Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
- huggingface
- inference
- llm
- mechanistic-interpretability
140,194 visible repositories in the index
73–96 of 145 · Most stars
Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
talkie is a vintage language model from 1930
Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.
Your AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer, multi-agent Command Center(Deep Work), and 7-layer security. Anthropic, OpenAI, or Ollama.
open-source skill that learns any brand and turns it into a complete design system. works on claude code and codex. install once, every UI your assistant builds matches your brand.
🌙 ZetaLib - The only AI Library you need
🧠 Motorhead is a memory and information retrieval server for LLMs.
AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知
A talking LLM that runs on your own computer without needing the internet.
A comprehensive SEO audit command-line tool with 332 audit rules across 20 categories. Analyze any website for SEO best practices, Core Web Vitals, security headers, structured data, accessibility, and more.
Diffusion-based Portrait and Animal Animation
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
这是一个基于SpringBoot和Telegrambot-Api的多功能Telegram群管机器人,Powered By DeepSeek And Google Cloud Vision。
Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
Port of OpenAI's Whisper model in C/C++ with xtts and wav2lip
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
KaliGPT: an Agentic AI (built with Gemini, ChatGPT, Ollama, OpenRouter Models) fine tuned for ethical hackers & students in offensive security making workflows smarter, faster, and more accessible.
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
Samples showing how to build Java applications powered by Generative AI and LLMs using Spring AI and Spring Boot.
Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.