Pascal

subprocess.h. 🐜 single header process launching solution for C and C++

qwenasr.cpp. Local AI speech-to-text, powered by GGML. C++17 port of Qwen3-ASR (Qwen team, Alibaba). 30 languages and 22 Chinese dialects, any input resampled to 16 kHz mono, runs on CPU, CUDA, Vulkan, SYCL.

transcribe.cpp. ggml speech-to-text inference for 16+ model families

convert. Convert models to GGUF

ds4. DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

qwen3-tts.cpp. C++

vox-transcribe. Local-first Android voice notes with live on-device transcription, transcript cleanup, titles, and summaries powered by Nemotron ASR and Gemma. Built with Jetpack Compose and Room.

lemonade. Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

llama-install.sh. Build and install script for llama.app

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

acestep.cpp. Portable C++17 implementation of ACE-Step 1.5 AI Music Generator using GGML. Text + lyrics in, stereo 48kHz MP3 or WAV out. Runs on CPU, CUDA, ROCm, Metal, Vulkan.

lucebox. LLM speculative inference server for consumer hardware & heterogeneous computing

non-magical-csi. Exclusively non magical non radar ESP32 CSI

faster-qwen-asr. Python

qwenasr.cpp. Fast, installable Qwen3-ASR inference wrapper with CUDA-oriented backends

qwentts-cpp-python. Python bindings and wheel packaging for qwentts.cpp

magenta-realtime. Magenta RealTime 2: An Open-Weights Live Music Model

speech-to-speech. Build local voice agents with open-source models

llama-install.sh. Build and install script for llama.app

agentskills. Specification and documentation for Agent Skills

SRT. Python

moshi.cpp. Partial port of Kyutai's Moshi to C++ and ggml.

llama.cpp-realtime-audio-recap. Realtime conference audio recap for llama.cpp

llama.pages. llama.cpp's official website

wllama. WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

HOT-Step-CPP. Turn dials. Summon bangers! NOW WITH MORE C++! Local AI music generation powered by GGML

qwentts.cpp. Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of Qwen3-TTS (QwenLM/Qwen3-TTS). 10 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.

pi-mono. AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

claude-code-src.

camofox-browser. Headless browser automation server for AI agents to visit sites that are usually blocked

OmniVoice. High-Quality Voice Cloning TTS for 600+ Languages

mcp.js. Personal dev tool that exposes a local shell and filesystem to any Model Context Protocol client. Built on the official TypeScript SDK, with a custom WebSocket server transport.

Qwen3-TTS. Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Qwen3-TTS. Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

omnivoice.cpp. Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of OmniVoice (k2-fsa/OmniVoice). 646 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.

OmniVoice. High-Quality Voice Cloning TTS for 600+ Languages

camofox-browser. Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

moshi.cpp. Partial port of Kyutai's Moshi to C++ and ggml.

DCW. [CVPR 2026] Elucidating the SNR-t Bias of Diffusion Probabilistic Models

DCW. [CVPR 2026] Elucidating the SNR-t Bias of Diffusion Probabilistic Models

acestep-cpp-comfyui. ComfyUI Node for acestep.cpp

ComfyuAudioNodes-BitsAndBobs. Python

VMAVIFICIENT. Automatic AV1+OPUS encoder, with support of DV and HDR10+

Side-Step. The most powerful training scripts for ACE-Step 1.5 including a Command Line Interface, a Terminal Wizard and a Graphical User Interface.

superview.sh. See your claude code logs in clear details in your dashboard

GenieX. Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

acestep.vst3. VST3 plugin for ACE-Step 1.5 music generation. Based on acestep.cpp (C++17/GGML). Runs on CPU, CUDA, Metal, Vulkan.

deepdarkCTI. Collection of Cyber Threat Intelligence sources from the deep and dark web

ACE-Step-DAW. WIP...

huggingface_hub. The official CLI and Python client for the Hugging Face Hub.

peaqb-fast. Faster version of peaqb program, which calculates PEAQ BASIC for any sound file.

acestep-cpp-ui. 🎵 AceStep-cpp UI - 100% local and free Suno alternative powered by acestep-cpp and 0% python

ggml. Tensor library for machine learning

llama.cpp. Forked from ggerganov/llama.cpp

diffusion-to-gguf. Python

ggml-easy. Thin wrapper around GGML to make life easier

acestep.cpp-simple-GUI. Super simple GUI for use with acestep.cpp

aceradio. A C++ Qt graphical user interface for generating music using acestep.cpp

sdmod32. PIC32 SD Card Amiga MOD Music Player

multiwii-firmware. Firmware - GitHub mirror of the official SVN multiwii project

hackrf_android. A ported version of Michael Ossmann's libhackrf library to use with Android 3.1+

anyterm. Anyterm qui compile sous Debian Jessie avec libboost-dev et zlib1g-dev

RFAnalyzer. Spectrum Analyzer for Android using the HackRF

cleanflight. Clean-code version of the baseflight flight controller firmware

rtl_433. Application using librtlsdr to decode the temperature from a wireless temperature sensor (433.92MHz)

