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
Tracer-Cloud
OpenSRE is an open-source framework for deploying AI agents that autonomously investigate production incidents, correlating signals across 40+ observability, infrastructure, and incident management integrations with full LLM provider flexibility.
xming521
WeClone is an open-source one-stop solution for creating an AI digital twin from personal chat history. Fine-tunes LLMs using LLaMA Factory with Microsoft Presidio PII filtering, multimodal (text + image) training, and deployment to Telegram, Discord, Slack, and WeChat.
Open-LLM-VTuber
Open-LLM-VTuber lets you run a customizable, voice-interactive AI companion entirely on your own hardware — no cloud required — pairing major LLMs with animated Live2D avatars, real-time speech recognition, and hands-free conversation.
bytedance
Protenix is ByteDance's fully open-source biomolecular structure prediction system that outperforms AlphaFold3 across diverse benchmark sets. The v2 release (April 2026) scales to 464M parameters with full training pipeline access under Apache 2.0.
NVIDIA
PersonaPlex is NVIDIA's open-source real-time speech-to-speech system that enables full-duplex conversation with text-defined personas and audio voice conditioning, built on the Moshi architecture with a 7B Helium LLM backbone.
shiyu-coder
AAAI 2026-accepted foundation model for financial time series forecasting, pre-trained on OHLCV candlestick data from 45+ global exchanges with a novel hierarchical tokenizer for discrete price representation.
microsoft
Lightweight Python utility from Microsoft that converts virtually any file format—PDFs, Word docs, PowerPoints, images, audio, and web pages—into clean, token-efficient Markdown for LLM integration.
OpenBMB
OpenBMB's 9B parameter multimodal model achieving Gemini 2.5 Flash-level performance on vision, speech, and full-duplex live streaming—designed specifically for on-device and edge deployment.
microsoft
Microsoft's open-source framework for training and optimizing AI agents via reinforcement learning and prompt optimization, compatible with LangChain, OpenAI SDK, AutoGen, and CrewAI.
virattt
An open-source educational multi-agent AI framework simulating a hedge fund team with 13 investor personas and 5 specialist agents for stock analysis and trading decisions.
AIDC-AI
An AI-powered fully automated short video engine by AIDC-AI that generates complete videos from a single topic input, handling script, visuals, TTS, and BGM via ComfyUI-based pipeline.
vectorize-io
Agent memory system that organizes memories biomimetically into world facts, experiences, and mental models, with multi-strategy retrieval achieving SOTA on the LongMemEval benchmark.