Alcyoneus OS Mark
AlcyoneusOSv1.1.0

Build IntelligentAgent Systems

Production-grade Python framework for building, orchestrating, and deploying multi-agent LLM systems with 100+ ready-to-use capabilities. Open-source, Apache 2.0 Licensed.

$pip install alcyoneus
quickstart.py
from alcyoneus.core import StateGraph, Agent, ToolNode
from alcyoneus.storage.checkpointer import InMemoryCheckpointer
graph = StateGraph()
graph.add_node("agent", Agent(model="gemini/gemini-2.5-flash", tool_node="tools"))
graph.add_node("tools", ToolNode([get_weather]))
graph.add_edge("agent", "tools")
graph.set_entry_point("agent")
compiled = graph.compile(checkpointer=InMemoryCheckpointer())
result = compiled.invoke({"messages": [{"role": "user", "content": "Weather in NYC?"}]})
100+
Capabilities
50+
Built-in Tools
3,230+
Tests Passing
3.12 | 3.13
Python Support
17 Phases
Hardened
Features

Production-Ready Capabilities

Everything you need to build, deploy, and scale intelligent agent systems — 17 production-hardening phases complete.

StateGraph Engine

LangGraph-inspired cyclic workflow engine with nodes, edges, dynamic routing via Command(goto=...), conditional branches, and subgraphs.

View docs

9 Prebuilt Agents & Swarms

ReactAgent, RAGAgent, SwarmAgent, SupervisorTeamAgent, PlanActReflectAgent, StructuredOutputAgent, and AudioAgent ready out of the box.

View docs

Realtime Audio & Voice

Gemini Live, OpenAI Realtime, Local Whisper+TTS with audio barge-in interruption, transcript persistence, and SIP telephony integration.

View docs

Sandboxing & Computer Use

8+ isolated backends (Docker, K8s, Firecracker micro-VMs, Daytona, E2B, Modal) with GUI Computer Use (X11/Wayland/VNC/WebRTC).

View docs

Open Protocols (MCP / A2A / ACP)

Model Context Protocol with Stdio/SSE/WebSocket transports, Starlette-based A2A server with agent cards, and ACP discovery.

View docs

50+ Built-in Tools

Search (7 providers + deduplication), browser automation, code interpreter, file I/O, image generation (DALL-E/Imagen/SDXL), and calendar tools.

View docs

3-Layer Persistence & Memory

In-memory state, Postgres + Redis checkpointers, QdrantStore, Mem0Store, and dynamic compaction policies for zero context overflow.

View docs

Enterprise Policy & Security

9-priority RBAC engine (allow/deny/ask_user), input/output guardrails with tripwire triggers, JWT/mTLS auth, and Vault secrets fallback.

View docs

alc CLI & Observability

Unified CLI for scaffolding, HTML/Mermaid graph visualization, replay debugging, OpenTelemetry auto-spans, and 15+ Prometheus metrics.

View docs
Interactive Code Architecture

Engineered for Production Velocity

From deterministic state graphs to realtime voice agents and multi-agent swarms. Explore authentic code patterns from the Alcyoneus OS framework.

graph_agent.py
import alcyoneus as alc
from alcyoneus.core import StateGraph, Agent, ToolNode, START, END
from alcyoneus.storage.checkpointer import InMemoryCheckpointer
from alcyoneus.prebuilt.tools import safe_calculator, google_web_search

# 1. Define custom domain tools
def check_inventory(sku: str) -> dict:
    """Check live warehouse stock for an SKU."""
    return {"sku": sku, "in_stock": True, "warehouse": "us-east-1"}

# 2. Build graph with Agent + ToolNode
graph = StateGraph()
graph.add_node("agent", Agent(model="gemini/gemini-2.5-flash", tool_node="tools"))
graph.add_node("tools", ToolNode([check_inventory, safe_calculator, google_web_search]))

# 3. Add cyclic execution edges
graph.add_edge("agent", "tools")
graph.add_edge("tools", "agent")
graph.set_entry_point("agent")

# 4. Compile with persistence
compiled = graph.compile(checkpointer=InMemoryCheckpointer())

# 5. Run stateful invocation
result = compiled.invoke(
    {"messages": [{"role": "user", "content": "Check stock for SKU-9821 and calculate tax at 8.5%"}]},
    config={"thread_id": "session-42"}
)
Deterministic flow with tool loops and checkpointing
Browse full examples on GitHub
Developer Experience

The alc CLI Power Tool

Manage your agent lifecycle with a single unified CLI. Scaffold state graphs, render visual diagrams, replay checkpoints, and deploy with confidence.

Install CLI Extras
pip install "alcyoneus[cli]"
bash — 80x24
$alc graph create multi-agent-pipeline --template swarm
✨ Initializing project 'multi-agent-pipeline'...
✔ Template 'swarm' selected (SwarmAgent + dynamic handoff router)
✔ Generated multi-agent-pipeline/graph.py
✔ Generated multi-agent-pipeline/config.yaml
✔ Configured InMemoryCheckpointer & OpenTelemetry spans
🚀 Graph scaffolded successfully! Run with: alc graph run graph.py
Status: ReadyExit Code: 0 (OK)
Documentation Hub

Comprehensive Technical Guides

Over 17 in-depth production guides, architecture specifications, and complete API references.

Getting Started

Quickstart

Build, compile, and run your first stateful AI agent graph in 5 minutes.

docs/QUICKSTART.mdRead →
Architecture

Core Patterns

StateGraph, nodes, cyclic edges, conditional routing, and Command(goto=...).

docs/CORE_PATTERNS.mdRead →
Agent Library

Prebuilt Agents

ReactAgent, RAGAgent, SwarmAgent, SupervisorTeamAgent, and AudioAgent.

docs/PREBUILT_AGENTS.mdRead →
Tool Registry

50+ Tools Guide

Multi-search (7 providers), browser automation, sandboxed shell, and code interpreter.

docs/TOOLS.mdRead →
Data Layer

Persistence & Memory

Postgres + Redis checkpointing, QdrantStore, Mem0Store, and dynamic compaction.

docs/PERSISTENCE.mdRead →
Realtime

Streaming & Events

15 streaming event types, SSE heartbeat keep-alives, and low-latency chunking.

docs/STREAMING.mdRead →
Enterprise

Security & Guardrails

9-priority RBAC policy engine, input/output guardrails, JWT/mTLS, and secret vaults.

docs/SECURITY.mdRead →
Standards

Protocols (MCP & A2A)

Model Context Protocol (Stdio/SSE/WS), Agent-to-Agent server, and ACP delegation.

docs/PROTOCOLS.mdRead →
Quality

Testing Framework

QuickTest one-liners, TestAgent simulation, MockLLM, and isolated test contexts.

docs/TESTING.mdRead →
Quality

Evaluation & CI

LLM-as-judge criteria, trajectory matching, hallucination detection, and simulators.

docs/EVALUATION.mdRead →
Reference

All Imports Reference

Complete index of all classes, decorators, constants, and utilities in alcyoneus.

docs/IMPORTS.mdRead →
Troubleshooting

Common Gotchas & Fixes

Solutions for recursion limits, checkpoint deserialization, and multi-tenant scoping.

docs/GOTCHAS.mdRead →
Get Started

Start Building Today

Install the framework in seconds and start building intelligent agents with 100+ production-grade capabilities.

$pip install alcyoneus