AI and models · Independent · 21 Oct 2026

Significant-Gravitas/AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

← AI and models
AutoGPT: AI agents that finish the work. Builds and runs multi-step AI agents from plain English.

In simple English

AutoGPT is a system for building artificial intelligence agents that do tasks for you. You describe what you want in plain words, and the agent figures out the steps and executes them. It can search the web, read files, and talk to other programs like Slack or GitHub. You can use their hosted online service for a fee, or run the software yourself on your own computer. If you run it yourself, you need to bring your own model API keys (secret passwords that let your program talk to an artificial intelligence service) and set up Docker (a way to run a program inside its own sealed box, so it cannot break anything else on your server).

What it is

AutoGPT is a platform for creating, scheduling, and running autonomous artificial intelligence agents using a visual builder or a chat interface. It combines a workflow canvas, a marketplace of ready-made agents, and integrations with dozens of external services.

What it is good for

Solo builders who want to automate repetitive research, social media posting, lead enrichment, or customer support triage without writing complex orchestration code from scratch.

Stars188k
LicenceCustom
Latestautogpt-platform-beta-v0.8.4 (2026-10-14)checked 21 Oct 2026
Last code change2026-10-21
Written inPython
Setup effort
4 / 5
Payoff
4 / 5
Good
  • Visual builder lets you drag and connect agent steps without coding.
  • Large marketplace of pre-built community agents to start from.
  • Connects to dozens of popular platforms like Gmail, Slack, and Notion.
Watch for
  • Polyform Shield licence restricts selling this as a competing hosted service.
  • Self-hosting requires Docker and your own model API keys.
  • Running complex multi-step agents can consume a lot of token credits and cost real money.
Replaces

manual multi-step workflow execution and custom Python automation scripts

Works well with

OpenAI API keys and Docker

Similar repositories
  • langchain-ai/langchain148k stars

    A framework for building applications with language models using code rather than a visual platform.

  • n8n-io/n8n208k stars

    A node-based workflow automation tool that also supports artificial intelligence agent nodes.

Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

How to get it

Read the manual self-hosting guide in the repository documentation to deploy the platform on your own infrastructure.

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Assistants & Agents › Autonomous Agents.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.