AutoGPT: review, pricing, security and alternatives

What AutoGPT does

AutoGPT belongs to the automation family: platforms, often visual, that chain steps, apps and models into workflows with or without an agent. On our grid it ranks #4 of the 26 projects of this family listed in the directory.

You use it from: web app. Usable models: Claude (Anthropic), GPT (OpenAI), Llama (Meta), and local models (Ollama, llama.cpp, vLLM…). It can run on your own machine or server.

Who is AutoGPT for?

It is for teams that want to connect their tools (CRM, e-mail, spreadsheets) and hand the AI the steps that require reading or deciding. Typical tasks people give it:

• qualify incoming requests and route them
• extract data from documents into a spreadsheet
• generate periodic reports

It is a good candidate if you prefer doing everything in a browser, with no install, your data must stay on your machines, and you want the option of a local model, with no API fees.

Access and human control

Its documentation does not detail the access granted to the agent: check the settings before connecting it to your accounts.

We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.

AutoGPT pricing

The code is public but the repository declares no licence: reuse is not formally allowed. The real cost comes from model calls: each loop step sends the whole context back to the model, and a task of several dozen steps can cost far more than a single question. The LLM price calculator estimates it for the chosen model.

Getting started with AutoGPT

1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
2. Pick the model: an API key from a provider, or a local model if your machine has enough graphics memory (the VRAM calculator tells you).
3. Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

A workflow runs unattended: limit the credentials it holds and log what it sends.

Points found for AutoGPT:

• No licence: legally shaky for company use.

Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.

Project activity and releases

Created on March 16, 2023, the Significant-Gravitas/AutoGPT repository has 187,725 stars, 45,894 forks and 339 open issues, with 10,050 commits in total. It received changes this month.

Over the last 52 weeks: 4,401 commits, an average of 84.6 per week.

126 releases in total; 29 in the last twelve months. Latest release: autogpt-platform-beta-v0.9.0, on October 23, 2026.

AutoGPT vs other automation

GitHub stars of the best-rated open-source projects in the automation family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.

AutoGPT and other automation at a glance

The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.

How we rated it

Score: 84/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 39/40: 187,725 stars on a log scale (40 points from about 200,000).
• Activity 30/30: last commit less than a month ago, 24 releases in six months, 4,401 commits in a year.
• Framework 15/30: licence, default human approval, self-hosting, model choice and documentation site.

The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.