MAVProxy. MAVLink proxy and command line ground station

term.js. A terminal written in javascript.

distance-to-line-segment. JavaScript module to calculate the closest distance between a point and a line segment

line-simplify-rdp. JavaScript module to simplify lines (polygons) using the Ramer–Douglas–Peucker algorithm

SiK. Tools and firmware for the Si1000

LIDAREnhanced. Driver for the LIDARLite v2 and v3 on the Arduino, with many improvements over the base library (Robustness, asynchronous acquisition, higher acquisition frequency, state machine, maintained)

jsmpeg. MPEG1 Video Decoder in JavaScript

PIC32-avrdude-bootloader. The 'new' bootloader for MPIDE/chipKIT PIC32 boards

visio. Ultra fast live streaming raw h264 from Raspberry Pi to multiple browser clients with Node, websockets and Broadway

avc2ts. H264 encoder and mpeg transport stream encapsulator

jquery-spoiler. Minimal, lightweight jQuery spoiler plugin

RTIMULib. RTIMULib makes it easy to use 9-dof IMUs with embedded Linux systems (especially the Raspberry PI!)

v4l2tools. V4L2 tools using V4L2 C++ wrapper

pigpio. pigpio is a C library for the Raspberry which allows control of the General Purpose Input Outputs (GPIO).

FFmpeg. Mirror of git://source.ffmpeg.org/ffmpeg.git

nocode. The best way to write secure and reliable applications. Write nothing; deploy nowhere.

Mediainfo-Template. Mediainfo Custom Template Example

Olaf. Olaf: Overly Lightweight Acoustic Fingerprinting is a portable acoustic fingerprinting system.

mnemophonix. A simple audio fingerprinting system

diff-challenge. Is this even possible?

meshtastic-map. A map of all Meshtastic nodes heard via MQTT.

firmware. Meshtastic device firmware

meshtastic-d3js. A D3.js Vector Nodes Map for Meshtastic-Map Database or Others

bark.cpp. Suno AI's Bark model in C/C++ for fast text-to-speech generation

v0-system-prompts-and-models.

whisper.cpp. Port of OpenAI's Whisper model in C/C++

sd-forge-fluxtools-v2. Flux.1 Tools For Forge WebUI

sd-forge-deforum. Deforum extension for stable-diffusion-webui-forge

mcp. Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

llamahtml. LLamaHTML is a simple html file to communicate with a running llamacpp llama-server

mcp-client. An MCP client for Node.js.

web-search-mcp. A simple, locally hosted Web Search MCP server for use with Local LLMs

browser-control-mcp. MCP server paired with a browser extension that enables AI agents to control the user's browser.

qwen600. Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

delayed-streams-modeling. Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

neutrino. the neutrino core, cross mcu pio template

trae-agent. Trae Agent is an LLM-based agent for general purpose software engineering tasks.

MiniModel.

fastllm. fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

sre. The Operating System for Agents

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

qwen-code. Qwen Code is a coding agent that lives in the digital world.

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

codex. Lightweight coding agent that runs in your terminal

moshi. Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

llamactl. Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.

TheBigPromptLibrary. A collection of prompts, system prompts and LLM instructions

unmute. Make text LLMs listen and speak

mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >70% on SWE-bench verified!

cpp-mcp. Lightweight C++ MCP (Model Context Protocol) SDK

XLeRobot. XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

fastmcp. A TypeScript framework for building MCP servers.

spec-kit. 💫 Toolkit to help you get started with Spec-Driven Development

paddler. Open-source LLM load balancer and serving platform for self-hosting LLMs at scale 🏓🦙

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

chat-ui. Open source codebase powering the HuggingChat app

llama-swap. Model swapping for llama.cpp (or any local OpenAI API compatible server)

llama.ui. A minimal interface for AI Companion that runs entirely in your browser.

exa-mcp-server. Exa MCP for web search and web crawling!

xterm.js. A terminal for the web

jellyfin. The Free Software Media System - Server Backend & API

fred. the UI and agentic backend of the fred innovation track

freakwan. A floor-routing WAN implementing a chat over bare-LoRa (no LoRaWAN).

