PentAGI: review, pricing, security and alternatives

What PentAGI does

PentAGI belongs to the business agents family: agents specialised in one job: customer support, sales, finance, legal, HR, security. On our grid it ranks #3 of the 52 projects of this family listed in the directory.

You use it from: web app. Usable models: Claude (Anthropic). It can run on your own machine or server.

Who is PentAGI for?

It targets a specific job (customer support, sales, finance, legal…) with workflows already set up. Typical tasks people give it:

• handle first-line customer requests
• prepare standard documents
• track cases and follow up

It is a good candidate if you prefer doing everything in a browser, with no install and your data must stay on your machines.

Access and human control

According to its documentation, PentAGI can:

• run commands in a terminal
• read and edit files
• call online services and APIs
• drive a web browser

By default it acts without asking for confirmation. Turn on an approval mode if it has one, or limit its rights to the bare minimum.

PentAGI pricing

The code is free, under the MIT licence.

Getting started with PentAGI

1. Install it: the project ships as a single Go binary, downloadable from the repository releases. The exact command is in the repository README.
2. Create an API key with the model provider and put it in an environment variable, never in a shared or versioned file.
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 business agent acts on the company's behalf: define what it may promise, refund or change, and keep a record of its decisions.

Points found for PentAGI:

• Sensitive access: it can run commands in a terminal, with no established default human approval.
• Outside content: it reads web pages or API responses, which may contain booby-trapped instructions (prompt injection).

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 January 6, 2025, the vxcontrol/pentagi repository has 32,270 stars, 5,003 forks and 23 open issues, with 953 commits in total. It received changes this month.

Over the last 52 weeks: 877 commits, an average of 16.9 per week.

10 releases in total; 7 in the last twelve months. Latest release: v2.2.0, on October 5, 2026.

PentAGI vs other business agents

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

PentAGI and other business agents 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: 77/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 30/40: 32,270 stars on a log scale (40 points from about 200,000).
• Activity 27/30: last commit less than a month ago, 2 releases in six months, 877 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.