OpenViSTAI · Agents · Blockchain · Crypto
Menu
Multi-Agent Systems

Pentagi

Pentagi is a public, MIT-licensed Go project that uses autonomous AI agents for complex penetration-testing tasks. Its repository topics reference multi-agent systems, offensive security, GraphQL, Anthropic, and OpenAI.

Independent OpenViST project profile, based on linked sources.

Pentagi — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider Pentagi for authorized internal security assessments where an engineering team can define target boundaries and operational controls around autonomous testing.

Who it is for

  • Security teams exploring autonomous penetration-testing workflows.
  • Developers assessing an open-source foundation for internal red-team automation.
  • Organizations evaluating multi-agent approaches to approved security assessments.

Documented uses

  • Automate parts of complex penetration-testing work.
  • Coordinate reconnaissance, analysis, and reporting through a multi-agent workflow.
  • Explore security testing for permitted GraphQL endpoints.
  • Prototype an internal red-team automation tool.
Before you choose

Requirements & limits

The repository is public and MIT-licensed.

  • The project is implemented in Go.
  • Its stated purpose is autonomous penetration testing rather than general-purpose task automation.
  • Authorization and scope enforcement require modification for a controlled internal workflow.
  • GraphQL is among the repository’s referenced security-testing areas.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
vxcontrol/pentagi · Official homepage title · retained in its source language