stable-diffusion.cpp. Stable Diffusion and Flux in pure C/C++

llama.vim. Vim plugin for LLM-assisted code/text completion

opencode. The open source coding agent.

gopher-mcp. MCP C++ SDK - Model Context Protocol implementation in CPP with enterprise-grade security, visibility and connectivity.

gitea. Git with a cup of tea! Painless self-hosted all-in-one software development service, including Git hosting, code review, team collaboration, package registry and CI/CD

clawdbot. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

flux2.c. Flux 2 image generation model pure C inference

ACE-Step-1.5. The most powerful local music generation model that outperforms most commercial alternatives

ggml. Tensor library for machine learning

MeshCore. A new lightweight, hybrid routing mesh protocol for packet radios

llama.cpp. LLM inference in C/C++

acestep.cpp. Portable C++17 implementation of ACE-Step 1.5 music generation using GGML. Text + lyrics in, stereo 48kHz WAV out.

acestep.cpp. Portable C++17 implementation of ACE-Step 1.5 music generation using GGML. Text + lyrics in, stereo 48kHz WAV out.

ggml. Tensor library for machine learning

acestep.cpp. Portable C++17 implementation of ACE-Step 1.5 AI Music Generator using GGML. Text + lyrics in, stereo 48kHz MP3 or WAV out. Runs on CPU, CUDA, ROCm, Metal, Vulkan.

ace-step-ui. 🎵 The Ultimate Open Source Suno Alternative - Professional UI for ACE-Step 1.5 AI Music Generation. Free, local, unlimited. Stop paying for Suno!

ACE-Step-1.5. The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

freakwan. A floor-routing WAN implementing a chat over bare-LoRa (no LoRaWAN).

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

iris.c. Flux 2 image generation model pure C inference

llama.vim. Vim plugin for LLM-assisted code/text completion

fred. Production-ready platform for building, deploying, and operating AI and agentic applications

codexica. HTML

xterm.js. A terminal for the web

test-jinja. Jinja

exa-mcp-server. Exa MCP for web search and web crawling!

geometric-coincidence. A Geometric Coincidence: How a Deterministic Global Phase Model Reproduces the CHSH Value Through Trigonometric Averaging

paddler. Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

Cartographie-et-localisation. Ce module propose une introduction pratique aux principes de cartographie (mapping) et de localisation 2D dans le cadre d’un robot mobile équipé d’un Lidar LD06 et d'un microcontrôleur ESP32.

XLeRobot. XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

browser-control-mcp. MCP server paired with a browser extension that enables AI agents to control the user's browser.

use-mcp. TypeScript

fastmcp. A TypeScript framework for building MCP servers.

chat-ui. The open source codebase powering HuggingChat

spec-kit. 💫 Toolkit to help you get started with Spec-Driven Development

llamactl. Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.

trae-agent. Trae Agent is an LLM-based agent for general purpose software engineering tasks.

mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

zed. Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

PhaseHound. Lightweight modular SDR runtime in pure C

moshi. Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

codex. Lightweight coding agent that runs in your terminal

MeshCore. A new lightweight, hybrid routing mesh protocol for packet radios

qwen-code. An open-source AI coding agent that lives in your terminal.

sre. The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

deskflow. Share a single keyboard and mouse between multiple computers.

llama.cpp. LLM inference in C/C++

diff-challenge. Is this even possible?

koboldcpp. Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Sunshine. Self-hosted game stream host for Moonlight.

fastllm. fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

MiniMeshT. Terminal chat client compatible with Meshtastic firmware

MiniModel. Python

delayed-streams-modeling. Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

unmute. Make text LLMs listen and speak

llama.ui. A minimal interface for AI Companion that runs entirely in your browser.

contact. A curses-based console UI for Meshtastic, providing mesh chat, and device configuration from the terminal.

neutrino. the neutrino core, cross mcu pio template

SGFX. Universal display for lib

ACE-Step. ACE-Step: A Step Towards Music Generation Foundation Model

llamahtml. LLamaHTML is a simple html file to communicate with a running llamacpp llama-server

llama.cpp.mcp. LLM inference in C/C++

simplex-chat. SimpleX - the first messaging network operating without user identifiers of any kind - 100% private by design! iOS, Android and desktop apps 📱!

ezoterikus. a chat

qwen600. Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

LibreChat. Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active

tfjs. A WebGL accelerated JavaScript library for training and deploying ML models.

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

CryptSIS. CryptSIS is an encryptor/decryptor working with different Cipher depending on the version.