whereismyai
Sapper V2
Sapper V2 is an autonomous penetration-testing agent legion that divides labor and uses a layered fact graph.
Sapper V2 is an autonomous penetration-testing legion that coordinates multiple AI agents to divide labor, communicate, and preserve knowledge. It features an AI commander that reads the board and dispatches tasks, generals and soldiers that execute parallel attacks, and a watchdog that ensures uptime. The system builds a layered fact graph for memory, preventing context burn and single-point failures. It supports model tiering, using GLM-5.3 for commanders and DeepSeek V4.1 Flash for soldiers, running inside Docker and tmux. The architecture emerged from eighteen versions and successfully competed in AI challenge platforms.
Sapper V2 at a glance
- Best for: Software engineer
- Runs on: Docker, CLI, self-hosted, open source
- Pricing: Free and open source under the MIT license.
- Released: October 2026
- Category: AI agent tool
- Website: github.com/n1neman/sapper-v2
Key features
- Commander agent for task dispatch
- Parallel general and soldier agents
- Layered fact-intent graph for memory
- Watchdog script for automated recovery
- Model tiering across different roles
- Automated signalman role creation
- Context recycling and playbooks
Use it for
- Autonomous penetration testing
- Automated vulnerability assessment
- Parallel security challenge solving
Alternatives to Sapper V2
- ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
- CyberStrike — Autonomous AI agents execute recon, web, network, and cloud penetration testing.
- VulnClaw — It uses LLM agents to autonomously execute end-to-end security testing loops.
- Beeuni — Agents retain context and improve skills over time through a controlled review process.
- FakeLiang — Verifies attack paths step by step with traceable call records and evidence.
- AgentOps — Track token usage, costs, and traces across 400 plus LLMs and agent frameworks.
- OmniAgent — It evolves skills in real-time and dynamically hardens security during task execution.
- Raven — Provides a persistent, self-evolving environment for all-domain agent collaboration.
- Agent Squad — Runs multi-agent orchestration in Python, TypeScript, and locally on Apple devices.
- APIStack — Connect AI agents to over 100 tools using one API key or a single MCP endpoint.
- TaintWall — Enforces deterministic security policies at the tool boundary for AI agents.
- Caura — Governed memory providing persistent knowledge sharing for AI agent fleets.
All Sapper V2 alternatives