FastGPT
A platform for building AI knowledge bases, agents and question-answering apps, with RAG retrieval and a visual workflow editor, from the Sealos team.
What is FastGPT?
FastGPT lets you load documents into knowledge bases, test retrieval, and build chat apps, agents and plugin workflows in a visual editor with RPA nodes, user interaction steps and MCP in both directions. Answers show the passages they cite, which you can correct, and every call is logged for debugging and evaluation. It is popular in China, and the documentation is mostly in Chinese, with English and other translations available.
Good fit if
- You build internal Q&A bots over company documents and want a visual workflow editor.
- You want to inspect and fix citations and retrieval quality.
Before you adopt it
The FastGPT Open Source License is Apache 2.0 with added conditions, so it is not open source by the OSI definition. Running a multi-tenant SaaS like FastGPT, or removing its logo and copyright from the console, requires a commercial license from Sealos. A self-hosted setup runs about 14 containers, including PostgreSQL, MongoDB, Redis and MinIO.
Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction
FastGPT health: is it still maintained?
82 of 100, actively developed
Read from GitHub on 1 November 2026. How the score works
FastGPT license: is it open source?
FastGPT uses FastGPT Open Source License. It is source-available, not an OSI-approved open-source license: the code is public, but the license restricts how you may use it, usually commercially.
- February 2023First published on GitHub.
- TodayFastGPT Open Source License.
How to run FastGPT yourself
- Docker
- Dockerfile or compose file in the repository
- Compose file
- deploy/dev/docker-compose.yml: 14 services (postgres, mongodb, redis, minio)
- Setup effort
- 4 of 5, judged from the compose file
- Kubernetes
- No Helm chart in the repository
- Desktop and mobile
- No app builds in GitHub releases
- Interface languages
- 3 languages
Install instructions: fastgpt.io or the README on GitHub.
Alternatives to FastGPT
- LobeHubLobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and… 73 health · LobeHub Community License · 83.7k stars
- vLLMA high-throughput and memory-efficient inference and serving engine for LLMs 84 health · Apache-2.0 · 96k stars
- Open WebUIUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) 76 health · Open WebUI License · 157k stars
- LibreChatEnhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API,… 74 health · MIT · 46.6k stars
- OllamaGet up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. 89 health · MIT · 186k stars
Questions about FastGPT
Is FastGPT open source?
Not by the OSI definition. FastGPT uses FastGPT Open Source License, which makes the code public but restricts how it may be used.
Is FastGPT still maintained?
Its health score is 82 of 100 (actively developed). It had 552 commits in the last 90 days, the latest on 1 November 2026, and its latest release came out on 9 October 2026.
How do I run FastGPT?
You can run it with Docker. The README on GitHub has the exact steps.
What are the alternatives to FastGPT?
Close alternatives in the AI chat & local LLMs category include LobeHub, vLLM, Open WebUI.