AutoGen: review, pricing, security and alternatives

What AutoGen does

AutoGen belongs to the multi-agent family: systems that split a task between several specialised agents passing work to one another. On our grid it ranks #17 of the 43 projects of this family listed in the directory.

A framework is not used as is: it is a library developers build into their own code to describe the agent's tools, decision loop and memory. It requires programming skills, but leaves control over every detail.

You use it from: developer SDK. Usable models: GPT (OpenAI), Claude (Anthropic), Gemini (Google), local models (Ollama, llama.cpp, vLLM…), and any OpenAI-compatible model. It can run on your own machine or server.

Who is AutoGen for?

It interests technical teams that want to split a complex task between several specialised agents that check each other. Typical tasks people give it:

• pair a writer agent with a reviewer agent
• split a project into subtasks given to roles
• simulate a team (analysis, plan, execution)

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

Access and human control

A framework has no access of its own: the tools you plug in define what the agent can do. Start with read-only tools.

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

AutoGen pricing

The code is free, under the CC-BY-4.0 licence.

Getting started with AutoGen

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. Start with the minimal example from the docs, then add one tool at a time and check what the agent does with it.
4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

More agents mean higher bills and chained errors: set a budget and a maximum number of steps.

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 August 18, 2023, the microsoft/autogen repository has 61,548 stars, 9,314 forks and 562 open issues, with 3,783 commits in total. It received changes this month.

Over the last 52 weeks: 4 commits, an average of 0.1 per week.

98 releases in total; 0 in the last twelve months. Latest release: python-v0.7.5, on September 30, 2025.

AutoGen vs other multi-agent

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

AutoGen and other multi-agent 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: 74/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 33/40: 61,548 stars on a log scale (40 points from about 200,000).
• Activity 16/30: last commit less than a month ago, 0 releases in six months, 4 commits in a year.
• Framework 25/30: 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.