# elder-plinius/T3MP3ST

autonomous red teaming platform; multi-agent offensive-security meta-harness

Repository: https://github.com/elder-plinius/T3MP3ST
Canonical: https://ross.abutalabs.com/products/t3mp3st
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: agents, ai, multi-agent, offensive-security, redteam
Last push: 2026-08-24T01:27:31+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 4
- inputs: {"age_days": 62, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5684, forks 1174 (observed 2026-08-28T04:09:27.842081+00:00)

## What it is
T3MP3ST is a multi-agent offensive-security framework that turns existing AI coding agents (Claude Code, Codex, Ollama, etc.) into autonomous red-teaming and zero-day hunting harnesses. It orchestrates a recon-to-exploit-to-report kill chain from a CLI or browser War Room, with reproducible benchmarks on CTF and CVE-style challenges.

## Use cases
- run automated red team engagements against authorized targets
- hunt for zero-day vulnerabilities with an AI coding agent
- solve CTF challenges without hints
- test AI agent security tooling against benchmark suites like XBOW's 104 challenges
- orchestrate multi-agent offensive security workflows
- run offline penetration testing with locally hosted models

## When to choose
- you want to automate authorized penetration testing or red teaming using an AI agent you already use
- you need reproducible, verifiable security benchmark results
- you prefer keyless, self-hosted operation with local models like Ollama or vLLM

## When to avoid
- you need a passive vulnerability scanner or compliance auditing tool rather than active exploitation
- you lack authorization to test the target - this is an offensive tool
- you need a managed cloud SaaS with vendor support

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, penetration-testing, security, cli, llm-inference
- domain: security, penetration-testing, developer-tools
- platform: cli, cross-platform, self-hosted
- tags: red-teaming, offensive-security, multi-agent, vulnerability-scanning, ai-coding-agent, ctf, exploitation, recon, ai-agents, command-line, nodejs

## Member repositories
- elder-plinius/T3MP3ST (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:27.842081+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:54:14.386547+00:00, confidence not recorded.
  - readme: https://github.com/elder-plinius/T3MP3ST (fetched 2026-08-28T04:09:27.842081+00:00, sha eae2d395c852)
- Data as of 2026-08-30T08:39:29.467469+00:00.