Projects

• 🧠 AI Agent

  • OpenDevin
  • AgentQL
  • Agent Protocol
  • Devon - source pair programmer
  • PR-Agent - Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More!
  • FinRobot - Source AI Agent Platform for Financial Applications using LLMs
  • Translation Agent
  • Devika - level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective.
  • AgentQL
  • Aider
  • AgentGPT
  • *Devin - bench coding benchmark.
  • Plandex
  • AgentQL
  • Husky - Source Language Agent for Multi-Step Reasoning
  • DigiRL - The-Wild Device-Control Agents with Autonomous Reinforcement

• 🦄 LLMs

  • Granite Code Models 3b,8b,20b,34b - source code models: A Family of Open Foundation Models for Code Intelligence
  • OpenChat - source Language Models with Imperfect Data
  • Awesome-Chinese-LLM
  • llama3
  • Qwen 1.8B,7B,14B,72B
  • Hunyuan-DiT - Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
  • GLM-4-9B - 4 series: Open Multilingual Multimodal Chat LMs
  • AutoCoder - 4 Turbo (April 2024) and GPT-4o.
  • mPLUG-DocOwl
  • WizardLM - Trained Language Models to Follow Complex Instructions
  • Snowflake Arctic - MoE Hybrid transformer architecture pre-trained from scratch by the Snowflake AI Research Team. Taking an average of Coding (HumanEval+ and MBPP+), SQL Generation (Spider), and Instruction following (IFEval).
  • Grok-1 - 1 is a 314 billion parameter Mixture-of-Experts model trained from scratch by xAI.
  • Mistral
  • DBRX - purpose LLM created by Databricks.
  • CodeGemma-7b
  • DeepSeek-V2-Chat - of-Experts Language Model
  • MiniCPM-V 2.0 - side MLLM with Strong OCR and Understanding Capabilities
  • Stable Audio Open 1.0 - length (up to 47s) stereo audio at 44.1kHz from text prompts.
  • Nemotron 4 340B
  • Fish Speech V1.2 - to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.
  • Phi-3 family - 3 family of small language and multi-modal models. Language models are available in short- and long-context lengths.
  • Gemma 2 - in-class performance, runs at incredible speed across different hardware and easily integrates with other AI tools.

• 🗣️ Voice

  • Whisper - Scale Weak Supervision
  • VoiceCraft - Shot Speech Editing and Text-to-Speech in the Wild.
  • Parler-TTS - TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc).
  • ChatTTS
  • StreamSpeech
  • CosyVoice - lingual large voice generation model, providing inference, training and deployment full-stack ability.
  • *Vall-E
  • ElevenLabs
  • Krisp
  • Voicemod - time voice changer and soundboard available on both Windows and macOS.
  • *NaturalSpeech 3 - Shot Speech Synthesis with Factorized Codec and Diffusion Models.
  • Sounds
  • VIVA
  • Dream Machine

• 🌄 Image

  • *PIXART-Σ - to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation.
  • ResAdapter - and-play resolution adapter for enabling diffusion models of arbitrary style domains to generate resolution-free images: no additional training, no additional inference and no style transfer.
  • FaceChain - learning toolchain for generating your Digital-Twin.
  • APISR - World Anime Super-Resolution (CVPR 2024)
  • OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models - concept image generation
  • DesignEdit - Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing.
  • MagicClothing - driven image synthesis.
  • *IntrinsicAnything
  • IC-Light - Light is a project to manipulate the illumination of images.
  • MistoLine - ControlNet Model for Adaptable Line Art Conditioning
  • InstaDrag - based Image Editing Emerging from Videos
  • Omost
  • Hallo - Driven Visual Synthesis for Portrait Image Animation
  • UniAnimate
  • MimicBrush - shot Image Editing with Reference Imitation
  • SketchDeco
  • LivePortrait
  • IMAGDressing
  • PaintsUndo
  • VAR - style models beyond diffusion & Scaling laws observed.
  • DALL-E
  • Stable Diffusion - to-image model.
  • Midjourney - E and Stability AI's Stable Diffusion.
  • StickerBaker - source tool that allows users to create stickers using AI technology.
  • BasicPBC
  • Ideogram - to-use AI tool that generates realistic images, posters, logos and more.
  • HeyBeauty
  • Logo Diffusion
  • Tensor.Art
  • AutoStudio - turn Interactive Image Generation

• 🧸 3D Model

  • TripoSR - forward 3D generative model developed in collaboration between Stability AI and Tripo AI.
  • Era3D - Resolution Multiview Diffusion using Efficient Row-wise Attention.
  • AIUNI
  • MeshFormer - Quality Mesh Generation with 3D-Guided Reconstruction Model
  • Unique3D - Quality and Efficient 3D Mesh Generation from a Single Image.
  • *Make-It-Vivid
  • DiffTF - Vocabulary 3D Diffusion Model with Transformer
  • DreamMat - quality PBR Material Generation with Geometry- and Light-aware Diffusion Models
  • PantoMatrix
  • *CAT3D - View Diffusion Models
  • *OccFusion

