---
slug: "lyrie-ai"
source_type: "readme"
source_url: "https://cdn.jsdelivr.net/gh/ott-cybersecurity-llc/lyrie-ai@main/README.md"
repo: "https://github.com/ott-cybersecurity-llc/lyrie-ai"
source_file: "README.md"
branch: "main"
---
# ๐ก๏ธ Lyrie
### The autonomous security agent.
_Pentests apps. Defends agents. Researches binaries. Trains itself. One daemon._
[](LICENSE)
[](https://pypi.org/project/lyrie-omega/)
[](https://www.npmjs.com/package/@lyrie/atp)
[](https://research.lyrie.ai)
[](https://atp.lyrie.ai)
[](https://x.com/lyrie_ai)
[**Install**](#-install) ยท [**Quick Start**](#-quick-start) ยท [**Commands**](#-commands) ยท [**ATP**](#-atp-agent-trust-protocol) ยท [**Security**](https://github.com/ott-cybersecurity-llc/lyrie-ai/blob/HEAD/SECURITY.md)
---
## ๐ What's New in v3.1.0
- **Memory Encryption**: XChaCha20-Poly1305 implementation for sensitive threat data (`@noble/ciphers`)
- **7 New PoC Generators**: prompt injection, auth bypass, CSRF, open redirect, race condition, secret exposure, XXE
- **3 New Deep Scanners**: Rust analysis, taint engine, AI deep analysis
- **UI Workspace Fix**: Proper `@lyrie/atp` workspace resolution
- **Expanded Test Suite**: 1,737 tests passing across `@lyrie/atp`, `@lyrie/core`, `@lyrie/gateway`, `@lyrie/mcp`, `@lyrie/ui`
- **New Security Modules**: Domain verification, ML-based threat classifier, URL guardianship
- **Fully backward compatible** with v3.0.0 โ no migration required
See [CHANGELOG.md](https://github.com/ott-cybersecurity-llc/lyrie-ai/blob/HEAD/CHANGELOG.md) for the complete list.
---
## What is Lyrie?
Lyrie is an autonomous security agent built by [OTT Cybersecurity LLC](https://overthetop.ae). It runs end-to-end pentests, red-teams LLM endpoints, scans code and live URLs, and ships with the **Agent Trust Protocol (ATP)** โ the first open cryptographic standard for AI agent identity.
**Two installs, one tool:**
| Component | Language | Install | What it does |
|---|---|---|---|
| **`lyrie-omega`** | Python | `pip install lyrie-omega` | CLI for scanning, pentesting, red-teaming, governance |
| **`@lyrie/atp`** | TypeScript/Node | `npm install @lyrie/atp` | Agent Trust Protocol SDK โ cryptographic agent identity |
---
## ๐ Install
```bash
# Option 1: one-line installer (installs both)
curl -sSL https://lyrie.ai/install.sh | bash
# Option 2: install separately
pip install lyrie-omega
npm install @lyrie/atp
```
After install:
```bash
lyrie init # one-time setup wizard
lyrie doctor # verify everything works
```
---
## โก Quick Start
```bash
# Scan a live URL for security misconfigurations
lyrie scan https://app.example.com
# Run a 7-phase autonomous pentest
lyrie hack https://app.example.com
lyrie hack ./myapp # local source tree
lyrie hack ./myapp --stage scan --output report.json
# AI red-team an LLM endpoint
lyrie redteam https://api.openai.com/v1/chat --strategy crescendo --dry-run
# Check CVSS score
lyrie cvss 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'
# Self-diagnostic
lyrie doctor
```
---
## ๐ Commands
All 25 commands are real and tested. Run `lyrie --help` for details.
### Core security
```bash
lyrie hack # 7-phase autonomous pentest (URL or local path)
lyrie scan # Scan file/dir/URL for vulnerabilities
lyrie redteam # AI red-team an LLM endpoint
lyrie cvss # CVSS v3.1 scoring
lyrie exploit --cve # SMT-backed exploit feasibility
lyrie validate --target # Agentic exploitability validation
lyrie intel --repo # GitHub OSS forensics evidence collection
lyrie smt --check # Z3 SMT solver interface
```
### Binary analysis (Omega)
```bash
lyrie omega analyze # Static binary analysis
lyrie omega rop # ROP gadget search
lyrie omega smt # SMT constraint analysis
lyrie omega replay # Replay recorded session
```
### Identity & trust (ATP)
```bash
lyrie atp verify # Verify agent identity + scope
lyrie atp badge --show # Display compliance badge
lyrie atp receipt # Audit trail for a session
```
### Operations
```bash
lyrie init # First-time setup wizard
lyrie doctor # Self-diagnostic (env, deps, keys, network)
lyrie auth setup # Configure API keys interactively
lyrie auth set --key NAME # Set a specific key (prompts securely)
lyrie auth list # Show configured keys (redacted)
lyrie config show # Show config file contents
lyrie config path # Print config file path
```
### Automation & lifecycle
```bash
lyrie daemon --threat-watch # Continuous threat detection
lyrie service install # Install as system service (launchd/systemd)
lyrie service status # Service status
lyrie cron list # List scheduled jobs
lyrie cron add "*/5 * * * *" "lyrie scan https://example.com"
```
### Governance & compliance
```bash
lyrie governance assess --interactive # NIST AI RMF 8-question assessment
lyrie governance permissions tools.json # Audit tool permissions for risk
lyrie tools audit # Risk assessment of installed tools
lyrie memory integrity-check # Detect tampered memories
```
### Self-improvement
```bash
lyrie evolve dream # Full cycle: score โ extract โ prune โ summarize
lyrie evolve stats # Domain breakdown
lyrie evolve train --export atropos # Export training data
```
### Models & migration
```bash
lyrie models list # List available LLM aliases
lyrie models route # Show routing decision (cyber, code, seo, trading)
lyrie models health # Health-check all model providers
lyrie migrate --detect # Auto-detect existing agent platforms
lyrie migrate --from openclaw # Import from another platform
```
### Skills
```bash
lyrie skills list # List installed skills
lyrie skills search # Search skill library
lyrie skills install # Install a skill
lyrie skills run # Execute a skill
```
---
## ๐ก๏ธ Capabilities
### Autonomous pentesting (`lyrie hack`)
7-phase pipeline: **recon โ fingerprint โ scan โ exploit โ PoC โ report**.
