Back to directory

AutoGPT

A Rust framework for building and managing autonomous AI agents, with declarative YAML agent configuration, long-term memory, planning and multi-agent collaboration.

AutoGPT

This AutoGPT framework lets a developer define an agent's behavior in YAML without writing code, giving it tools and sensors to interact with the world such as file I/O, external APIs, audio and video, and combining long-term vector memory with structured knowledge bases for recall and reasoning. A planner breaks a complex task into subgoals and tracks progress, persona and capability settings define what an agent is allowed to do, and agents can delegate work to each other or work in teams.

It is distributed as a downloadable executable, a cargo package, or a Docker image, and is under active development alongside a related, non-LLM project from the same author that instead predicts and reasons with equation-based methods.

It is written in Rust and licensed under MIT.

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.