• 🎥 Video

  • *Emote Portrait Alive
  • AniPortrait - Driven Synthesis of Photorealistic Portrait Animations
  • MuseV - length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising.
  • CameraCtrl - to-Video Generation.
  • OpenVoice
  • AniTalker - Decoupled Facial Motion Encoding
  • EasyAnimate - to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion.
  • MusePose - Driven Image-to-Video Framework for Virtual Human Generation
  • MASA
  • MimicMotion - Quality Human Motion Video Generation with Confidence-aware Pose Guidance
  • Video-Infinity - Infinity generates long videos quickly using multiple GPUs without extra training.
  • DiffSynth Studio
  • SAM 2
  • MotionClone - Free Motion Cloning for Controllable Video Generation
  • *Sora
  • Runway
  • HeyGen
  • Pika - to-video platform that sets your creativity in motion.
  • *VASA-1 - Driven Talking Faces Generated in Real Time.
  • Veo
  • Pandora
  • V-Express - Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.
  • Hedra - generated videos and video components.

• 🕸️ Search Engine

  • Perplexica - powered search engine. It is an Open source alternative to Perplexity AI
  • Reor
  • Phind
  • Devv
  • Perplexity
  • Arc

• 👩🏽‍💻 Develop Assistant

  • Transformer Debugger
  • CopilotKit - app AI chatbots, in-app AI Agents, & AI-powered Textareas.
  • Tabby - hosted AI coding assistant
  • Melty - ready code.
  • CodeRabbit
  • GitHub Copilot - based suggestions in real time.
  • Codium

• 🤼 Multi-Agent Collaboration

  • MetaGPT
  • TransAgents - Agent for Translating Ultra-Long Literary Texts
  • ChatDev - to-use, highly customizable and extendable framework, which is based on large language models (LLMs) and serves as an ideal scenario for studying collective intelligence.

• 💻 Terminal

  • Gorilla - line interactions with a user-centric tool.
  • Open Interpreter
  • Warp - powered assistance for command lookups and allow users to input their objectives in plain English
  • CodeWhisperer Cli - style completions for hundreds of popular CLIs like as Git, npm, Docker, MongoDB Atlas, and the AWS CLI. Previously known as [fig](https://fig.io/).

• 📰 Web Sites

  • Design2Code - End Engineering
  • OpenUI
  • Dora
  • Tempo - quality react code directly in your codebase so you can ship UIs in minutes.
  • v0

• 🗜️ Hardware

  • insight
  • OpenGlass - powered smart glasses
  • LeRobot - to-end Learning for Real-World Robotics in Pytorch
  • *LOOI Root
  • Limitless
  • Frame AI glasses - source eyewear.
  • Rabbit R1
  • *Haptic Source-effector - body Haptics via Non-invasive Brain Stimulation
  • Octo - based robot policy trained on a diverse mix of 800k robot trajectories.
  • HumanPlus
  • Ray-Ban Meta Smart Glasses - Ban Meta collection combines the latest in wearable tech with authentic Ray-Ban design, to keep you connected wherever you go.
  • Solos AirGo Vision

• ⌨️ Prompt Engineering

  • Prompt-Engineering-Guide
  • Prompt Library

• 🤯 LLMs Inference and Serving

  • vLLM - throughput and memory-efficient inference and serving engine for LLMs.
  • Text Generation Inference
  • Ollama
  • LM Studio

• 📋 Others

  • Cradle - improvment, and skill curation, in a standardized general environment with minimal requirements.
  • LLMPerf - project/llmperf-leaderboard) for LLMs.
  • WebLINX - world website navigation with multi-turn dialogue.
  • HippoRAG - term memory that enables LLMs to continuously integrate knowledge across external documents.
  • Deep-tempest
  • Great Tables
  • ComfyUI
  • Gauth
  • Latent Box - lists for AI, creativity and art.
  • Vanna - licensed open-source Python RAG (Retrieval-Augmented Generation) framework for SQL generation and related functionality.
  • LLM Transparency Tool - TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models.
  • LLM Visualization
  • Rewind
  • Cursor
  • Raycast
  • Gamma

• 🎵 Music

  • Jamboss - length songs.
  • Haimian Music - generated music product by ByteDance, delivers superior vocal quality in both Chinese and English.
  • Suno
  • Udio

• 💬 ChatBot

  • Gemini
  • ChatGPT - to-use AI system. Use it for engaging conversations, gain insights, automate tasks, and witness the future of AI, all in one place.
  • character.ai
  • Claude
  • Mistral AI - made AI to all the builders.

• 🏆 Benchmarks Leaderboard

  • open_llm_leaderboard
  • LMSys Chatbot Arena Leaderboard
  • META Leaderboard
  • LLM-Perf Leaderboard - Benchmark and Optimum flavors.
  • Big Code Models Leaderboard - E.
  • Open ASR Leaderboard
  • Toolbench Leaderboard
  • OpenCompass 2.0 LLM Leaderboard - tier large language models and multimodal models.
  • Open Ko-LLM Leaderboard
  • Occiglot Euro LLM Leaderboard - translated into the four main languages from the Okapi benchmark and Belebele (French, Italian, German and Spanish).
  • BigCodeBench Leaderboard