Undrum

gpt4free

The official gpt4free repository | various collection of powerful language models

bloop

bloop is a fast code search engine written in Rust.

bark

🔊 Text-Prompted Generative Audio Model

mini-agi

MiniAGI is a simple general-purpose autonomous agent based on the OpenAI API.

milvus

A cloud-native vector database, storage for next generation AI applications

StableLM

StableLM: Stability AI Language Models

OpenBB

Investment Research for Everyone, Everywhere.

SdPaint

Stable Diffusion Painting

pretty-ts-errors

🔵 Make TypeScript errors prettier and human-readable in VSCode 🎀

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

AutoGPT.js

Auto-GPT on the browser

ChatGDB

Harness the power of ChatGPT inside the GDB or LLDB debugger!

AgentGPT

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

tabby

Self-hosted AI coding assistant

wenda

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

chroma

the AI-native open-source embedding database

so-vits-svc

SoftVC VITS Singing Voice Conversion

llama.cpp

LLM inference in C/C++

opentau

Using Large Language Models for Repo-wide Type Prediction

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

TaskMatrix

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

gpt4all

GPT4All: Chat with Local LLMs on Any Device

pygpt4all

Official supported Python bindings for llama.cpp + gpt4all

baize-chatbot

Let ChatGPT teach your own chatbot in hours with a single GPU!