Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace. Discover projects across categories like LLM, Vision, Audio, and more.
489 projects
PlayCanvas
Free, open-source browser-based editor for 3D Gaussian Splats. Inspect, edit, optimize, and publish photoreal 3D captures with zero install. Built by PlayCanvas, MIT licensed.
Alibaba Cloud Qwen Team
Open-source TTS series from Alibaba's Qwen team with 97ms streaming latency, 10-language support, 3-second voice cloning, and natural-language voice design. Apache-2.0 licensed.
NVlabs
NVIDIA Labs' open-source framework for high-resolution image and video generation with linear diffusion transformers and 32x latent compression.
humanlayer
A principles-based guide for production-grade LLM agents with twelve factors covering prompts, context, tools, control flow, and lifecycle.
Imbad0202
A Claude Code skill suite that runs a 10-stage human-in-the-loop academic research pipeline with multi-database reference verification.
MoonshotAI
Moonshot AI's open-weight 1T-parameter mixture-of-experts language model with 32B active parameters, 128K context, and frontier-tier benchmark scores.
OpenBMB
OpenBMB's 2B-parameter tokenizer-free TTS model with 48 kHz output, 30-language support, voice cloning, and an Apache-2.0 license.
Anil-matcha
Open-source MIT-licensed studio for AI image, video, and lip-sync generation across 200+ models with local inference and a node-based workflow runner.
fikrikarim
Apache-2.0 desktop assistant that runs real-time multimodal voice and vision AI fully on-device using Gemma 4 E2B, Kokoro TTS, and Apple MLX or LiteRT-LM backends.
RightNow-AI
MIT-licensed portable C inference engine that runs a 1B-parameter LLM on a $10 board with 256MB RAM, targeting ARM Cortex-M, ESP32, Raspberry Pi Zero, and RISC-V hardware.
raullenchai
Apache-2.0 local AI inference engine for Apple Silicon claiming 4.2x faster throughput than Ollama, 80ms cached TTFT, 100% tool calling, and a drop-in OpenAI-compatible API.
opendatalab
Production document parsing engine that converts PDFs, Office files, images, and web pages into clean Markdown and JSON for RAG and agent pipelines, with CPU, GPU VLM, and hybrid backends.