High-Quality Voice Cloning TTS for 600+ Languages

Write HTML. Render video. Built for agents.

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

This repository contains demos I made with the Transformers library by HuggingFace.

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

bluetooth mesh chat, IRC vibes

IPFS HTTP Gateway daemon in Go, tuned for public production traffic: retrieval only, no pinning, no providing

Lavaplayer fork maintained by Lavalink

Standalone audio sending node based on Lavaplayer.

Portal is a quick and easy command-line file transfer utility from any computer to another 🌌 ✨

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

List of ngrok, Cloudflare Tunnel, Tailscale, and ZeroTier alternatives and other tunneling software and services. Focus on self-hosting.

A simple command-line utility to send messages to Telegram

🔊 High-precision web player for multi-device audio playback and spatial audio.

real time face swap and one-click video deepfake with only a single image

MinIO is a high-performance, S3 compatible object store, open sourced under GNU AGPLv3 license.

Nim is a statically typed compiled systems programming language. It combines successful concepts from mature languages like Python, Ada and Modula. Its design focuses on efficiency, expressiveness,…

telegram-cli

Run frontier AI locally.

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claud…

Generative models for conditional audio generation

Voilà, install macOS on ANY Computer! This is really and magic easiest way! PVE 7.XX ~ 8.XX Support and macOS High Sierra ~ macOS Sequoia Support.

Robust Speech Recognition via Large-Scale Weak Supervision

The LoRaMesher library implements a distance-vector routing protocol for communicating messages among LoRa nodes.

The HTML5 Creation Engine: Create beautiful digital content with the fastest, most flexible 2D WebGL renderer.

Javascript Canvas Library, SVG-to-Canvas (& canvas-to-SVG) Parser