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.

FastGPT – An Open‑Source AI‑Agent Building Platform

What it is – FastGPT is a self‑hostable web platform that lets you assemble AI agents, chat‑bots and RPA‑style workflows without writing code. It bundles data‑pre‑processing, model‑calling, knowledge‑base (RAG) support and a visual Flow editor for arranging “skills” and plugins into complex applications.

Core capabilities

Area What FastGPT provides
Application orchestration Visual Flow editor; supports Agent‑Skill pipelines, conversational and plugin workflows, basic RPA nodes, two‑way multi‑channel communication (MCP).
Debug & testing Single‑point knowledge‑base search test, reference feedback that can be edited/deleted during a chat, full call‑chain logs, app‑level evaluation tools.
Knowledge‑base (RAG) Multiple reusable vector stores, chunk edit/delete, manual input or automatic chunking, import from TXT, MD, HTML, PDF, DOCX, PPTX, CSV, XLSX, URLs, CSV bulk import; mixed retrieval & re‑ranking; API‑exposed KB.
Plugins Hot‑reload of system tools; roadmap includes hot‑reload for RAG modules, agent loops and real‑time AI generation plugins.
Operations Shareable no‑login UI windows, one‑click iframe embed, unified conversation history with annotation, operational logs.

How to get started

  1. One‑click Docker install – run the provided script to fetch a docker-compose.yml and start the service:
    bash <(curl -fsSL https://doc.fastgpt.io/deploy/install.sh)
docker compose up -d
    The UI becomes available at http://localhost:3000 (default credentials root / 1234).
  2. Cloud SaaS – if you prefer not to self‑host, a hosted version is available at fastgpt.io.
  3. Self‑host alternatives – besides Docker you can deploy with Sealos Cloud for a one‑click cluster setup.
  4. Commercial edition – offers extra features and dedicated support; licensing details are linked in the docs.

Ecosystem & integrations

  • FastGPT‑plugin repository for extending the platform with custom tools.
  • AI‑Proxy (labring/aiproxy) – a model‑aggregation load‑balancer that FastGPT can call.
  • Sealos – the underlying Kubernetes‑style deployment system used for cloud/cluster installs.
  • Third‑party services such as TokenDance (unified AI API gateway) and SiliconCloud (online model demo) are listed as compatible.

Community & contribution

  • Open issues and pull‑requests are welcomed; contribution guidelines are in the repo.
  • A Feishu (Chinese Slack‑like) group is provided for real‑time discussion.
  • Contributor statistics are displayed via OSS Insight widgets.

License – FastGPT uses the FastGPT Open Source License which permits commercial backend use but forbids offering the software as a SaaS product without a separate commercial agreement. Full terms are in LICENSE.

All information above is taken directly from the repository’s README; no external assumptions have been added.

Related

  • Project
    Significant-Gravitas/AutoGPT

    AutoGPT is an AI-powered platform that lets you manage a team of specialized agents to automate recurring professional tasks like content creation, research, and administrative work.

  • Project
    arc53/DocsGPT

    DocsGPT is an open‑source, self‑hosted platform that turns your documents, sites and connected apps into AI agents. It supports any OpenAI‑compatible model, provides cited answers, visual workflow building, extensive data connectors, team‑level SSO/quotas, and can be accessed via a web UI, widget, API or chat‑bot integrations.

  • Project
    JoshuaC215/agent-service-toolkit

    A comprehensive toolkit for building and deploying AI agents using LangGraph, FastAPI, and Streamlit, providing a complete template from agent logic to user interface.

  • Project
    melih-unsal/DemoGPT

    DemoGPT is an open-source framework that automatically generates LangChain code and Streamlit apps from user instructions and provides a library of tools for building AI agents with RAG capabilities.

  • Project
    appleboy/CodeGPT

    CodeGPT is a Go‑based CLI that uses LLM APIs (OpenAI, Azure, Gemini, Anthropic, Ollama, Groq, OpenRouter, LiteLLM) to auto‑generate Conventional‑Commit messages and short code‑review summaries. It installs a Git `prepare‑commit‑msg` hook, supports many providers, proxy settings, language translation, streaming output, and a flexible prompt/template system. Install via Homebrew, Chocolatey, an install script, pre‑compiled binary, or `go install`. Configure API keys (or dynamic helpers), choose models, and customize prompts. Ideal for developers who want AI‑assisted commit messages and quick reviews directly from the terminal.