Trending Projects

A Python library for easy and robust visual localization using deep learning and feature matching.

A comprehensive course on Transformers, a powerful deep learning framework for NLP tasks.

ReAct is a framework that synergizes reasoning and acting in large language models for decision-making.

AI-powered tool to convert audio/video into various document formats like notes, mind maps, and subtitles

Pointcept is a codebase for point cloud perception research, featuring the latest works on 3D computer vision.

PersonaLive! is a Python-based tool for creating expressive portrait image animations for live streaming.

A fast and simple implementation of learning algorithms for robotics in Python.

A Python library for building AI agents that learn from experience using the Agentic Context Engineering framework.

AIMedia is an AI-powered content creation and publishing platform for popular social media channels.

A comprehensive list of papers, code, and resources related to NeRF and 3D Gaussian Splatting for SLAM/Robotics applications.

A community-maintained hardware plugin for running large language models (LLMs) on Ascend accelerators.

A research paper on representation alignment for training diffusion models for AI-assisted code generation.

A comprehensive collection of the best research papers on multi-agent systems and swarm intelligence.

g4f provides free access to multiple LLMs and media-generation models with Python and JS clients, Docker support, and APIs.

A browser automation framework and ecosystem for vibe coders.

Real-time face swap for PC streaming or video calls

Deep learning tutorial for image processing with PyTorch and TensorFlow2

Curated list of open source libraries for deploying, monitoring, and scaling machine learning in production

Open-source semantic layer for AI, BI, and embedded analytics

An open-source toolkit for training intelligent agents using deep reinforcement learning and imitation learning in Unity games and simulations.

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

A PDF version of the renowned MIT Deep Learning Book, a comprehensive resource for studying machine learning and neural networks.

Structured Outputs is a Python library focused on building generative AI systems with prompts, LLMs, and symbolic AI.

A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.

NVIDIA TensorRT is an SDK for high-performance deep learning inference on NVIDIA GPUs.

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities.

Official implementation of the paper 'Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection'.

A curated list of awesome tools and projects for the LangChain framework, a popular AI development toolkit.

A Spring-based framework for building AI-powered applications and services.

An open-ended embodied agent with large language models for exploring and learning in Minecraft environments.

An open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Agent Laboratory is an end-to-end autonomous research workflow to assist human researchers in implementing their ideas.

Highly performant CUDA-accelerated library for gaussian splatting, useful for AI and computer vision applications.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments using MuJoCo.

Zep is a Python library that provides examples, integrations, and tools for working with large language models (LLMs).

Lightweight Python framework for building autonomous AI agents with memory and exploration capabilities.

A nearly-live implementation of OpenAI's Whisper, a powerful speech recognition and translation tool.

Demystify AI agents by building them yourself with no black boxes, real understanding of function calling, memory, and ReAct patterns.

Comprehensive roadmap to become skilled in AI, ML, data science, and more from scratch.

A data platform for context engineering, enabling agents to store, observe, and learn from context data.

A lightweight and generalist NER model for extracting entities from text, with support for prompt-tuning.

Family fitness app with AI health coaching, food tracking, and self-hosted deployment.

A Java library for scraping brand mentions, rankings, and competitor intelligence from the Perplexity AI platform.

An open-source tool to transcribe and summarize video content using AI, supporting multiple languages.

HY-Motion is an AI-powered 3D character animation generation model for developers building with AI tools.

A tutorial series for developers to learn how to use large language models (LLMs) from zero to hero.

An open-source audio wake word detection framework with a focus on performance and simplicity.

A comprehensive survey of self-evolving AI agents, bridging foundation models and lifelong agentic systems.

An open-source library for efficiently connecting and optimizing teams of AI agents.

A TypeScript library for a voice activity detector (VAD) with a simple API for the browser.