Back to directory

AutoGPT

An open-source platform for building, deploying and running AI agents that carry out complete workflows, designed in plain English or in a visual block builder.

AutoGPT

AutoGPT lets you build AI agents by describing an outcome in plain English or by connecting blocks in a visual builder. Agents run on demand, on a schedule or from a trigger.

The platform has four parts: AutoPilot, which turns a conversation into a working agent; Agents, which shows runs, costs and actions; a Marketplace of existing agents; and Build, the visual editor.

It is available as a paid hosted platform or self-hosted with Docker, where you provide the infrastructure and model API keys. It is written in Python.

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.