Top AI Project by Categories

🐚 OpenDevin: Code Less, Make More

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

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Building a quick conversation-based search demo with Lepton AI.

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Private & local AI personal knowledge management app.

A UI-Focused Agent for Windows OS Interaction.

The open source platform for AI-native application development.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

Automate browser-based workflows with LLMs and Computer Vision

Composio equips agents with well-crafted tools empowering them to tackle complex tasks

Large Action Model framework to develop AI Web Agents

SGLang is a fast serving framework for large language models and vision language models.

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

🚀 KIMI AI 长文本大模型逆向API白嫖测试【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、长文档解读、图像OCR、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Blazingly fast LLM inference.

Start building LLM-empowered multi-agent applications in an easier way.

Efficient Triton Kernels for LLM Training

Supabase for RAG - Build and scale production-ready user facing AI apps

Implementation for MatMul-free LM.

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

Multilingual Voice Understanding Model

🔍 AI search engine - self-host with local or cloud LLMs

✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.

Run PyTorch LLMs locally on servers, desktop and mobile

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️

基于大模型的智能对话客服工具，支持微信、千牛、哔哩哔哩、抖音企业号、抖音、抖店、微博聊天、小红书专业号运营、小红书、知乎等平台接入，可选择 GPT3.5/GPT4.0/ 懒人百宝箱 （后续会支持更多平台），能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业 AI 应用。

Turn any webpage into structured data using LLMs

Master Any Code: One-Click Comments and Language Conversion. 掌握任何屎山代码：一键注释和语言转换。💪

Wren AI makes your database RAG-ready. Implement Text-to-SQL more accurately and securely.

Easy token price estimates for 400+ LLMs. TokenOps.

Text-To-Speech, RAG, and LLMs. All local!

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

In-browser Postgres sandbox with AI assistance

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

LM Studio CLI. Written in TypeScript/Node

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Tensor parallelism is all you need. Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

Help your LLMs online

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Library to build personalized AI powered by what you've seen, said, or heard. Works with Ollama. Alternative to Rewind.ai. Open. Secure. You own your data. Rust.

Open-source alternative to Assistant's API with a managed backend for memory, RAG, tools and tasks. ~Supabase for building AI agents.

An open-source, high-performance SQL vector database built on ClickHouse.

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

LLM powered fuzzing via OSS-Fuzz.

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

Evaluate your LLM's response with Prometheus and GPT4 💯

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

A lightweight multilingual SOTA LLM

MobiLlama : Small Language Model tailored for edge devices

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

An intuitive approach to building with LLMs

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

DataChain 🔗 AI-dataframe to enrich, transform and analyze data from cloud storages for ML training and LLM apps

Fully-featured, beautiful web interface for Ollama LLMs - built with NextJS. Deploy with a single click.

Code2Prompt is a powerful command-line tool that simplifies the process of providing context to Large Language Models (LLMs) by generating a comprehensive Markdown file containing the content of your codebase. ⭐ If you find Code2Prompt useful, consider giving us a star on GitHub! It helps us reach more developers and improve the tool. ⭐

A personal wearable AI that runs locally

Generate music based on natural language prompts using LLMs running locally

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3

🍦 ChatTTS-Forge is a project developed around the TTS generation model ChatTTS, implementing an API Server and a Gradio-based WebUI.

A Framework of Small-scale Large Multimodal Models

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Efficient AI Inference & Serving

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

structured extraction for llms

[ACL 2024] Progressive LLaMA with Block Expansion.

AI Powered Search and Chat for Orgs - Think ChatGPT meets Google Search but powered by your data.

A library for making RepE control vectors

Create characters in Unity with LLMs!

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Hackable open-source version of Anthropic's AI Artifacts chat

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

Video Search and Streaming Agent 🕵️‍♂️

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

Control Any Computer Using LLMs

Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed Up Responses, and Ensure Non-Stop Reliability.

Stateful load balancer custom-tailored for llama.cpp

Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

Mac compatible Ollama Voice

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

Galah: An LLM-powered web honeypot.

Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.

A 4-hour coding workshop to understand how LLMs are implemented and used

🤖 Free Search with AI, 💡 Open-Source Perplexity, 📍 Support Ollama/SearXNG, Support Docker deployment. 让AI大模型和搜索引擎回答你的问题，支持本地大模型(Ollama)、聚合搜索引擎SearXNG，支持Docker一键部署。

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models