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
FareedKhan-dev
Apache-2.0 C99 inference engine that runs the 2.78T-parameter Kimi K3 on a CPU in 8.24 GB of RAM by streaming a 1.56 TB checkpoint — byte-identical output at every memory budget, from 8 GB to 224 GB.
arcships
Apache-2.0 offline OCR for Node.js and C++ — PP-OCRv6 with Core ML, Vulkan, and D3D12 acceleration, plus a bundled PDF renderer and model in one npm install with no runtime downloads.
livekit
Apache-2.0 Python framework for realtime voice AI agents — mix any STT, LLM, and TTS behind one session loop with transformer-based turn detection, telephony, MCP tools, and a built-in test harness.
tirth8205
MIT-licensed Tree-sitter code graph that serves AI coding tools blast-radius-scoped context over MCP, with published token-reduction benchmarks and one-command setup across 15+ platforms.
superlinked
Apache-2.0 self-hosted inference engine serving 100+ open models — embeddings, rerankers, OCR, extraction, safety, and generation — behind one OpenAI-compatible API and a full Terraform/Helm production stack.
PrimeIntellect-ai
Prime Intellect's MIT-licensed self-improving coding agent, built on a persistent IPython REPL where subagents are function calls and daemon-backed sessions survive terminal disconnects.
magicrew
Go CLI that turns PDFs, Office files, scans, and screenshots into AI-ready Markdown through your own OpenAI-compatible vision model, with no required OCR stack.
MrNeRF
Native C++/CUDA workstation that unifies 3D Gaussian Splatting training, real-time inspection, gaussian editing, and export, with Python plugins and MCP automation.
QuintinShaw
Rust local-first speech-to-text engine unifying 30 ASR models across 16 families behind one CLI, with a signed model catalog and a fail-closed no-silent-upload design.
QwenAudio
A full-duplex realtime voice runtime from Alibaba's Tongyi speech team that keeps you talking to your existing coding agent — OpenCode, Claude Code, Codex — while it runs tasks in the background.
H-EmbodVis
A vision-language-action model that drops the LLM from the middle of the VLA pathway, hitting 97.7% on LIBERO with 0.2B parameters, 31.2 ms latency and 0.9 GB of VRAM on an RTX 4090.
Zyphra
Zyphra's open-weight MoE text-to-speech model trained on 6M+ hours across 34 languages, with emotion direction vectors that shift prosody without changing the cloned voice's identity.