Automate development gruntwork like code reviews, patching and documentation with LLM workflows.

Install and run your own AI agent service

PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and effici…

The 𝗣𝗼𝘄𝗲𝗿𝗳𝘂𝗹 Conversational AI JavaScript Library 💬 — UI for any LLM, supporting LangChain / HuggingFace / Vercel AI, and more 🧡 React, Next.js, and plain JavaScript ⭐️

A generative speech model for daily dialogue.

A beautiful CLI dashboard for GitHub 🚀

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

🤗 LeRobot: End-to-end Learning for Real-World Robotics in Pytorch

An open-source alternative to Ngrok, designed to serve production traffic and be simple to host (particularly on Kubernetes)

Automate browser-based workflows with LLMs and Computer Vision

GPT based autonomous agent that does online comprehensive research on any given topic

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Support for bootable OS containers (bootc) and generating disk images

Private & local AI personal knowledge management app.

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

Open source ngrok alternative designed for teams. Tunnel http, tcp or websocket connections.

A Native-PyTorch Library for LLM Fine-tuning

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Control Any Computer Using LLMs

🌐 The Internet OS! Free, Open-Source, and Self-Hostable.

Detect file content types with deep learning

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

Build resilient language agents as graphs.

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

DSPy: The framework for programming—not prompting—foundation models

Modeling, training, eval, and inference code for OLMo