Awesome Chatgpt

Everything you need to know to build your own RAG application

A live stream development of RL tunning for LLM agents

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

A system for agentic LLM-powered data processing and ETL

Malwoverview is a first response tool for threat hunting across VirusTotal, Hybrid Analysis, URLHaus, Polyswarm, Malshare, Alien Vault, Malpedia, Malware Bazaar, ThreatFox, Triage, IPInfo, Shodan, AbuseIPDB, GreyNoise, URLScan.io, Whois/RDAP, NIST, and VulnCheck. Supports LLM enrichment, IOC extraction, YARA scanning, and Android analysis.

Harness LLMs with Multi-Agent Programming

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)

A series of large language models developed by Baichuan Intelligent Technology

OpenAgents - The collaboration OS for AI agents

SoTA LLM for converting natural language questions to SQL queries

一键将音视频转化为小红书/公众号/知识笔记/思维导图/视频字幕等各种风格的文档。

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.

A simple, easy-to-hack GraphRAG implementation

Claraverse is a opesource privacy focused ecosystem to replace ChatGPT, Claude, N8N, ImageGen with your own hosted llm, keys and compute. With desktop, IOS, Android Apps.

Easiest and laziest way for building multi-agent LLMs applications.

中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

LeanCTX — Context Gateway for AI Systems. Control what your AI can see. Open-source Engine for context selection, supported controls, and evidence.

A ~9M parameter LLM that talks like a small fish.

[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

A service that can convert ChatGPT on the web to OpenAI API format.

SOTA search powered LLM

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Doctor Dignity is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

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🎙️、Vue 生态搭建前端🍍、FastAPI 搭建后端🗝️、Docker-compose 打包部署🐋

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Power CLI and Workflow manager for LLMs (core package)

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

A collection of scientific methods, processes, algorithms, and systems to build stories & models.

A persistent workspace for development work that self-improves and continues beyond one session.

Interact with your SQL database, Natural Language to SQL using LLMs

Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Run PyTorch LLMs locally on servers, desktop and mobile

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

The open-source AI workbench for scientific research

Evaluation and Tracking for LLM Experiments and AI Agents

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

An open source implementation of OpenAI's ChatGPT Code interpreter

Seamlessly integrate LLMs into scikit-learn.

A LLM based research assistant that allows you to have a conversation with a research paper

Seamlessly integrate LLMs into scikit-learn.

The platform for LLM evaluations and AI agent testing