Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

The official repository of NodeRAG

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

A lightweight data processing framework built on DuckDB and 3FS.

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

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

🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs ggml, gguf, GPTQ,…

OpenAgents: An Open Platform for Language Agents in the Wild

An Autonomous LLM Agent for Complex Task Solving

Train transformer language models with reinforcement learning.

Converts text input or URL into knowledge graph and displays

Teaching LLMs memory management for unbounded context 📚🦙

Haystack and Mistral 7B RAG Implementation. It is based on completely open-source stack.

OpenAI's Code Interpreter in your terminal, running locally

Port of Facebook's LLaMA model in C/C++

8-bit CUDA functions for PyTorch

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Tensor library for machine learning

An open platform for training, serving, and evaluating large language model for tool learning.

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

A Python Library for Graph Outlier Detection (Anomaly Detection)

🔊 Text-Prompted Generative Audio Model

Interact privately with your documents using the power of GPT, 100% privately, no data leaks

Examples on how to use LangChain and Ray

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

Offsite-Tuning: Transfer Learning without Full Model