doğrulama iddialarını deterministik araçlarla sınayan, CLI ve MCP server sunan bir Python aracıdır.

Neden yükseliyor · Repo yalnızca 28 günlük olmasına rağmen 1.245 yıldıza ve son 28 günde 83 commit’e ulaşmış; AI agent’ları için doğrulanabilir çıktı ihtiyacıyla MCP entegrasyonu dikkat çekmiş olabilir. Dört farklı yazarın katkısı aktiviteyi destekliyor, ancak yıldızlar tek başına benimseme veya kalite kanıtı değil.

LLM2Jev, yerel language model’leri Jev uyumlu yapılandırılmış karar modelleri gibi kullanmaya yarayan bir Python aracıdır.

Neden yükseliyor · Sekiz günde 342 yıldız ve son 28 günde 25 commit dikkat çekiyor; README’deki JevBench ve gecikme sonuçları da ilgi çekebilir, ancak bu ölçümler proje tarafından raporlanmış ve bağımsız doğrulama bilgisi verilmemiş.

JevChat-Windows, Windows’taki sohbet penceresini yakalayıp yerel OCR ile mesajları okuyan ve bulut modellerinden yanıt önerileri alıp bunları elle gönderilmek üzere giriş alanına dolduran bir yardımcı uygulamadır.

Neden yükseliyor · 6 günlük yaşına karşılık 599 yıldız, son 28 günde 60 commit ve 4 farklı yazar dikkat çekiyor. Bu, erken ilgi ve aktif geliştirme işareti; ancak yükselişin nedeni veya gerçek kullanıcı benimsemesi verilen ölçümlerden doğrulanamıyor.

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.

Aiden — an autonomous AI agent and work engine built solo. It can operate your browser, terminal, files, apps, APIs, skills and tools, remem

LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.

A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use

ParseBench - A Document Parsing Benchmark for AI Agents

Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly,

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, a

FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs

pi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you

Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with defau

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-awa

Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows ·

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from

LLMInternSkill: LLM internship resume and job-search Codex Skill for resume polish, JD tailoring, evidence guard, interview grilling, and Pr

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Interactive desktop app with 58 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compr

A vLLM-inspired inference engine for looped transformers, with loop-level scheduling and execution across composable stages

⚒️ Open-source game wiki template. Astro + Cloudflare Pages. Free, fast, beginner-friendly. Static-first, zero-JS, AI-native content workflo

Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host)

ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuous

Wemux - self-hostable AI agent collaboration platform (Apache-2.0, community edition)

llama.cpp fork that abliterates at inference

Curated collection of AI agent skills for Hermes and other agent frameworks

Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthrop

User friendly GUI for configuring and launching llama.cpp

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and

Console is a private, native Android app for your self-hosted Hermes Agent: chat that shows the agent's work, voice, bots and rooms, cron, t

VS Code extension for a self-maintaining personal wiki — the LLM summarizes, cross-references, and files every source for you

EduAgent: Open-Source RAG AI Tutor for K-9 Education. 国内首个专为1-9年级量身定制的开源 RAG AI 教辅智能体

Self-hosted AI buddy with visible memory: personal AI agent + Pi coding-agent workspace for any browser, phone or WeChat. 自托管私人 AI 助理：记得你，能办

Chat with local and cloud AI

核弹，椅子，瘫坐！DSH新预设模式“工程模式”，只需要你说出“请帮我完成一个机械臂”，你的AI模型靠内部的工作流，按照要求完成对应机械的设计，完全实现“AI设计机械，无需人工干预”的场景！(测试版本：SW ：2025 DSH:0.2.2 rc1 ）（如果您对此项目感兴趣，请加

剧流 Studio：开源 AI短剧生成 / AI短剧工作台，支持 LLM、视觉理解、生图、图生视频、配音、字幕与视频剪辑。Open-source AI short drama and video workflow studio.