LYDOS Documentation
Everything you need to build with the LYDOS AI Agent OS. From a 5-minute quickstart to a deep-dive into the Q-engine architecture and the full REST API surface.
Quick links
Instant start
LYDOS runs as a local FastAPI server on port 8888. No public PyPI or npm packages exist yet — set up by cloning the private repo:
# Clone the private repository (SSH recommended)
git clone [email protected]:lydianai/AILYDIAN-AGENT-ORCHESTRATOR.git
cd AILYDIAN-AGENT-ORCHESTRATOR
# Create venv and install dependencies
python3 -m venv ~/.ailydos-venv
source ~/.ailydos-venv/bin/activate
pip install -r requirements.txt
# Configure API keys
cp .env.example .env # then edit .env with your PRIMARY_API_KEY
# Start the server
python3 server.py
# → Server running at http://localhost:8888# Verify the server is healthy
curl -s http://localhost:8888/api/health | python3 -m json.tool
# List available agents
curl -s http://localhost:8888/api/agents | python3 -m json.tool | head -30
# Send a chat message
curl -s -X POST http://localhost:8888/api/llm/chat \
-H "Content-Type: application/json" \
-d '{"prompt": "What is LYDOS?"}' | python3 -m json.toolDocumentation sections
Getting Started
Clone the repo, activate the venv, start the server, and verify the health check in under 5 minutes.
API Reference
Complete reference for all 128+ registered routers — health, agents, chat, memory, and every Q-engine route.
Agents Guide
Learn how to list, run, configure, and build your own YAML agents from the 109 registered agent catalog.
Q-Engine Catalog
Browse all 245 Q-Series engines from Q1 through Q248 — each with endpoint prefix, description, and code examples.
SDK Reference
Python SDK (coming soon) and TypeScript SDK (in development). Currently the server is accessed via the REST API or CLI directly.
CLI Reference
Command-line interface for health checks, agent execution, streaming chat, task management, and workflow DAG runs.
Architecture
Deep-dive into the layered system design: FastAPI core, 29 modules, Q-engine plugin system, 4-tier LLM failover, and AIOS kernel.
Use Cases
End-to-end examples: security scanning, deep research, compliance audits, code evolution, workflow automation, and multi-agent orchestration.
LLM Providers
4-tier failover chain: Primary Provider, Bilingual Provider (fallback), Analysis Provider (backup), and Cloud Provider ($0/month).
MCP Setup
Connect AI IDEs, Cursor, Windsurf, and any MCP-compatible IDE to 162 LYDOS tools via a single .mcp.json config.
Security
Q32 Bug Bounty, Q48 Confinement Engine, Q65 Enterprise Governance, Q193 Security Fortress, and EU AI Act compliance via Q186/Q202.
CI/CD & DevOps
Q60 worktree isolation, Q61 CI/CD Bridge, Q195 Horizontal Scaling, Q219 Autonomous DevOps — full pipeline automation.
Need help?
Check the Getting Started guide first, then browse the API Reference or explore the Q-Engine Catalog. For enterprise support and SLAs visit the Enterprise page.