# vxcontrol/pentagi

> Autonomous multi-agent system in Go for automated penetration testing: AI agents plan and execute steps in an isolated Docker sandbox with 20+ tools (nmap, metasploit, sqlmap).

- Magnitude: 2.9 out of 10 — Cooling
- Stars: 32,548 total · +36 stars measured 2026-10-27, 00:37–10:07 UTC, ≈ 88 by evening
- Star trust: star growth looks organic
- Category: Security · Language: Go · License: MIT · Created: 2025-01-06 · Last push: 2026-10-22
- GitHub: https://github.com/vxcontrol/pentagi · Homepage: https://pentagi.com · Page: https://gitnova.dev/en/r/vxcontrol/pentagi

## Useful for

- Run an automated penetration test against a target system via the web UI
- Connect your own LLM provider (OpenAI, Anthropic, Ollama) for the agents
- Generate a vulnerability report with exploitation guides in Markdown or PDF

## Why it’s here

- Star-counter measurements on 2026-10-27 (UTC), 00:37–10:07: 32512 → 32548 stars (+36). This is the change over that interval.
- Estimated end-of-day forecast: about +88 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 26% of the previous week and a half.
- About 34 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 5,068
- Issues and pull requests: 461
- Watchers: 172
- Average over the last week: 148 per day
- Usual pace: 372 per day
- Stars in the last hour (measured): 3
- Latest release: v2.2.0 (2026-10-05)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 31, 34, 26, 24, 30, 23, 20, 39, 44, 64, 30, 71, 1908, 1074, 1479, 650, 218, 180, 244, 201, 234, 222, 257, 121, 140, 114, 96, 15, None, None

## Magnitude by day, last 14 days

10-14 7.4, 10-15 7.8, 10-16 5.7, 10-17 4.2, 10-18 4.1, 10-19 4.3, 10-20 3.9, 10-21 3.6, 10-22 3.8, 10-23 3.5, 10-24 3.0, 10-25 3.0, 10-26 2.9, 10-27 2.9

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-27 10:19 UTC, updated every 30 minutes.