OSS Tanbou

FastGPT — build AI applications with knowledge bases, RAG, and visual workflows

About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
29,703
Primary language
TypeScript
License
Not determined
Repository last updated
Sep 21, 2026

Overview

FastGPT is an AI application platform centered on knowledge bases and RAG retrieval, with visual workflows, agent skills, plugins, and MCP. It supports Community self-hosting alongside cloud and commercial editions.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Turn documents into knowledge bases with hybrid retrieval and reranking

Documents across common office and text formats can be chunked, managed, searched, and reranked for RAG context.

Sources: [2][3]

Compose visual workflows with agent skills, plugins, and MCP

Conversation workflows, plugin workflows, agent skills, RPA-style nodes, and bidirectional MCP can be orchestrated visually.

Sources: [2][3]

For building both internal knowledge QA and more complex AI-agent workflows

It fits teams that want retrieval, tool use, and multi-step application logic managed in the same platform.

Sources: [2]

Review the custom additional license restrictions and commercial-edition boundary

The license restricts similar multi-tenant SaaS operation and imposes branding/copyright conditions. Do not assume standard Apache-2.0 terms.

Sources: [2][4]

Official sources

  1. [1]labring/FastGPT repository(2026-09-21)
  2. [2]FastGPT README(2026-09-21)
  3. [3]FastGPT documentation(2026-09-21)
  4. [4]FastGPT Open Source License(2026-09-21)
Supplemental curator note

FastGPT uses Apache-2.0 as a base but adds restrictions including a prohibition on operating a similar multi-tenant SaaS and requirements around logo/copyright notices. It is therefore recorded as `NOASSERTION` rather than ordinary Apache-2.0 OSS. Review Community versus Commercial edition boundaries as well.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/labring/FastGPT.git
  2. 2

    Enter the repository

    cd FastGPT
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

29,703 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
166
Open PRs
23

Development activity is still being collected.

Built with

Categories and tags

GitHub data

GitHub dataView detailed GitHub data

GitHub Topics

  • nextjs
  • openai
  • llm
  • rag
  • claude
  • deepseek
  • qwen
  • workflow
  • agent
  • mcp
Stars
29,703
Forks
7,321
Watchers
153
Open issues
145
Contributors
180
Primary language
TypeScript
License
Not determined
Repository last updated
Sep 21, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.