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.
886 projects
resemble-ai
Resemble AI's open-source TTS family with zero-shot voice cloning from seconds of audio, a low-latency Turbo model, and 23+ language multilingual synthesis (MIT).
OpenBMB
OpenBMB's efficient multimodal LLM series that runs image and video understanding on phones — MiniCPM-V 4.6 hits GPT-4V-class quality at just 1.3B params (Apache-2.0).
m-bain
A fast open-source ASR pipeline on top of Whisper: word-level timestamps via forced alignment, 70x realtime batched inference, and speaker diarization (BSD-2).
bradautomates
An MIT-licensed /watch command that lets an AI agent 'watch' any video — captions first, then yt-dlp + ffmpeg frame extraction and Whisper fallback — grounding answers in what's actually on screen.
stanfordnlp
Stanford NLP's framework for programming — not prompting — language models: declare tasks as typed Python modules and let optimizers auto-tune prompts, few-shot examples, and weights (MIT).
huggingface
Hugging Face's open-source voice-agent pipeline (VAD -> STT -> LLM -> TTS) exposed through an OpenAI Realtime-compatible WebSocket API, with every component swappable and self-hostable (Apache-2.0).
iOfficeAI
Apache-2.0 Office suite built for AI agents — read, edit, and automate Word, Excel, and PowerPoint from a single dependency-free binary, with a built-in HTML/PNG rendering engine that lets agents visually verify output.
stablyai
Open-source Agentic Development Environment (ADE) that runs Codex, Claude Code, OpenCode, and Pi in parallel — each in its own git worktree — with a mobile companion, on macOS/Windows/Linux (MIT).
browser-use
MIT-licensed open-source pipeline that edits videos through a coding agent — drop in raw footage, chat with Claude Code, and get a finished cut with filler-word removal, color grading, subtitles, and animation overlays.
baaivision
BAAI's open multimodal suite that tokenizes image, text, and video into one discrete space and trains a single transformer with pure next-token prediction — generation and perception, no diffusion or CLIP (Apache-2.0).
pyannote
The de facto open-source speaker diarization toolkit — PyTorch-native "who spoke when" pipelines with state-of-the-art pretrained models on Hugging Face, fine-tunable on your own data (MIT).
facebookresearch
Meta FAIR's library of efficient, reusable, GPU-accelerated components for 3D deep learning — batched mesh/point-cloud data structures, differentiable operators, and a differentiable renderer for PyTorch (BSD).