# KeygraphHQ/shannon

> Autonomous AI pentester for web applications and APIs: analyzes source code, finds attack vectors, and runs real exploits, reporting only vulnerabilities with a working proof-of-concept.

- Magnitude: 6.0 out of 10 — Breakout
- Stars: 50,003 total · +99 stars measured 2026-10-28, 11:23–15:55 UTC, ≈ 170 by evening
- Star trust: star growth looks organic
- Category: Security · Language: TypeScript · License: AGPL-3.0 · Created: 2025-09-27 · Last push: 2026-10-27
- GitHub: https://github.com/KeygraphHQ/shannon · Homepage: https://keygraph.io/ · Page: https://gitnova.dev/en/r/KeygraphHQ/shannon

## Useful for

- Run a pentest of a staging environment before release via npx @keygraph/shannon
- Embed vulnerability checks into GitHub Actions for every build
- Verify a PHP app against the php2shell RCE chain with the experimental flag

## Why it’s here

- Star-counter measurements on 2026-10-28 (UTC), 11:23–15:55: 49904 → 50003 stars (+99). This is the change over that interval.
- Estimated end-of-day forecast: about +170 stars, using observed gains and the previous day.
- Over the last two days the pace is 5.4× that of the previous week and a half.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending TypeScript today: #9, +415 stars.
- About 80 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: 5,732
- Issues and pull requests: 465
- Watchers: 233
- Average over the last week: 119 per day
- Usual pace: 44 per day
- Stars in the last hour (measured): 22
- Latest release: v3.5.0 (2026-10-27)

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

2026-09-29 … 2026-10-28: 34, 19, 24, 26, 22, 24, 31, 40, 32, 34, 43, 23, 29, 63, 49, 37, 58, 81, 66, 31, 36, 54, 34, 34, 81, 37, 33, 115, 365, 99

## Spotted in now

- GitHub Trending TypeScript today: #9, +415 stars

## Similar by description

1. **usestrix/strix** — 3.5 · Steady · Security · Python · +138 stars measured 2026-10-28, 00:03–15:57 UTC, ≈ 206 by evening
   Open-source AI pentesting tool: autonomous agents run your code, find vulnerabilities, and validate them with working PoCs. For developers and security teams needing fast testing without manual pentests or static-analysis false positives.
   Full card: https://gitnova.dev/en/r/usestrix/strix.md
2. **elder-plinius/T3MP3ST** — 1.3 · Steady · Security · TypeScript · +2 stars measured 2026-10-28, 00:09–16:06 UTC, ≈ 4 by evening
   Multi-agent red-teaming platform that turns an existing AI coding agent into a vulnerability-hunting harness, automating the recon → exploit → report kill chain for web apps, CTFs, smart contracts, and source code.
   Full card: https://gitnova.dev/en/r/elder-plinius/T3MP3ST.md
3. **Haryy985/yunkun-console-preview** — 0.0 · Steady · Security · Go · Not enough measurements today
   A console for authorized penetration testing that unifies AI-agent chat, tasks, tools, a RAG knowledge base, proxy pool, HTTP traffic and vulnerability reports in one workspace. The repo currently holds only docs, screenshots and…
   Full card: https://gitnova.dev/en/r/Haryy985/yunkun-console-preview.md
4. **junaire/CVE-2026-109618-exploit** — 0.5 · Cooling · Security · Python · +2 stars measured 2026-10-28, 00:12–16:09 UTC, ≈ 3 by evening
   Working exploit and Docker target for an unauthenticated RCE in PHP's session.upload_progress handling (CVE-2026-109618/109619), affecting versions 5.4.0–8.5.11.
   Full card: https://gitnova.dev/en/r/junaire/CVE-2026-109618-exploit.md
5. **jiwoochris/artex-global** — 3.0 · Steady · Security · Go · +37 stars measured 2026-10-28, 00:05–15:59 UTC, ≈ 56 by evening
   Korean-localized edition of ARTEX, an autonomous penetration-testing framework driven by multi-agent LLMs (Go backend + Next.js) that plans and executes attack steps on its own. Aimed at security practitioners studying and defending…
   Full card: https://gitnova.dev/en/r/jiwoochris/artex-global.md

---

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 2026-10-28 16:10 UTC, updated every 30 minutes.