Developer Portal — Internal Alpha

Build on LYDOS Agent OS

109 agents, 245 Q-engines, 128+ routers, 162 MCP tools. Internal alpha running on lydos.ailydian.com. This reference documents the real subsystems and extension points.

Checking status...
109Agents (13 Python + 99 YAML)
245Q-Engines
128+API Routers
162MCP tools
29Health-monitored modules
4LLM providers
Architecture Map

Subsystem layers

Every layer that processes a request from client to infrastructure.

Client Layer
LYD CLI (./lyd) · REST API (curl/httpx) · MCP server (162 tools) · Next.js frontend (localhost:3001)
API Gateway — FastAPI (port 8888)
Rate limiter · Circuit breaker · Security hardening (industry standards) · Q63 JWT auth (optional) · CORS
Q-Series Engines (Q1–Q248, 128+ registered routers)
Q25 Plugin · Q26 DAG Workflow · Q29 Agent Hub · Q34 Research · Q43 LLM Routing · Q62 WS Dashboard · Q158 Autonomous Engineering · Q163 Distributed Mesh · Q194 Persistence · Q195 Scaling …
Agent Layer — 109 agents (13 Python + 99 YAML)
harika_agent · harika_supreme · harika_ultra_team · ecosystem_agents · 99 YAML-defined agents (config/agents.yaml)
LLM Router (Q43) — 4 provider priority chain
Primary Provider llama-3.3-70b-versatile (PRIMARY) → Bilingual Provider (FALLBACK) → Analysis Provider Sonnet (BACKUP) → Cloud Provider-32B ($0/mo)
LYD v3.0 Orchestration
Hedef Motoru (23 goals) · Kalıp Motoru (pattern engine) · Voice Engine (speech recognition STT) · Memory consolidation · Auto cross-project sync
Infrastructure
Embedded database WAL (dev) · Relational database+asyncpg (prod) · Cache layer (cache) · Message queue (distributed tasks) · WebSocket Hub (Q62) · Semantic memory (TF-IDF) · Observability (trace collector + metrics engine + structlog)
Runtime Modes

Monolith vs Distributed

Choose the mode that matches your deployment target. Both run the same agent and engine code.

Monolith

Default
LYDOS_MODE=monolith

Single Python process handles all routing, agent execution, and LLM calls. SQLite WAL for task queue and state. No external services required.

Advantages

  • Zero-dependency startup (only .env required)
  • All 29 modules and 109 agents available immediately
  • Full LYD CLI and MCP server included
  • Suitable for development and single-user production

Constraints

  • Agent scheduler capped at 10 concurrent tasks
  • No worker horizontal scaling
  • SQLite not suitable for multi-user production load
Start:
python3 server.py

Distributed

Alpha
LYDOS_MODE=distributed

Control-plane node handles API and task routing. Worker nodes pull tasks from message queue and execute agents in parallel. Relational database + cache layer for durable state.

Advantages

  • Horizontal worker scaling (container compose --scale lydos-worker=N)
  • Durable task queue via message queue with at-least-once delivery
  • Relational database for multi-user state and audit trails
  • Cache layer for low-latency cache (Q194 Persistent State)

Constraints

  • Requires container runtime + Compose
  • Message queue cluster is single-node (no TLS) in alpha
  • Higher startup complexity
Start:
docker compose -f docker-compose.alpha.yml up -d --scale lydos-worker=3
Transport / Queue / Consensus

How data moves through LYDOS

Every communication channel documented with the actual implementation.

HTTP
FastAPI + httpx

All REST API calls. Async request handling with retry logic in the http_client module (circuit breaker, exponential backoff).

WebSocket
FastAPI WebSocket + Q62 Hub

Real-time agent status, health score stream, task updates. Pub/sub channels via websocket_hub. Connect at wss://lydos.ailydian.com/api/q62/dashboard/ws.

Task Queue
SQLite (monolith) / NATS JetStream (distributed)

Priority queue with retry and dead-letter support via task_queue module. Distributed mode uses NATS JetStream streams for at-least-once delivery.

MCP
STDIO transport (core/infrastructure/mcp_server.py)

162 MCP tools exposed to Claude Code, Cursor, Windsurf, or any MCP client. Launch via: ~/.ailydos-venv/bin/python3 core/infrastructure/mcp_server.py --transport stdio

Voice
Speech Recognition STT

Speech-to-text via multi_stt_engine. Activated via ./lyd listen N or POST /api/voice/transcribe. Requires microphone access and PRIMARY_API_KEY.

