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
Screenpipe (YC S26)
Y Combinator S26 open-source local AI memory daemon that continuously transcribes audio via local Whisper, OCRs the screen, and indexes everything into a searchable SQLite store. MIT, 18k+ stars.
TypeWhisper
Open-source on-device speech-to-text for macOS supporting WhisperKit, Parakeet TDT v3, Apple SpeechAnalyzer, and local Gemma 4 post-processing. System-wide dictation with per-app workflows. GPL-3.0.
Zackriya Solutions
Privacy-first AI meeting assistant in Rust with 4x faster Parakeet/Whisper live transcription, Sortformer speaker diarization, and Ollama-powered local summaries. MIT, 12k+ stars.
Anthropic
Anthropic's official, curated GitHub repository of Claude Code plugins. Browse and install commands, agents, skills, and MCP servers directly inside Claude Code via /plugin > Discover.
HKUDS (Hong Kong University of Data Science)
Open-source framework from HKUDS that auto-generates CLIs for any GUI software so AI agents can control Blender, GIMP, Ollama, ComfyUI, and 30+ apps natively. Apache 2.0, 38k+ stars.
colbymchenry
Pre-indexed local code knowledge graph that gives Claude Code, Codex, Cursor, and OpenCode agents 35% cheaper, 70% fewer-tool-call queries via MCP. MIT licensed, 19+ languages, 100% offline.
HKUDS (Hong Kong University of Data Science)
Open-source agentic video generation framework with Director, Screenwriter, Producer, and Video Generator agents. Turns ideas, scripts, or entire novels into long-form AI video. MIT licensed.
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.
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.
NVlabs
NVIDIA Labs' open-source framework for high-resolution image and video generation with linear diffusion transformers and 32x latent compression.