Open-source deep research tool that searches and reasons over private data using LLMs and vector databases.
- Stars
- 29,875
- Forks
- 7,342
- Open issues
- 148
- Last commit
- 6 hours ago
What is it?
FastGPT is a platform for building LLM-based applications, especially question-answering systems backed by a knowledge base. It handles importing and processing documents, retrieval-augmented generation (RAG) with hybrid search and reranking, and calling models from a single app.
Applications are assembled in a visual Flow editor that supports conversation and plugin workflows, agent skill orchestration, user interaction steps, and bidirectional MCP. Built-in tools cover single-point knowledge base search tests, full call-chain logs, application evaluation, and citation feedback during chats.
For operations, apps can be shared through a login-free link or embedded in a page with iframe, and conversation records can be reviewed and annotated. It can be used through the hosted cloud service or self-deployed with Docker or Sealos.
Key features
- 01Visual Flow editor for chat and plugin workflows, including basic RPA nodes.
- 02RAG knowledge bases with hybrid search and reranking.
- 03Imports TXT, Markdown, HTML, PDF, Docx, PPTX, CSV and XLSX files, plus URLs.
- 04Bidirectional MCP support and agent skill orchestration.
- 05Full call-chain logs and application evaluation for debugging.
- 06Login-free share links and iframe embedding for publishing apps.
Use cases
- Building an internal question-answering assistant over company documents.
- Creating customer support bots backed by a product knowledge base.
- Prototyping RAG pipelines and comparing retrieval results before deployment.
- Self-hosting an AI app platform that keeps data on your own servers.
Quick start
- 1
Run the official install script from the README to fetch the config files
- 2
Start FastGPT with Docker Compose
docker compose up -d - 3
Open http://localhost:3000 and log in with the default account (root / 1234) once startup completes
Things to know
- The FastGPT Open Source License does not permit offering it as a SaaS service without a commercial license.
- The repository metadata lists the license as unspecified (NOASSERTION), so check the LICENSE file before commercial use.
Topics
FAQ
- What is FastGPT?
- FastGPT is an open-source AI Agent building platform with data processing, RAG knowledge bases, and visual workflow orchestration for LLM apps. FastGPT is a platform for building LLM-based applications, especially question-answering systems backed by a knowledge base. It handles importing and processing documents, retrieval-augmented generation (RAG) with hybrid search and reranking, and calling models from a single app.
- Is FastGPT free to use? What license does it have?
- FastGPT is open source under the Other license. Check the license terms before using it in commercial products.
- Is FastGPT still maintained?
- Actively maintained. The last commit to FastGPT was on Oct 20, 2026.
- What can I use FastGPT for?
- Building an internal question-answering assistant over company documents. Creating customer support bots backed by a product knowledge base. Prototyping RAG pipelines and comparing retrieval results before deployment. Self-hosting an AI app platform that keeps data on your own servers.
- How do I install FastGPT?
- Run the official install script from the README to fetch the config files Start FastGPT with Docker Compose: docker compose up -d Open http://localhost:3000 and log in with the default account (root / 1234) once startup completes
- Where can I get FastGPT?
- The source code and installation instructions are on GitHub: https://github.com/labring/FastGPT
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A zero-code platform that generates production-style AI agents from natural-language descriptions, with built-in tools, memory and orchestration.
Unreal Engine plugin that connects games and editor tooling to LLM, image, TTS and 3D generation APIs, plus an MCP server for AI assistants.
Open-source, cross-platform AI chat client for Web, desktop and mobile that connects to OpenAI, Claude, Gemini, DeepSeek and self-hosted models.
Open-source platform for building AI-powered chat bots that connect LLMs to Slack, Discord, Telegram, WeChat, Lark, DingTalk and more.
Agent-native memory infrastructure that turns LLM agent conversations and execution into persistent, structured memory for Python and TypeScript apps.