Inter-agent RPC
Q22 Agent Bus

In-process RPC between agents with circuit breaker and deadlock detection. Q29 Agent Hub delegates tasks using FC/ReAct/Plan-Execute/CoT strategies.

Consensus (future)
Message Queue KV + Distributed State Sync (Q163)

Q163 Distributed Mesh provides 5 load-balancing strategies and distributed state sync. Single-node in alpha — multi-node consensus not yet enabled.

Module Inventory

29 active modules

Modules are health-monitored at GET /api/health. Overall score: 94/100 in the latest alpha run.

Core modules4

kernel_loader, config_manager, error_handler, self_healing_engine

Agent modules4

agent_manager, harika_agent, harika_supreme, harika_ultra_team

LLM modules5

primary_api, llm_router, primary_full_client, bilingual_client, analysis_api

v7 infra modules11

rate_limiter, http_client, circuit_breaker, db_pool, observability, agent_scheduler, task_queue, websocket_hub, multi_stt_engine, semantic_memory, security_hardening, cuda_agent

Infra modules2

mcp_server (162 tools), nim_llm_client

Deps1

python_dependencies (7/7 checked)

Q-Engine Catalogue

245 Q-Series engines

Each engine registers its own FastAPI router under /api/q{N}/* in server.py.

Q25–Q40
16 engines

Plugins, DAG workflows, session intel, GEO-SEO, agent hub, skill library, CTI, bug bounty, hooks, research, visual automation

Q41–Q59
19 engines

TTS (23 languages), eval loop, adaptive LLM routing, code evolution, goal execution, MCP gateway, code graph, critic, benchmark, swarm, multimodal, meta-engine

Q60–Q71
12 engines

Git worktree isolation, CI/CD bridge, WS dashboard, multi-user JWT, hardware OBD-II, governance, context optimizer, reliability cert, cost intelligence, federated learning, marketplace

Q72–Q100
29 engines

Specialized agents: social, email, browser automation, file, calendar, finance, IoT, healthcare, legal, education, and more

Q101–Q140
40 engines

8 categories: Language/Platform, IDE, Cloud, Data/AI, Security, Industry, Communication, Embedded

Q141–Q158
18 engines

Production audit, anomaly detection, root cause, auto-remediation, WAF/threat intel, SEO sentinels (7 types), user command interpreter, DB/CDN/e-commerce sentinels, compliance, performance, cross-site intel, orchestrator, AI chat assistant, user consciousness, autonomous engineering

Q159–Q178
20 engines

Universal LLM gateway, visual canvas, A2A bridge, MCP mega-gateway (30 MCP servers), distributed mesh, self-modification engine, cognitive planner, temporal reasoning, predictive tasks, cross-project intel, AIOS kernel, self-verification, emergent behavior, marketplace, NL OS, agent dreaming, auto-docs, SDK gen, demo sandbox, telemetry

Q179–Q192
14 engines

Autonomous consciousness: global workspace, metacognition, adaptive memory, attention schema, reputation, proactive tasks, permission matrix, ADR records, active inference, safety policy guard, DAG re-planner, motivation state, transparent execution, skill transfer

Q193–Q213
21 engines

Security fortress, persistent state (relational+cache+embedded), horizontal scaling (container orchestrator), API docs, feedback analytics, skill factory, schema drift monitor, cross-platform adapter, user workspace, compliance engine, agent economy, Google OAuth, user settings, multimodal workspace, real-time collab, memory graph, smart caching, workflow templates, API versioning, batch processing, health aggregator

Q214–Q220
7 engines

Advanced intelligence: neuro-symbolic reasoning, causal discovery, counterfactual simulation, embodied agent bridge, meta-learning optimizer, emergent communication, quantum-inspired optimizer — registered, not fully production-validated

Q222–Q232
11 engines

Durable state recovery, event-triggered automation, token-accurate context condenser, agent tournament ranked scoring, SOC 2 compliance, public MCP registry (20 built-in), visual workflow designer, multi-region edge deploy, auto-approval engine, code agent engine, external API bridge

Q240–Q248
9 engines

Wireless recon (WiFi/OUI/HMAC audit), edge device manager, token optimizer, sandbox hardening, GitHub OAuth (Device Flow + PKCE), magic link & OTP auth, test synthesis, PR lifecycle management, migration engine with dry-run and rollback

Full endpoint listing with request/response schemas:

API Reference →
Developer Workflow

From clone to running

Real commands that work against the actual codebase.

