Logo
Deploy Now

Categories

Knowledge Base Chatbot Low-Code RAG Workflow Automation Artificial Intelligence LLM Platform

Stars

29,421

Forks

7,274

Watchers

147

Developer links

Last Updated: 08-22-2026 09:54 AM (UTC)

FastGPT

FastGPT lets you build production AI agents and knowledge base chatbots through a visual drag-and-drop workflow editor, connecting any LLM provider to your documents with retrieval-augmented generation that cites sources and reduces hallucination. The workflow canvas chains LLM calls, conditional branching, HTTP requests, code sandbox execution, and plugin nodes into complex conversation flows and agent skill pipelines without writing backend code. The knowledge base engine ingests documents in ten formats (TXT, Markdown, HTML, PDF, DOCX, PPTX, CSV, XLSX, URL scraping, and CSV batch import) then applies automatic chunking, hybrid vector retrieval with semantic reranking, and QA-pair splitting to deliver accurate, citation-backed answers. FastGPT connects to virtually any LLM provider through its AI Proxy aggregation layer: OpenAI GPT-4o, Anthropic Claude, Google Gemini, DeepSeek, Qwen, ERNIE Bot, and models hosted via Ollama all work through a unified OpenAI-compatible API. Bidirectional MCP support enables agents to call external tools and expose their own capabilities to other systems. Completed applications can be shared via login-free links, embedded as iframe widgets, or integrated with WeCom, Lark, DingTalk, and WeChat Official Accounts through the published REST API. Application operation logs, conversation annotation, and per-model usage analytics provide full lifecycle governance for compliance-sensitive deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. FastGPT Open Source License (Apache 2.0 based) licensed.

FastGPT
FastGPT
FastGPT
FastGPT

Benefits

  • Visual No-Code Workflow Builder
  • Drag-and-drop Flow editor chains LLM calls, conditional branching, HTTP requests, code sandbox execution, and plugin nodes into production-ready AI agent pipelines without writing backend code.
  • Enterprise Knowledge Base RAG
  • Ingests ten document formats with automatic chunking, hybrid vector retrieval using PostgreSQL or Milvus, and semantic reranking to deliver citation-backed answers that minimize hallucination.
  • Universal Multi-Model Support
  • AI Proxy aggregation layer connects OpenAI, Claude, DeepSeek, Qwen, Gemini, ERNIE Bot, and local Ollama models through a single unified API with load balancing and usage analytics.
  • One-Click Deployment and Sharing
  • Deploy via Docker Compose with MongoDB and vector database, then publish AI agents as shareable links, iframe widgets, or REST API endpoints integrated with WeCom, Lark, and DingTalk.

Features

  • Agent Skill Orchestration
  • Build multi-step AI agents with dialogue workflows, plugin workflows, RPA nodes, user interaction gates, and bidirectional MCP protocol support.
  • Hybrid Retrieval Engine
  • Combines vector similarity search with keyword matching and reranking models across multiple knowledge bases simultaneously for accurate context retrieval.
  • Multi-Format Document Ingestion
  • Imports TXT, Markdown, HTML, PDF, DOCX, PPTX, CSV, XLSX files and URLs with automatic segmentation, QA-pair splitting, and chunk editing.
  • OpenAI-Compatible API
  • Publishes every application as a REST endpoint following the OpenAI chat completions format for seamless integration with existing tools and services.
  • Operation Analytics
  • Tracks conversation logs, model token usage, request latency, and supports data annotation for continuous quality improvement and compliance auditing.