Scripts2026年3月31日·1 分钟阅读

AnythingLLM — All-in-One AI Knowledge Base

All-in-one AI app: chat with documents, RAG, agents, multi-user, and 30+ LLM/embedding providers. Desktop + Docker. Privacy-first, no setup needed. 57K+ stars.

TO
TokRepo精选 · Community
快速使用

先拿来用，再决定要不要深挖

这里应该同时让用户和 Agent 知道第一步该复制什么、安装什么、落到哪里。

Desktop app (easiest): Download from anythingllm.com — macOS, Windows, Linux.

Docker (self-hosted):

docker run -d -p 3001:3001 \
  -v anythingllm:/app/server/storage \
  mintplexlabs/anythingllm

Open http://localhost:3001, choose your LLM provider, and start chatting.

介绍

AnythingLLM is an all-in-one AI productivity app. Upload documents (PDF, DOCX, TXT, web pages) and chat with them using RAG. Supports 30+ LLM providers (OpenAI, Anthropic, Ollama, local models), 15+ embedding engines, and 10+ vector databases. Includes AI agents with tool use, multi-user workspaces, and a built-in API. Privacy-first with on-device processing. 57,000+ GitHub stars, MIT licensed.

Best for: Teams and individuals who want a private ChatGPT + document Q&A without complex setup Works with: OpenAI, Anthropic, Ollama, LM Studio, Google, Azure, Groq, Together, Perplexity

Key Features

Document Chat (RAG)

Upload any file and ask questions. Supports PDF, DOCX, TXT, CSV, audio, video, web pages, and GitHub repos.

30+ LLM Providers

OpenAI, Anthropic Claude, Ollama (local), LM Studio, Azure, Google Gemini, Groq, Together, Perplexity, and more.

AI Agents

Built-in agents with web browsing, code execution, file management, and RAG search tools.

Multi-User Workspaces

Create separate workspaces with different documents and permissions. Role-based access control.

Desktop App

Native desktop application — no Docker or terminal needed. Download and run.

Privacy-First

  • Documents processed locally (no data sent to cloud unless you choose a cloud LLM)
  • Full offline mode with Ollama
  • Self-hosted Docker deployment

Developer API

Full REST API for embedding AnythingLLM into your own applications.

FAQ

Q: What is AnythingLLM? A: An all-in-one AI app for chatting with documents, RAG, AI agents, and multi-user workspaces. Supports 30+ LLM providers. 57K+ GitHub stars, MIT licensed.

Q: Can I use it fully offline? A: Yes, pair AnythingLLM with Ollama for a completely offline setup — no internet required after initial model download.

🙏

来源与感谢

Created by Mintplex Labs. Licensed under MIT. Mintplex-Labs/anything-llm — 57,000+ GitHub stars

相关资产

Jina Reader — Convert Any URL to LLM-Ready Text

Convert any URL to clean, LLM-friendly markdown with a simple prefix. Just prepend r.jina.ai/ to any URL. Handles JS-rendered pages, PDFs, and images. 10K+ stars.

TokRepo精选

Bolt.new — AI Full-Stack Web App Generator

Prompt, run, edit, and deploy full-stack web apps in the browser. AI generates code, installs packages, runs dev server, and deploys — all from a chat interface. 16K+ stars.

TokRepo精选

Claude Engineer — Interactive AI Dev CLI

Interactive CLI powered by Claude for software development. Self-generating tools, file operations, web search, code analysis, and project management. 11K+ stars.

TokRepo精选
◈首页🏆Trending👤我的