Stars
Compilation of high-profile real-world examples of failed machine learning projects
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Robust Speech Recognition via Large-Scale Weak Supervision
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
Voice + Vision powered AI assistant that answers questions about any application, in context and in audio.
A Python interface for reinforcement learning environments
Easily migrate your codebase from one framework or language to another.
Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app
Interact with your documents using the power of GPT, 100% privately, no data leaks
🐫 CAMEL: Finding the Scaling Law of Agents. A multi-agent framework. https://www.camel-ai.org
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
High-performance In-browser LLM Inference Engine
Universal LLM Deployment Engine with ML Compilation
Official supported Python bindings for llama.cpp + gpt4all
openhubgpt / open-access-gpt
Forked from cogentapps/chat-with-gptAn open-source alternative to ChatGPT using OpenAI APIs with your API key. Privacy-first, serverless, use online or install locally.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
New ways of breaking app-integrated LLMs
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Building Startups with an AI Co-Founder
A set of type stubs for popular Python packages. These are works in progress from the Microsoft Python team and others, with the intent that they are contributed to typeshed or to the associated pa…