sapper-v2

sapper-v2 is a multi-agent orchestration framework that coordinates swarms of AI agents to perform autonomous penetration testing.

What it is good for

  • Running automated penetration tests with multiple coordinated AI agents
  • Coordinating many agent instances to divide labor on long tasks
  • Keeping shared memory across agent sessions so work survives individual failures
  • Building a custom multi-agent orchestration system for your own domain

At a glance

Who it is for
Setup difficulty
Technical ยท Guided command-line setup

Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.

Cost
Free and open source
Type
Framework or SDK
Tasks
Works with
Claude Code, Codex, DeepSeek, tmux

How to get started with sapper-v2

  1. Clone the nvwabase repository with git clone https://github.com/N1nEmAn/nvwabase.
  2. Run cd nvwabase && bash install.sh.
  3. Set up a goal with nvwabase setup --goal "your long-horizon goal" --agents.
  4. Check progress with nvwabase status.
  5. Fork sapper-v2 and replace docker/commander/SKILL.md to adapt it to your own scenario.

From the project's own documentation. If a step does not match what you see, the official pages have the latest instructions.

Before you try it

  • Intended for authorized security testing only, per the project's disclaimer.
  • Requires running agent CLIs like Claude Code, Codex, or similar tools you supply yourself.
  • Designed primarily for competition-style penetration testing scenarios.
  • Setup involves command-line tools and configuring agent and model choices.

Momentum

Rank this week
#8 in builder tools
Best rank
#2 week 45, 2026
Stars gained last week
+391
GitHub stars
2,128

GitHub numbers as of Nov 16, 2026. Updated weekly.

105 1,192 2,278 Oct 31, 2026 Nov 16, 2026
GitHub stars for sapper-v2: 255 on Oct 31, 2026, 2,128 on Nov 16, 2026. Source: GitHub.

Ranking history

First ranked in week 45, 2026.

Questions

Is sapper-v2 free?
Yes. It is free and open source (MIT license).
Do I need to know how to code to use sapper-v2?
You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
What does sapper-v2 work with?
According to its own documentation, it works with Claude Code, Codex, DeepSeek, and tmux.
How do I get started with sapper-v2?
1. Clone the nvwabase repository with git clone https://github.com/N1nEmAn/nvwabase. 2. Run cd nvwabase && bash install.sh. 3. Set up a goal with nvwabase setup --goal "your long-horizon goal" --agents. 4. Check progress with nvwabase status. 5. Fork sapper-v2 and replace docker/commander/SKILL.md to adapt it to your own scenario.
What should I know before trying sapper-v2?
Intended for authorized security testing only, per the project's disclaimer. Requires running agent CLIs like Claude Code, Codex, or similar tools you supply yourself. Designed primarily for competition-style penetration testing scenarios. Setup involves command-line tools and configuring agent and model choices.
What is sapper-v2 good for?
Running automated penetration tests with multiple coordinated AI agents, coordinating many agent instances to divide labor on long tasks, keeping shared memory across agent sessions so work survives individual failures, and building a custom multi-agent orchestration system for your own domain.

Similar agents to sapper-v2

  • Eigent

    Runs a desktop team of agents for general multi-step work instead of a pentest-focused swarm.

  • OpenMausBot

    Lets you chat with a local team of bots rather than orchestrating an autonomous security-testing legion.

  • cua

    Gives agents control of a full desktop for general computer tasks, not multi-agent pentest orchestration.

  • openharness

    Watches and manages multiple coding agents from a GUI rather than running an autonomous attack swarm.

  • Kestra

    Kestra is an open-source orchestration platform that schedules and automates data, infrastructure, and AI agent workflows for technical teams.

  • reef

    reef is a framework that lets developers keep AI agents improving from real usage feedback, by training model weights or updating prompts, rules, and skills.

Also compared with sapper-v2 on these pages:

Last updated Nov 16, 2026. Tracked since Oct 31, 2026. Parts of this summary required judgment because the source material was brief. Spotted an error? Tell us.