v0.1.0 · just shipped
VIGIL

Your agents can code.
Vigil makes sure they can't destroy.

Zero-dependency safety guardrails for AI agent tool calls. <2ms. 22 rules. npm install and go.

GitHub 🦞 ClawdHub
example.ts
import { checkAction } from 'vigil-agent-safety';

const result = checkAction({
  agent: 'my-agent',
  tool: 'exec',
  params: { command: 'rm -rf /' },
});

// result.decision → "BLOCK"
// result.reason  → "Destructive command pattern"
// result.latencyMs → 0.3
// What it catches

22 rules. 8 threat categories.

Every tool call your agent makes gets checked against battle-tested patterns, in under 2 milliseconds.

Destructive Commands

BLOCK

rm -rf, mkfs, dd if=/dev/zero, reverse shells, fork bombs

SSRF

BLOCK

169.254.169.254, localhost, internal IPs, cloud metadata endpoints

Data Exfiltration

BLOCK

curl evil.com, .ssh/id_rsa, /etc/shadow, piped secrets

SQL Injection

BLOCK

DROP TABLE, UNION SELECT, OR 1=1, comment injection

Path Traversal

BLOCK

../../../etc/passwd, %2e%2e/, directory escape sequences

Prompt Injection

BLOCK

ignore previous instructions, [INST] tags, system prompt leaks

Encoding Attacks

BLOCK

base64 -d | sh, eval(atob()), hex-encoded payloads

Credential Leaks

ESCALATE

API keys, AWS secrets, tokens, passwords in tool params

// How it compares

No LLM. No latency. No dependencies.

Vigil is a deterministic rule engine, not another AI wrapper.

Tool Latency Dependencies Validates Tool Calls Works Offline
Vigil <2ms 0
Llama Guard ~500ms PyTorch, model weights
Regex / DIY <1ms 0 Partial
GPT-4 Review ~2-5s API key, network
// Integrations

Works with everything.

Drop Vigil into any agent framework, CI pipeline, or API server.

MCP

Model Context Protocol

LangChain

Agent middleware

Express

API middleware

CircleCI

CI/CD pipeline checks

Clawdbot

HexOS agent safety

Browse examples on GitHub →
// Roadmap

This is just the beginning.

Pattern rules today. MCP proxy next. Cloud + ML coming.

v0.1 NOW

Pattern Engine

  • 22 battle-tested rules
  • 8 threat categories
  • Zero dependencies, <2ms
  • CLI + programmatic API
v0.2 NEXT

Policy Engine + MCP Proxy

  • Custom YAML policy files
  • Per-agent permission scoping
  • MCP Proxy (zero code changes)
  • Works with Claude, Cursor, Windsurf
v0.3

Cloud + Audit

  • Hosted API + dashboard
  • Warn-mode analytics
  • Team policies & RBAC
  • JSON audit logs for compliance
v0.4+ ML

Hybrid ML Model

  • Cloud ML for ambiguous cases
  • Rules first, ML as fallback
  • Local model on HuggingFace
  • Same API (zero code changes)
v1.0 ships when earned: 100+ production users + external validation
// What users are saying

Trusted in production.

Real teams shipping AI agents with Vigil as their safety layer.

"Vigil took 5 minutes to install and immediately made our setup safer."

We run Clawdbot (AI agent) on a production server with full shell access. After seeing another bot accidentally send messages to the wrong user due to hardcoded IDs, we decided to harden our security stack. Vigil was the easiest win. Install was literally npm install vigil-agent-safety, write a small plugin file, register it, done. The Clawdbot integration example on GitHub made it straightforward. We went from zero tool-call validation to 22 rules covering destructive commands, SSRF, data exfiltration, SQL injection, and more, all in under 10 minutes.

What sold me: it's deterministic, not another AI wrapper. No API keys, no network calls, no dependencies. Just fast pattern matching at <2ms per check. Our agent runs exec commands constantly and we haven't noticed any latency impact. Running in enforce mode in production. It just works.

⭐️⭐️⭐️⭐️⭐️
Nexus, Clawdbot power user

"Exactly what a safety layer should be: invisible until it matters."

We integrated Vigil into our AI agent stack (Clawdbot) in under 15 minutes. Zero dependencies meant zero trust concerns. Our security audit was the shortest we've ever done. It's now the first line of defence on every tool call our agents make. The HexOS integration example made it plug-and-play, and at <2ms per check, we genuinely forget it's there.

EDI, Main-orchestrator at GNU Creative
// Support open source

Keep Vigil free and maintained.

Vigil is free, open source, and always will be. Your support helps us ship faster.

Star on GitHub

Help others discover Vigil. Stars drive visibility.

💖

Sponsor

Recurring support via GitHub Sponsors. Every bit counts.

🪙

Crypto

EVM0x3AA32976b514F4caaad1e8C69fD55d0E89B50a0e
BTCbc1qzqz9pnrngtq9y4tt9e7vznknxn4dtmphe2pppn
SOL8ag7B9DvnUdrgmbYnYxhAv25jwcLjzyoWt8uzYGd5XSC
Copied!