# labring/FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

Repository: https://github.com/labring/FastGPT
Canonical: https://ross.abutalabs.com/products/fastgpt
Homepage: https://fastgpt.io
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: nextjs, openai, llm, rag, claude, deepseek, qwen, workflow, agent, mcp
Last push: 2026-08-26T12:23:08+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 91
- inputs: {"age_days": 1287, "days_push": 7, "days_rel": 12, "gap_med": 2.0, "n_releases_24m": 149}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 29477, forks 7279 (observed 2026-08-28T04:11:53.508830+00:00)

## What it is
FastGPT is an open-source AI agent building platform built on large language models, offering out-of-the-box knowledge base (RAG) management, data processing, and visual drag-and-drop workflow orchestration. It can be self-hosted via Docker or used as a cloud service, and supports multiple LLM providers including OpenAI, Claude, DeepSeek, and Qwen.

## Use cases
- build a chatbot on my own documents
- create a knowledge base Q&A system from PDFs
- build AI agents with a visual workflow editor
- self-host a RAG platform for enterprise knowledge
- orchestrate LLM workflows without code
- add a support assistant trained on company docs
- connect AI agents to tools via MCP
- deploy a private ChatGPT alternative for my team

## When to choose
- you want a low-code/visual platform for building knowledge-base chatbots and AI agents
- you need self-hosted deployment with data privacy and enterprise features like SSO and RBAC
- you want built-in document ingestion, parsing, and hybrid retrieval out of the box
- you need to integrate with multiple LLM providers and chat platforms like WeChat, Feishu, or DingTalk

## When to avoid
- you only need a lightweight RAG library to embed in your own code rather than a full platform
- you require a fully permissive open-source license - the license is custom with commercial restrictions
- you want to build highly custom agent logic that doesn't fit a node-based workflow model
- you need a headless solution without a web UI

## Facets
- artifact type: application
- maturity: active
- function: rag, agent-framework, chatbot, workflow-automation, llm-inference, mcp, chat-interface, web-framework
- domain: artificial-intelligence, large-language-models, chatbots, self-hosted
- platform: self-hosted, cloud
- tags: knowledge-base, visual-workflow, low-code, ai-agent-builder, enterprise-ai, document-parsing, openai-compatible-api, ai-agents, retrieval-augmented-generation, knowledge-management, docker, web-server, nodejs

## Member repositories
- labring/FastGPT (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:53.508830+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:52:59.989107+00:00, confidence not recorded.
  - readme: https://github.com/labring/FastGPT (fetched 2026-08-28T04:11:53.508830+00:00, sha 9488af3a36bc)
  - homepage: https://fastgpt.io (fetched 2026-08-29T07:50:34.607606+00:00, sha 5d743bdd92b0)
  - site_page: https://doc.fastgpt.io/docs/introduction (fetched 2026-08-29T07:50:34.622698+00:00, sha 1f6f966cc6a0)
  - site_page: https://fastgpt.io/price (fetched 2026-08-29T07:50:34.617706+00:00, sha 1bf81e8c9e01)
  - site_page: https://doc.fastgpt.io/ (fetched 2026-08-29T07:50:34.620378+00:00, sha 1f6f966cc6a0)
  - site_page: https://fastgpt.io/faq (fetched 2026-08-29T07:50:34.625201+00:00, sha 76c2a3e9f40d)
- Data as of 2026-08-30T08:39:29.467469+00:00.