Composable building blocks to build Llama Apps

Compressing Large Language Models using Low Precision and Low Rank Decomposition

Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"

AirLLM 70B inference with single 4GB GPU

𝙏𝙪𝙧𝙣𝙞𝙣𝙜 𝙨𝙢𝙖𝙡𝙡 𝙩𝙖𝙨𝙠 𝙙𝙚𝙨𝙘𝙧𝙞𝙥𝙩𝙞𝙤𝙣𝙨 𝙞𝙣𝙩𝙤 𝙢𝙚𝙜𝙖 𝙥𝙧𝙤𝙢𝙥𝙩𝙨 𝙖𝙪𝙩𝙤𝙢𝙖𝙜𝙞𝙘𝙖𝙡𝙡𝙮.

openperplex is an opensource AI search engine

Integrate cutting-edge LLM technology quickly and easily into your apps

Your Automatic Prompt Engineering Assistant for GenAI Applications

Lightweight library for scraping web-sites with LLMs

Structured Text Generation

A modular graph-based Retrieval-Augmented Generation (RAG) system

Enjoy the magic of Diffusion models!

Fast Multimodal LLM on Mobile Devices

A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.

Robust recipes to align language models with human and AI preferences

A language for constraint-guided and efficient LLM programming.

A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

A UI-Focused Agent for Windows OS Interaction.

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

We write your reusable computer vision tools. 💜

All things prompt engineering

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Python scraper based on AI

Automate browser-based workflows with LLMs and Computer Vision

Real-time face swap for PC streaming or video calls

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.