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.
760 projects
Google Chrome DevTools
Google's official Apache 2.0 MCP server that gives coding agents the full Chrome DevTools surface — performance traces with CrUX field data, source-mapped console and network inspection, and Puppeteer-driven automation. Works with Claude Code, Antigravity, Cursor, Codex, Copilot, and any MCP client.
Jesse Vincent / Prime Radiant
MIT-licensed agentic skills framework that gives Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Copilot CLI a TDD-enforced, spec-driven, subagent-orchestrated software development methodology. Distributed via the official Anthropic plugin marketplace.
Shanghai AI Laboratory (InternLM)
Shanghai AI Lab's Apache 2.0 LLM toolkit centered on the C++ TurboMind engine. v0.13.0 adds TurboQuant KV cache, Qwen3.5 MoE on Blackwell, Anthropic-compatible endpoints, and prefill-starvation fixes. Supports NVIDIA, Ascend, ROCm, Cambricon, and Apple Maca.
LightSeek Foundation
MIT-licensed speed-of-light LLM inference engine from the LightSeek Foundation, targeting TensorRT-LLM performance with vLLM usability. 9 to 11 percent faster than TensorRT-LLM on Kimi K2.5 on Nvidia B200. MLA kernel already adopted by vLLM.
JD.com
JD.com's Apache 2.0 inference engine for LLMs, VLMs, DiT, and recommendation models, optimized for Huawei Ascend, Cambricon MLU, MThreads MUSA, and Nvidia CUDA. Production-validated across JD Retail's customer service and recommendation workloads.
antirez
Salvatore Sanfilippo's MIT-licensed local inference engine for DeepSeek V4 Flash, in pure C with Metal, CUDA, and ROCm backends. Asymmetric 2-bit quantization fits the model in 96 GB. 11.7k stars in under three weeks.
NVIDIA Labs
NVIDIA Labs open-source infrastructure for long autoregressive video generation. Apache 2.0, NVFP4 W4A4 quantization, balanced sequence parallelism, multi-shot training, 1.3B-5B models reaching 45.7 FPS quantized.
Presenton
Open-source self-hostable AI presentation generator under Apache 2.0. Brings-your-own-key support for OpenAI, Gemini, Claude, Bedrock, Ollama. Editable PPTX/PDF output and Electron desktop apps. 6.4k stars.
Lum1104
MIT-licensed plugin that converts any codebase into an interactive knowledge graph with Tree-sitter parsing plus LLM semantic analysis. Works with Claude Code, Cursor, Codex, OpenCode, and Gemini CLI. 21k+ stars.
Nari Labs
1.6B-parameter open dialogue TTS from Nari Labs generating two-speaker English conversation with non-verbal cues (laughs, sighs) in a single pass. Apache 2.0, runs on a single RTX 4090 in 4.4 GB.
k2-fsa
Apache-2.0 zero-shot multilingual TTS with the broadest language coverage in open source — 600+ languages, voice cloning, voice design, and 40x real-time inference on NVIDIA, Apple Silicon, and Intel Arc.
Microsoft
Microsoft's MIT-licensed open frontier voice AI: 1.5B long-form TTS up to 90 minutes with 4 speakers, 0.5B streaming TTS at 300 ms latency, and 7B ASR for 60-minute single-pass transcription. 47k+ stars.