Works on live URLs and local source trees. Outputs SARIF for GitHub Code Scanning.
### URL security scan (`lyrie scan `)
Checks every site for:
- Security headers (CSP, HSTS, X-Frame-Options, etc.)
- TLS version and cert expiry
- Common exposed paths (`.env`, `.git/config`, `/admin`, etc.)
- Server version disclosure
### AI red-teaming (`lyrie redteam`)
5 attack strategies against LLM endpoints:
- **crescendo** โ gradual escalation
- **tap** โ tree-of-attacks-with-pruning
- **pair** โ prompt automatic iterative refinement
- **gcg** โ gradient-based suffix attack (full: H200 required)
- **autodan** โ genetic algorithm black-box (full: GPU required)
### Agent Trust Protocol (ATP)
Open cryptographic standard for AI agent identity. Ed25519 signatures, delegation chains, revocation lists, multisig. Spec at [atp.lyrie.ai](https://atp.lyrie.ai). 143 tests passing.
### Lyrie Shield (Rust)
Production-grade security engine: hash-signature scanning, heuristic analysis, WAF, rogue-AI detector. 31 tests passing.
---
## ๐ ATP โ Agent Trust Protocol
The first open cryptographic standard for AI agent identity. Think TLS for agents.
```typescript
import { issueCertificate, verifyAic } from '@lyrie/atp';
// Issue a scoped certificate
const aic = await issueCertificate({
subjectPublicKey: agentPubKey,
scope: { tools: ['scan', 'read'], maxBudget: 100 },
issuerPrivateKey: rootKey,
ttlSeconds: 3600,
});
// Verify it
const result = await verifyAic(aic, trustAnchor);
if (result.valid) {
// Agent is authorized
}
```
Full spec: **[atp.lyrie.ai](https://atp.lyrie.ai)** ยท [Whitepaper PDF](https://atp.lyrie.ai/atp-whitepaper.pdf)
---
## ๐ Configuration
```bash
# Interactive setup
lyrie auth setup
# Or set individual keys
lyrie auth set --key ANTHROPIC_API_KEY # prompts securely (no shell history)
lyrie auth set --key OPENAI_API_KEY
lyrie auth set --key GITHUB_TOKEN
# View configured keys (redacted)
lyrie auth list
```
Keys are stored at `~/.lyrie/config.json` with `chmod 600` (user-only).
Known keys: `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `GITHUB_TOKEN`, `LYRIE_LICENSE_KEY`, `CODEQL_CLI`, `CODEQL_QUERIES`.
---
## ๐๏ธ Architecture
```
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ lyrie CLI โ
โ (Python โ lyrie-omega, this repo) โ
โโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโดโโโโโโโโโโ
โผ โผ
โโโโโโโโโโโโ โโโโโโโโโโโโโโโโ
โ omega โ โ @lyrie/atp โ
โ engine โ โ (Node.js) โ
โ (Rust + โ โ โ
โ Python) โ โ Ed25519 โ
โ โ โ delegation โ
โ CodeQL, โ โ revocation โ
โ SMT, ROP โ โ multisig โ
โโโโโโโโโโโโ โโโโโโโโโโโโโโโโ
```
- **`packages/atp/`** โ TypeScript Agent Trust Protocol SDK (npm: `@lyrie/atp`)
- **`packages/omega-suite/`** โ Python CLI + analysis engines (PyPI: `lyrie-omega`)
- **`packages/shield/`** โ Rust security scanner (WAF + rogue-AI + threat scoring)
---
## โ
Quality
- **ATP:** 143 tests passing
- **Core:** 1,455 tests passing (memory, pentest, scanners, PoC-gen, threat-intel, providers)
- **Gateway:** 74 tests passing
- **MCP:** 12 tests passing
- **UI:** 53 tests passing
- **Shield:** 31 tests passing
- **CLI:** 25 commands, all functional
- **Security audit:** 39 findings closed (see [SECURITY.md](https://github.com/ott-cybersecurity-llc/lyrie-ai/blob/HEAD/SECURITY.md))
---
## ๐ Links
- **Platform:** [lyrie.ai](https://lyrie.ai)
- **ATP Spec:** [atp.lyrie.ai](https://atp.lyrie.ai)
- **Research:** [research.lyrie.ai](https://research.lyrie.ai)
- **PyPI:** [pypi.org/project/lyrie-omega](https://pypi.org/project/lyrie-omega/)
- **npm:** [npmjs.com/package/@lyrie/atp](https://www.npmjs.com/package/@lyrie/atp)
- **GitHub:** [github.com/OTT-Cybersecurity-LLC/lyrie-ai](https://github.com/OTT-Cybersecurity-LLC/lyrie-ai)
- **Twitter/X:** [@lyrie_ai](https://x.com/lyrie_ai)
- **Contact:** [guy@lyrie.ai](mailto:guy@lyrie.ai)
---
**Lyrie.ai** โ A project of **OTT Cybersecurity LLC** ยท Dubai, UAE
MIT License ยท ยฉ2026