DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run PentAGI on local models so findings never leave your network with PentAGI

Point PentAGI at Ollama or vLLM so prompts and results stay on your hardware.

Short answer: Set up Ollama or vLLM on a GPU server; then configure PentAGI's custom or Ollama provider; enable execution monitoring and task planning for smaller open models. All steps.

Who it is forA consultancy whose clients forbid sending engagement data to cloud AI providers.

The problemPentest data is sensitive and cloud LLMs may be off limits.

The outcomePentAGI running against a local model with execution monitoring and task planning to help smaller models.

What you need first

  • Docker and Docker Compose (an interactive installer sets it up on Linux, macOS or Windows)
  • An LLM provider key or a local model via Ollama or vLLM
  • Written authorization to test every target

Steps

  1. Set up Ollama or vLLM on a GPU server
  2. Configure PentAGI's custom or Ollama provider
  3. Enable execution monitoring and task planning for smaller open models
  4. Run a lab flow and compare results with a cloud model

Prompt for your agent

Configure vxcontrol/pentagi to use my local <Ollama or vLLM> endpoint with <model>, enable execution monitoring, and run a short flow against my lab VM. Report which steps the local model struggled with.

Caveat. Authorized targets only; smaller local models may miss findings a larger model would catch.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for vxcontrol/pentagi and "Run PentAGI on local models so findings never leave your network"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer