cd /news/artificial-intelligence/i-built-an-autonomous-multi-agent-ai… · home topics artificial-intelligence article
[ARTICLE · art-112591] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

I built an autonomous multi-agent AI pentester — and why it's not another GPT wrapper

A developer has released OIHK, an open-source autonomous multi-agent AI penetration-testing engine that requires real tool execution and independent validation before reporting a finding, avoiding the 'confident nonsense' of single-LLM wrappers. The engine uses a root planner that delegates to specialist agents, with guardrails enforced in code, and includes a deterministic evaluation environment with 16 vulnerable scenarios.

read2 min views2 publishedAug 27, 2026

Most "AI pentester" projects are a single LLM in a while-loop with a shell. You

give it a target, it runs commands until it decides it found something. That's

how you get confident nonsense — a model that writes a beautiful vulnerability

report for a bug that doesn't exist.

I wanted the opposite: an engine where a finding has to be earned. So I built

OIHK — an autonomous, multi-agent

AI penetration-testing engine. It's open source (MIT) and runs locally.

OIHK is a multi-agent engine. A root planner delegates to specialist agents —

recon, discovery, validation, reporting — that all share two things:

Agents don't coordinate by vibes in a chat log. They claim explicit plan steps,

attach real evidence, and update state through a revisioned store. The root can't

close a run while critical work is still open.

Here's the design decision the whole thing is built around:

An LLM writing a convincing PoC string is

nota finding.

A finding requires a real, successful, governed tool execution and a

separate validation record. Only a validation agent can turn evidence into a

finding. If there's no execution record and no independent validation, it never

becomes a finding — no matter how confident the model sounds.

Offensive tools + autonomous agents is a scary combo if "be careful" is just a

line in a prompt. In OIHK the guardrails are actual code:

example.com

doesn't authorize its subdomains or resolved IPs. Declared hosts are resolved once and DNS-pinned for the whole run.OIHK is provider-agnostic. Any OpenAI-compatible endpoint works (LM Studio by

default), with per-role model routing and no hardcoded provider. You can run a

strong reasoning model as the planner and a fast one for the specialists.

This is my favorite part. OIHK doubles as an evaluation environment: it runs

the real engine against 16 local, deliberately vulnerable scenarios and scores

the model programmatically — never by asking a model to grade itself.

There's a deterministic offline mock

solver for CI and demos:

bash
uv run oihk eval run-all --model mock
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @oihk 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-an-autonomou…] indexed:0 read:2min 2026-08-27 ·