Skip to content
AgentsIndex

MetaGPT

Python multi-agent framework that assigns GPT roles the SOPs of a software company.

Best for
Engineering teams who want multi-agent software workflows inside GitHub.
GitHub stars
70.8k

What we checked

Pages last read
Facts checked
4 facts

From 5 sources, read 24 October 2026

AI answers
Too few read

58 buyer-question answers read, November 2026

At a glance

Tags
Freemium, Open source, Self-hosted

Code

Last push
21 January 2026

For developers

Works with
Okta, Entra ID, GitHub Actions, GitHub Copilot, GitHub Enterprise Cloud, GitHub Issues and 24 more

MetaGPT in our research

All research

Study

AI Tool Pricing Index, November 2026

Pricing

Free only

29 of the 361 tools we checked are free with no paid plan.

Edition price, checked 28 October 2026.

Pricing pages of the AI tools, November 2026 editionas of n = 361 tools checked

What is MetaGPT?

MetaGPT is a multi-agent software workflow platform for engineering teams that turns ideas into code, reviews, and project artifacts inside GitHub. It combines Multi-Agent Framework, Pull requests, Code review, GitHub Actions, and APIs, with GitHub Codespaces and Security at scale for automation and governance. It is used alongside GitHub by teams at Shopify, Mercedes-Benz, and Vodafone. It is MIT-licensed open-source software you run yourself, and the project publishes no paid plans.

What it does well

MetaGPT's core idea — encode a software company's standard operating procedure (Code = SOP(Team)) as a fixed pipeline of LLM roles (Product Manager → Architect → Project Manager → Engineer → QA), each with structured document handoffs instead of free-form chat — is a genuinely distinctive answer to the 'multi-agent systems degenerate into a chat loop' problem, and it's the one open GitHub issue from a would-be contributor (issue #2141) that a stranger volunteered unprompted in August 2026. The generate_repo() one-line-to-repo call and the separate Data Interpreter role (notebook/browser/shell tool use for data analysis and ML tasks) are both usable as installed today. The project's research output is real and independently checkable: the core MetaGPT paper was accepted as an oral at ICLR 2024, and follow-on work (AFlow, at ICLR 2025) also went to oral presentation — both listed on OpenReview under FoundationAgents/MetaGPT contributors.

Maintenance has effectively stopped

The repository's last merge to main was 21 January 2026 (PR #1897, a Windows-terminal compatibility patch), and the last tagged PyPI release is 0.8.2, published 9 March 2025 — 18 months old as of this review. The GitHub repo still shows heavy inbound traffic, but recent issues and PRs are dominated by unrelated vendor pitches and speculative feature requests (e.g. a phone-pairing PR for an unrelated third-party product, an LLM-gateway vendor's unsolicited config recipe) with no maintainer replies visible in the thread history. This pattern is explained by the vendor's own account of its roadmap: MetaGPT's official successor page (atoms.dev/metagpt) describes the team's trajectory explicitly as 'MetaGPT (2023, open-source framework) → MGX (2024, commercial product) → Atoms (now, complete business platform)' — the company that built MetaGPT has moved its engineering effort to a paid, closed product and treats the open-source repo as a legacy artifact.

Unpatched security disclosures

Three GitHub Security Advisories are open against MetaGPT ≤0.8.2, all reported through public issues in 2026 with no maintainer response noted in either the advisory or the linked issue thread: GHSA-xr7v-m9px-q4qj / CVE-2026-6110 (CVSS 7.3) — an eval() call on unvalidated LLM output in the Tree-of-Thought solver (metagpt/strategy/tot.py) that a prompt-injected or malicious model response can turn into arbitrary code execution; GHSA-r5v8-c28h-f8r8 / CVE-2026-6111 — server-side request forgery via decode_image(); and GHSA-3c3g-7hwg-9qmr / CVE-2026-10566 (CVSS 5.3) — a deserialization flaw in Message.check_instruct_content(). A fix for the eval() issue was submitted as PR #1946 in February 2026 but sits unmerged and open six months later. A related eval() pattern in a different file (serialize.py) was patched previously, per the reporting issue, so the project has fixed this class of bug before — just not this instance.

License and cost

MIT license, confirmed on the GitHub repo and the PyPI package metadata — no seat fees, no usage tier; you run it against your own LLM API keys (OpenAI, Anthropic, Azure, and roughly a dozen others are supported via config2.yaml). There is no hosted/paid version of MetaGPT itself; the commercial descendant is a separate product (Atoms, formerly MGX) with its own pricing, not documented here.

MetaGPT price and terms

Terms

Free plan
YesYesNo vendor charge at all: the package is MIT licensed and installed from PyPI
The terms in full

The user supplies an LLM API key and pays that provider; the docs estimate about $0.2 in GPT-4 fees for one analysis and design example and about $2.0 for a full project.

For AI agents

Developer docs

Where these prices come from

github.com/geekan/MetaGPT, checked

All plans and limits

PlanPriceMain limits
MetaGPTFreeNone stated

Read from github.com/geekan/MetaGPT.

What we checked on MetaGPT

YesPartlyNo

What it costs to startYes

Free to use

The free Copilot plan includes the CLI with an allowance of AI credits, so you can install and run it without talking to anyone.

Copilot CLI is included as a core feature of all GitHub Copilot plans (Free, Pro, Pro+, Max, Business, and Enterprise).

github.com/features/copilot/cliChecked

How you build with itYes

Public API

Programmatic mode drives the agent from your own scripts with a single prompt argument, and it can authenticate with a fine-grained personal access token.

To use the CLI programmatically, include the -p or --prompt command-line option in your command.

docs.github.com/en/copilot/concepts/cop…Checked

How you build with itYes

MCP server

It ships with GitHub's MCP server enabled and connects to custom MCP servers, so it acts as an MCP client rather than a server other agents call.

the coding agent ships with GitHub's MCP server by default and supports custom MCP servers to extend capabilities

github.com/github/copilot-cliChecked

How you build with itYes

Open source

Source is public on GitHub under Apache 2.0, and the vendor invites code contributions and community extensions.

We welcome contributions! Gemini CLI is fully open source (Apache 2.0), and we encourage the community to:

github.com/google-gemini/gemini-cliChecked

MetaGPT alternatives

Questions about MetaGPT

How much does MetaGPT cost?
MetaGPT is free to use. From github.com/geekan/MetaGPT, checked 28 October 2026.
Does MetaGPT have an API or an MCP server?
MetaGPT has an API. From docs.github.com/en/copilot/concepts/copilot-surfaces/copilot-cli, checked 24 October 2026. MetaGPT has an MCP server. From github.com/github/copilot-cli, checked 24 October 2026.
Is MetaGPT open source, and can you host it yourself?
MetaGPT is open source. From github.com/google-gemini/gemini-cli, checked 24 October 2026. You can host MetaGPT yourself.
What have we checked on MetaGPT?
4 facts, under these headings: What it costs to start, how you build with it.
How do we check MetaGPT?
We hold 4 facts on MetaGPT, quoted from 5 pages. Facts last checked 24 October 2026. Price last checked 28 October 2026. Last change found 28 March 2026.

How we check every listing

Repository

Licence
MIT
Stars
70,795
Last push
21 January 2026

MetaGPT price history

We have read the price once so far, on 28 October 2026: free.

PricePlanFirst seenLast seenReadingsSource
Free28 October 202628 October 20261Pricing page, read 28 October 2026

From our research on 28 October 2026. A date is when we read the page, not when the price changed.

Is MetaGPT yours?

Free, and the page then carries the verified owner mark. Claim this listing

Report an error if a fact is wrong.