LLM 模型排行

IRIS is an android app for interfacing with GGUF / llama.cpp models locally.

[NeurIPS'25, ICLR'26] Graph Foundation Model for Retrieval Augmented Generation

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.

💬 🚀 告别繁琐命令行，用自然语言驱动专业级渗透测试。 ⚡ 让安全测试从未如此简单、高效。Forget complex command lines. 🛡️ Professional penetration testing, powered by natural language.

Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS

💻一款简洁实用轻量级的本地AI对话客户端，采用Tauri2.0和Next.js编写 A simple, practical, and lightweight local AI chat client, written in Tauri 2.0 & Next.js.

Chat with documents (pdf, docx, txt) using ChatGPT and Langchain

A Test Project for a Network Security-oriented LLM Tool Emulating AutoGPT

Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)

A set of lessons aimed at anyone learning LLM and generative AI concepts, with sections on operations and security, as well as development.

A Repo to store the Google Colaboratory Notebooks that I have created and shared

🔍 DiscovAI-Search: An AI-powered search engine for AI tools and custom data. Built with Next.js, OpenAI, Supabase, and more. Features vector-based search, Redis caching, and LLM-powered responses.

A structured prompt pipeline that turns vague ideas into implementable RFCs — works with any AI assistant.

An extension for oobabooga/text-generation-webui that enables the LLM to search the web

A simple Python program to implement the search-extract-summarize flow.

Autonomous Engineering

An AI agent that reads your PDFs and draws editable mind maps — visible tool-calling loop, built-in RAG, bring-your-own-key, multi-provider (OpenAI / Claude / DeepSeek / Kimi). Self-hostable.

Open-source AI agent that brings the power of open models directly into your terminal.

使用社交软件聊天记录结合向量数据库让AI更好的扮演对方的角色，在不微调模型的情况下可以达到可观的效果。把曾经的美好，续成往后的陪伴。

The official TypeScript/Node client for the Pinecone vector database