Multi-agent · AI agent
Squad: review, pricing, security and alternatives
Squad is an open-source AI agent published by Brady Gaster, in the multi-agent family. Organizes teams of AI agents to work on projects through a command-line environment associated with GitHub Copilot. Its repository has 3,304 stars and its last commit is from October 24, 2026.
What Squad does
Squad 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 #23 of the 43 projects of this family listed in the directory.
You use it from: terminal (CLI). It can run on your own machine or server.
Who is Squad 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 you are comfortable in a terminal and your data must stay on your machines.
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.
Squad pricing
The code is free, under the MIT licence.
Getting started with Squad
- Install it: the project ships as a Node.js package (install with
npm, or run directly withnpx). The exact command is in the repository README. - Create an API key with the model provider and put it in an environment variable, never in a shared or versioned file.
- 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.
- 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 February 6, 2026, the bradygaster/squad repository has 3,304 stars, 507 forks and 99 open issues, with 2,590 commits in total. It received changes this month.
Over the last 52 weeks: 2,221 commits, an average of 42.7 per week.
37 releases in total; 23 in the last twelve months. Latest release: v1.1.0, on October 20, 2026.
Squad 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.
Squad 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.
| Agent | Model | Score | Stars or entry price | Self-hostable | Human approval |
|---|---|---|---|---|---|
| Squad | open source | 68 | 3.3K ★ | yes | – |
| Orca | open source | 91 | 104.7K ★ | yes | – |
| CrewAI | open source | 88 | 60.1K ★ | yes | – |
| Agno | open source | 87 | 42.9K ★ | yes | – |
| Paperclip | open source | 86 | 106.8K ★ | yes | – |
| AgentScope | open source | 85 | 33.8K ★ | yes | – |
| OpenAI Agents SDK | open source | 85 | 30.3K ★ | yes | – |
| Eigent | open source | 81 | 15.7K ★ | yes | – |
How we rated it
Score: 68/100, computed only from public, verifiable data, with no subjective testing or partnership:
- Adoption 18/40: 3,304 stars on a log scale (40 points from about 200,000).
- Activity 30/30: last commit less than a month ago, 8 releases in six months, 2,221 commits in a year.
- Framework 20/30: 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.
Verdict
Squad is a serious option; check the limitations below before granting it access.
Strengths
- Very active development
- Frequent releases (23 in a year)
- Can run on your side: data under control
- Permissive licence (MIT)
Alternatives
- Orca104.7K ★
- CrewAI60.1K ★
- Agno42.9K ★
- Paperclip106.8K ★
- AgentScope33.8K ★
- OpenAI Agents SDK30.3K ★
Learn more
Frequently asked questions
Is Squad free?
The software is free (MIT licence). You still pay for the model calls, unless you use a local model.
Is Squad safe?
Our risk level: low. Give it minimum rights and approve irreversible actions.
Which models does Squad use?
Its documentation does not specify the supported models.
Can Squad be installed on your own server?
Yes, from the bradygaster/squad repository. Data then stays with you, but security and updates are your job.
What are the alternatives to Squad?
In the same family: Orca, CrewAI, Agno, and Paperclip.
Squad or Orca: what is the difference?
Both belong to the multi-agent family. Squad has 3.3K stars against 104.7K for Orca. The right choice mostly depends on the access you are willing to give it.
Related articles
- Open source or proprietary AI agent: how to decideOctober 25, 2026
- AI agent vs. chatbot: what's the difference?October 24, 2026
- Autonomous AI agents: how much should you let them do?October 12, 2026
- AI agent memory: how agents remember (and forget)October 11, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score