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
Open-source RAG engine combining deep document understanding with agentic capabilities to build a reliable context layer for LLMs.
Microsoft open-source quantitative investment platform using AI and LLMs for automated factor discovery, model training, and trading strategy development.
TradingAgents deploys specialized LLM-powered agents as analysts, researchers, traders, and risk managers to collaborate on market analysis and trading decisions — just like a real trading desk.
VibeVoice is a family of open-source voice AI models from Microsoft combining Text-to-Speech and Automatic Speech Recognition with 50+ language support, 60-minute audio processing, and sub-300ms real-time latency.
OpenCode is a community-driven open-source coding agent with 153k GitHub stars, offering a provider-agnostic alternative to proprietary AI coding assistants with built-in LSP support and a client/server architecture.
FinceptTerminal is a native C++20 financial intelligence platform combining AI agents with legendary investment personas (Buffett, Graham, Lynch), 100+ data connectors, and real-time trading support — 17.9K GitHub stars and growing.
Goose by Block is an Apache 2.0 general-purpose AI agent that operates natively on your machine, going beyond code suggestions to autonomously install dependencies, run tests, and commit code. Now under Linux Foundation governance.
OpenClaw is an open-source, local-first AI gateway with 366K GitHub stars that routes AI responses through WhatsApp, Telegram, Slack, Discord, iMessage, Teams, and 15+ other platforms — zero cloud dependency.
Omi is a fully open-source ambient AI system combining wearable hardware and cross-platform apps to continuously capture, transcribe, and recall personal context.
LEANN is an on-device vector database that achieves 97% storage reduction via graph-based selective recomputation, enabling private semantic search and RAG on personal hardware.
tiny-llm is a 3-week open-source course that teaches systems engineers to implement vLLM-style LLM inference serving infrastructure on Apple Silicon using only MLX primitives.
SGLang (Structured Generation Language) is a high-throughput, low-latency inference engine for large language models and multimodal models, developed by the LMSYS team. With 26,600 GitHub stars and over 12,000 commits, it has become the de facto o…