Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Introduction

Vigils is a local-first control plane for AI agents:

  • Action firewall (Firewall::evaluate) — fail-closed effect gating
  • Audit ledger (SHA-256 hash chain) — tamper-evident decision history
  • Privacy filter (hard-fingerprint rules + optional ONNX-backed PII detection)
  • MCP hub (Model Context Protocol server registry + descriptor pinning)
  • Approval queue (human-in-the-loop for risky effects)
  • Sandbox runner (Wasm + native, Linux Landlock LSM)

Vigils sits between AI agents and the effectful tools / APIs they touch, gating each action through redaction + policy + audit + approval — and everything stays on your machine.

Project status

DimensionState
Releases3-platform signed installers + auto-update (OTA) — latest release
Rust SDKvigil-sdk published to crates.io
SecurityComprehensive audit (OWASP + STRIDE + supply chain) — 9.9 / 10, 0 critical / high
MaturityCore safety claims proven-safe with code + test evidence; all sandbox / SDK / audit changes reviewed

Distribution

  • Desktop installers — Linux deb / rpm / AppImage + macOS dmg + Windows nsis / msi (Ed25519-signed, auto-update).
  • Rust SDKcargo add vigil-sdk (crates.io / docs.rs).
  • Browser extension — Chrome MV3 (redacts before paste / submit on AI sites).
  • CLI agent gatewayvigil-hub serve --stdio (Claude Code / Codex / Cursor / Zed).

License

Apache-2.0 © Vigils Project Contributors