Havuz

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Local, real-time system-audio captioner + translator for macOS — Whisper + a local LLM + a glass overlay. Fully offline.

Give AI hands to touch silicon — an MCP server for SEGGER J-Link, OpenOCD and Black Magic probes. Flash, halt, step, stream RTT logs and dec

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

Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token

🐟 闲鱼/Goofish 智能监控控制台：AI 大模型选品 + 收藏降价·售罄即时提醒，全本地运行不外传。Xianyu second-hand deal monitor — LLM-filtered picks, price-drop & sold-out alerts, dea

Self-hosted AI agent that builds apps. Chat with a coding agent (Claude Code or Codex) that builds mini-apps, modifies its own UI, and gets

Open-source local AI Agent desktop app for authorized security assessment — Electron + Mastra-powered runtime, visual pentest workflow, Kali

Open, MIT-licensed food, nutrition & agricultural science research skills for Claude Code, Codex, MiniMax Agent, OpenClaw & Grok Build — mul

Review code changes by intent, learn the concepts behind the changes, and optionally quiz yourself or your code reviewer before merging the

Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix Halo

MCP server + prompt that turns any AI coding agent (Cursor, Claude Code, Cline, Kiro, Windsurf…) into your Digital Twin — generate a project

Cross platform GLM proxy for AutoClaw's Zhipu AI models. Provides OpenAI-compatible Chat Completions and Anthropic Messages APIs for Claude

Let Jev read every new arXiv paper each morning and surface the few you should read. Plain-English interests, calibrated probabilities, ~$0.

187 plug-and-play AI agent personas em Português brasileiro — tradução do agency-agents + 3 originais do mercado brasileiro (PIX/Mercado Liv

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Automatic, model-driven permission review for OpenCode

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

Guia extenso sobre o Maestri: +257 templates de partitura em 12 áreas, documentação, dicas e recursos para reger times de agentes de IA. Par

SEO Content Engine for LLMs - generate, rewrite, and audit content against 49 ranking factors with multilingual support.

Autonomous YouTube AI agent: LLM script, TTS voice, stock clips, FFmpeg editing, AI thumbnail, auto-upload — 100% free, Telegram-controlled.

Research Math Agents, Official code release for our paper RMA

DeepSeek Harness bundle: the AgentRouter relay as one pi-ai route with a domestic/international endpoint switch, plus the outbound request c

Cross-harness communication mesh for LLM agents, with rooms, direct messages, presence and visibility over TCP and no filesystem dependencie

Referee report on your economics paper before a real referee sees it — verified comments and a revision plan your agents implement. Agent Sk

Official codebase for the paper "Sharpening Tax in Post-Training"

AI 学习辅导 · Claude Code Skill 套件：根据上传的教材/课件按章节学习，适用于考研、期末、资格考试——思维导图 / 讲义 / 真题风格试卷 / 错题本 / 费曼检验 / 掌握度仪表盘，进度跨会话保存

AI Business OS: multi-agent platform with RAG, OCR, speech & workflow automation. FastAPI + LangGraph + Celery + Flutter. Production-grade,

Static-analysis-based dataset for training LLMs to detect, explain, and patch security vulnerabilities (Java, Korean/English annotations, ve

Impulse by Velocity: run AI models on your own computer, on Windows and Linux. Load any GGUF model and chat with web search, files, charts a

Click-and-go SMB, HTTP, UDPBD & UDPFS, Retro Achievements, LAN servers for PlayStation 2 Homebrew! Easy to use GUI + Edge version for route

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

Press a key, speak, text lands at your cursor. Press another, get a spoken answer. Local-first, lightweight voice dictation and assistant fo

Let AI Agents control your real firefox browser: fill forms, authenticate, automate actions, web development; all via token-efficient, easy

An automated, multi-turn LLM red-teaming pipeline that pits an Attacker model against a Target model to evaluate safety boundaries, featurin

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）

A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro archit

MetAPI Go rewrite — meta-layer management and unified proxy for AI API aggregation platforms

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python

On-demand .NET runtime diagnostics for live CoreCLR apps — no code changes. Ships an MCP server (let an LLM drive the investigation), a stan

RigMark benchmarks local AI the way coding agents actually use it.

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it te

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig

Windows tag editor for LoRA / character image datasets: booru tag editing with Chinese UI & translation, WD14/PixAI/CL ONNX auto-tagging, LL

DSH 插件:直接复用 Codex CLI 本地登录订阅凭证,在 DeepSeek Harness 中使用 ChatGPT 订阅模型,无需 API Key | DSH plugin: reuse your Codex CLI local subscription login to

Lightweight, async multi-agent framework with native SQLite persistence and handoffs for WhatsApp, Telegram, Webhooks, and CLI. Production-h

train your own chatbot from scratch on a mac

Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.