一行命令在本机运行 Llama、Qwen、DeepSeek 等大模型。
🤖 AI 与搜索
本地大模型、AI 应用与自建搜索引擎
全部 1142🎬 影音媒体 64🖼️ 相册与图片 20☁️ 网盘与文件同步 32🔗 分享与短链 60📚 文档与电子书 43📝 笔记与 Wiki 45✅ 项目与任务 57🗓️ 办公与协作 64💬 通讯与社区 99📫 邮件 27🌐 建站与博客 45🛒 电商与财务 53📰 订阅与阅读 23🏠 智能家居与监控 26🎮 生活与娱乐 68🔐 密码与身份 15🌍 网络与代理 55🧭 面板与导航页 45📈 监控与统计 76💾 备份与归档 27🛠️ 开发与运维 104🤖 AI 与搜索 23📦 其他 71
一体化的 AI 应用：把任何文档喂给大模型并聊天，支持本地模型与多种向量库。
快速、易用的开源搜索引擎，开箱即用的容错与相关性排序。
OpenAI 兼容的本地推理服务，无需 GPU 也可运行多种模型。
User-friendly AI Interface, supports Ollama, OpenAI API.
开源的个人 AI“第二大脑”，可搜索文档与笔记并回答问题。
AI-powered search engine (alternative to Perplexity AI).
Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more.
开源的即时搜索引擎，延迟低、配置简单，Algolia 的替代。
Distributed and RESTful search engine.
Full-text search and data analytics, with fast response time for small, medium and big data (alternative to Elasticsearch).
AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypted local storage.
Personal web search engine with automatic indexing of visited websites. Supports offline local result previews, local files, multi-user handling and optional semantic search.
LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.
Peer based, decentralized search engine server.
Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI.
Tool for indexing large amounts of both documents (PDF, Word, HTML) and structured (CSV, XLS, SQL) data for easy browsing and search. It is built with investigative reporting as a primary use case.
Enterprise search platform featuring full-text search, hit highlighting, faceted search, real-time indexing, dynamic clustering, and rich document (e.g., Word, PDF) handling.
AI gateway written in Go with a unified OpenAI-compatible API for multiple LLM providers, USD cost tracking, budgets, usage analytics, guardrails, caching, and an admin dashboard.
Powerful and easily deployable Enterprise Search Server.
AI-powered meme search engine. Automatically extracts descriptions from images using vision-language models, then indexes with vector embeddings for semantic and keyword search.
Kubernetes operator for self-hosted LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API.
Hybrid search engine built for flexible deployment and real-world messy data.