Back to directory

FastGPT

An AI agent building platform with out-of-the-box data processing and model-calling capabilities, letting users assemble complex question-answering applications through a visual workflow editor.

FastGPT

FastGPT provides ready-to-use data processing and retrieval-augmented generation retrieval alongside model calling, and lets a user compose these into more complex applications through a visual flow-based workflow editor rather than custom integration code. It can be started quickly with Docker using a guided configuration prompt.

Its ecosystem includes a plugin system (FastGPT-plugin), an AI Proxy component for aggregating and load-balancing calls across multiple model providers, and Sealos for deploying clustered applications; third-party services are also listed as compatible.

Its source is published under the FastGPT Open Source License, which permits direct commercial use as a backend service but does not permit offering it as a SaaS product without a separate commercial license, and requires copyright notices to be kept in any commercial deployment.

It is written in TypeScript.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.