Local development workflow — start, verify, test

dev-workflow.sh
Bash
1# 1. Start the server (in one terminal)
2source ~/.ailydos-venv/bin/activate
3cd ~/Masaüstü/AILYDIAN-AGENT-OS
4python3 server.py
5 
6# 2. Verify it's alive (in another terminal)
7curl -s https://lydos.ailydian.com/api/health | python3 -m json.tool
8 
9# 3. Run the frontend (optional)
10cd web && npm run dev
11# → http://localhost:3001
12 
13# 4. Use the LYD CLI
14./lyd status # system overview
15./lyd hedef # goal hierarchy
16./lyd tasks # today's tasks
17 
18# 5. Run tests
19source ~/.ailydos-venv/bin/activate
20python3 -m pytest tests/test_core.py tests/test_agent_manager.py -v
21 
22# 6. Test a specific Q-engine
23curl -s https://lydos.ailydian.com/api/q26/workflow/status | python3 -m json.tool
24curl -s https://lydos.ailydian.com/api/q43/routing/status | python3 -m json.tool
25 
26# 7. Test MCP server standalone
27~/.ailydos-venv/bin/python3 core/infrastructure/mcp_server.py --transport stdio
Extension Points

How to extend LYDOS

Six ways to add capabilities without modifying core infrastructure.

New Q-engine

core/engines/q_new_engine.py + core/routes/q_new_route.py

Add a FastAPI router in core/routes/, implement the engine in core/engines/, and register the router in server.py with app.include_router(). The health system picks it up automatically if the module defines a get_health() function.

YAML agent

config/agents.yaml

Append an agent definition (name, description, system_prompt, tools, category) to config/agents.yaml. The agent_manager loads all YAML agents at startup — no code change required.

Python agent

core/agents/my_agent.py

Implement a class that follows the BaseAgent interface (run, health methods). Register it in core/agents/__init__.py. agent_manager will include it in the total agent count.

MCP tool

core/infrastructure/mcp_server.py

Add a new @mcp_tool decorated function. The tool becomes immediately available to AI IDEs, Cursor, and any other MCP client after restarting the MCP server process.

AI IDE skill

~/.claude/skills/ or config/skills/

Create a .md skill file following the LYDOS skill format. The skill becomes available via the /skill-name command in AI IDE sessions. 87 skills are currently bundled.

Hook

hooks/

LYDOS uses 11 hooks: session-start.sh (auto-start server, health cache write), post-compact.sh (goal/health injection), pre-tool-use, and others. Add custom logic here for session lifecycle events.

MCP Integration

162 MCP tools

Expose all LYDOS capabilities to AI IDEs, Cursor, Windsurf, and any MCP-compatible client.

.mcp.json configuration

.mcp.json
JSON
// Place in project root or ~/.config/claude/mcp.json
{
"mcpServers": {
"lydos": {
"command": "~/.ailydos-venv/bin/python3",
"args": [
"core/infrastructure/mcp_server.py",
"--transport",
"stdio"
]
}
}
}

Tool categories

Agent managementrun_agent, list_agents, get_agent_status
LLM chatprimary_chat, llm_chat, stream_response
Q-engine callsq26_workflow, q34_research, q43_routing, ...
Memorystore_memory, search_memory, consolidate
Healthsystem_health, module_status
Taskssubmit_task, get_task, cancel_task
Securitysecurity_scan, validate_input
Alpha Caveats

What is and is not available

Honest account of the current alpha state for developers integrating with LYDOS.

AVAILABLE

Available now

  • Full REST API on https://lydos.ailydian.com
  • 109 agents (13 Python + 99 YAML)
  • Q25–Q248 beta-stage engines
  • 162 MCP tools via STDIO transport
  • 4 LLM provider chain (Primary Provider)
  • LYD CLI (./lyd) for system management
  • WebSocket real-time monitoring (Q62)
  • Distributed cluster via container-compose.alpha.yml
  • Next.js frontend at localhost:3001
NOT YET

Not yet available

  • Python SDK (in development)
  • TypeScript SDK (in development)
  • Hosted API (lydos.ailydian.com)
  • Public repository (currently private)
  • Q214–Q220 fully production-validated
  • Multi-node message queue cluster with TLS
  • SOC 2 certification (roadmap Phase 4)
  • Public MCP registry (Q227) — alpha only
  • VS Code extension on Marketplace

Detailed constraint list with workarounds:

Internal Alpha Guide →

Start building on LYDOS

Server is at https://lydos.ailydian.com. Clone the private repo, activate the venv, and run python3 server.py.