Vigil

Vigil is an AI-driven CLI tool for offensive security and incident-response engagements using specialist agents and a Kali runtime.

Vigil drives security engagements end to end from a single command-line interface. An LLM operator reads a phased workflow prompt, dispatches specialist agents, runs real tooling inside a shared Kali container, and records every target, service, probe, finding, and attack chain into a durable orchestrator database. Web red-team, white-box code analysis, Android application analysis, and blue incident response share the same backend. It provides independently verified findings, audited target-facing commands, and durable state stored in SQLite. Supported client integrations include Claude Code, Codex, Kimi, goose, opencode, and Pi.

Vigil at a glance

Best for: Software engineer
Runs on: CLI, API, Web, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: github.com/vigiloss/vigil

Key features

Run independent finding verification
Audit target-facing commands and techniques
Execute real attack tooling in a Kali container
Perform white-box code analysis with tree-sitter
Store durable engagement state in SQLite
Support multiple client integrations

Use it for

Conducting web red-team engagements
Performing white-box code analysis
Executing Android application analysis
Managing blue incident response operations

Alternatives to Vigil

Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
VulnClaw — It uses LLM agents to autonomously execute end-to-end security testing loops.
AiSOC — Runs locally without API keys with bundled models and auditable reasoning ledgers.
ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
OpenAPPA — Tracks data flows algebraically to prevent prompt injection without breaking agents.
AgentDock — It coordinates multi-device workflows and provides secure environment access.
ARTEX — Manages autonomous penetration testing tasks and tracks vulnerability progress.
Destructive Command Guard — It prevents AI agents from accidentally running commands that destroy work.
CyberStrike — Autonomous AI agents execute recon, web, network, and cloud penetration testing.
Aegis Kernel — Stops prompt injection and tool-hijacking at the OS syscall boundary.
AgentGuard — Get a security and quality assessment of AI skills in seconds without an account.
Tirith — Detects 200+ terminal and AI-agent threats locally with zero latency.

All Vigil alternatives