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
shiyu-coder
MIT-licensed decoder-only foundation model that tokenizes OHLCV candlestick data from 45+ global exchanges, with 4.1M to 102.3M parameter open checkpoints and a full fine-tuning and backtesting pipeline.
supertone-inc
On-device multilingual TTS engine with a 99M-parameter ONNX model, 31-language support, and reference runtimes for iOS, macOS, Windows, Linux, web, and Raspberry Pi class hardware.
mattpocock
Open-source Claude Code skill library from TypeScript educator Matt Pocock with 18 engineering, productivity, and meta skills that bring senior-engineer discipline to AI coding agents.
K-Dense-AI
MIT-licensed library of 135 Agent Skills covering 17+ scientific domains, 100+ research databases, and 70+ Python packages that turn Claude, Cursor, and Codex into reliable research assistants.
obra
Agentic skills framework with mandatory brainstorm, design, plan, and review gates that turns Claude Code, Cursor, and other coding agents into disciplined engineers backed by 191,000+ GitHub stars.
Stakpak
Open-source autonomous DevOps agent in Rust that runs 24/7 with mTLS, dynamic secret substitution, Warden guardrails, and a curated rule book library for safe infrastructure automation.
CopilotKit
Open-source full-stack SDK for building agent-native React and Angular apps with generative UI, shared state, and human-in-the-loop workflows. Makers of the AG-UI Protocol.
HKUDS
Open-source ultra-lightweight personal AI agent with a small readable core, multi-channel chat, memory, MCP, and support for 20+ LLM providers.
AWS Labs
AWS Labs methodology and adaptive rule set that turns any AI coding agent (Claude Code, Cursor, Copilot, Q Developer) into a disciplined SDLC-aware engineering collaborator.
VectifyAI
Vectorless, reasoning-based RAG framework that builds hierarchical document trees and lets LLM agents navigate them through reasoning instead of vector similarity.
Tauric Research
Multi-agent LLM framework from Tauric Research that simulates a trading firm with specialized analyst, researcher, trader, and risk management agents collaborating through structured debate.
tinyhumansai
Local-first open-source personal AI assistant in Rust with Memory Tree, 118+ OAuth integrations, and TokenJuice compression.