CA: 4d5YyfR2BMWoCciwHZaZiWZmM7mtkwADvdJ3sKe7pump

Syra Network

The Intelligence Layer for Autonomous AI Agents

Production-ready AI agent platform with multi-LLM support, real-time dashboard, Python SDK, and CLI.

Quick Start · Documentation · Features · API Reference · Contributing

---

What is Syra Network?

Syra Network is a comprehensive AI agent platform that enables developers to build, deploy, and manage autonomous AI agents with ease. It provides seamless integration with 100+ LLM providers, built-in tools, and an extensible MCP (Model Context Protocol) server architecture.

Key Highlights

Feature	Description
🔗 Multi-LLM Support	Access 100+ models via OpenAI, Anthropic, Ollama, OpenRouter
🎯 Smart Task Management	Create, decompose, and execute complex tasks automatically
🛠️ MCP Integration	Connect to 30+ pre-configured MCP servers or build your own
📊 Real-time Dashboard	Monitor agent activities and task progress live
🔌 Python SDK	Simple, intuitive API for programmatic access
💻 Full CLI	Complete command-line interface for power users
🌐 On-chain Deployment	Deploy agents to ERC-8004 registries on Ethereum/Base

---

Architecture Overview

flowchart LR
    subgraph Clients["🖥️ Clients"]
        Dashboard["Dashboard<br/>Next.js"]
        SDK["Python SDK"]
        CLI["CLI"]
    end
    subgraph Core["⚡ Syra Core"]
        API["FastAPI Server"]
        subgraph Services["Services"]
            LLM["LLM Service<br/>100+ models"]
            Runner["Agent Runner"]
            Executor["Task Executor"]
        end
        subgraph Tools["Built-in Tools"]
            T1["📂 File Ops"]
            T2["🔍 Web Search"]
            T3["💻 Code Exec"]
        end
    end
    subgraph Agents["🤖 AI Agents"]
        A1["Researcher"]
        A2["Coder"]
        A3["Writer"]
        A4["Analyst"]
    end
    subgraph Storage["💾 Storage"]
        DB[("SQLite")]
        WS["Workspace<br/>Files"]
    end
    Clients -->|"REST / WebSocket"| API
    API --> Services
    Services --> Tools
    Runner --> Agents
    Services --> Storage
    style Clients fill:#dbeafe,stroke:#2563eb
    style Core fill:#fef9c3,stroke:#ca8a04
    style Services fill:#fff7ed,stroke:#ea580c
    style Tools fill:#f0fdf4,stroke:#16a34a
    style Agents fill:#fdf4ff,stroke:#a855f7
    style Storage fill:#f1f5f9,stroke:#64748b

---

Features

Core Capabilities

Feature	Description
🔗 Multi-LLM Support	OpenAI, Anthropic, Ollama, and 100+ providers via LiteLLM
🔄 Task Decomposition	Automatically break complex tasks into subtasks
📁 Workspace Management	Full file operations within task workspaces
🔍 Web Search	Integrated search capabilities for research agents
💻 Code Execution	Safe sandboxed code execution for coding tasks
🌐 On-chain Registry	Deploy agents to ERC-8004 identity registries

MCP Server Integration

Syra supports the Model Context Protocol (MCP) for unlimited tool extensibility:

Preset	Description
Filesystem	File and directory operations
GitHub	Repository, issues, and PR management
Brave Search	Web search capabilities
Puppeteer	Browser automation
PostgreSQL	Database queries and management
Memory	Persistent knowledge graph

---

Quick Start

Installation

# Clone the repository
git clone https://github.com/mukkuul976/syra.git
cd syra

# Install the package
pip install -e .

# Set your LLM API key (recommended: OpenRouter for all models)
export SYRA_OPENROUTER_API_KEY=sk-or-v1-...

Start the Server

# Start API server + Dashboard
syra server start

# Start without dashboard
syra server start --no-dashboard

# Custom ports
syra server start --port 9000 --dashboard-port 3001

Using the CLI

# List available models
syra models

# Create a network
syra network create "My Workspace"

# Create an agent
syra agent create --name "Research Assistant" --network <network_id> --model openrouter/openai/gpt-5.1

# Run a task
syra task create "Research the latest AI trends" --network <network_id> --wait

# Task management
syra task list
syra task status <task_id>
syra task decompose <task_id>
syra task run-all <task_id>
syra task continue <task_id> "more info"

# Deploy agent on-chain (ERC-8004)
export SYRA_PRIVATE_KEY=0xabc...
export SYRA_ETH_SEPOLIA_RPC=https://sepolia.rpc.provider
syra agent deploy <agent_id> --chain eth-sepolia

Using the Python SDK

from syra import SyraClient

# Connect to local server
with SyraClient(base_url="http://localhost:8000") as client:
    # Check available models
    models = client.config.get_models()
    print(f"Available models: {len(models['models'])}")

    # Create a network
    network = client.networks.create(name="Research Lab")

    # Create an agent
    agent = client.agents.create(
        name="Research Assistant",
        network_id=network["id"],
        model="openrouter/openai/gpt-5.1",
        role="researcher"
    )

    # Run a task and wait for result
    task = client.tasks.create(
        network_id=network["id"],
        description="What are the key benefits of AI agents?"
    )
    result = client.tasks.wait(task["id"])
    print(result["result"]["output"])

    # Decompose complex tasks
    complex_task = client.tasks.create(
        network_id=network["id"],
        description="Build a web scraper",
        run_mode="decompose"
    )
    subtasks = client.tasks.get_subtasks(complex_task["id"])
    client.tasks.run_all_subtasks(complex_task["id"])

---

Project Structure

syra/
├── syra/
│   ├── server/          # FastAPI backend
│   │   ├── models/      # SQLAlchemy models
│   │   ├── schemas/     # Pydantic schemas
│   │   ├── api/         # API routes
│   │   ├── services/    # LLM, task executor
│   │   └── tools/       # Built-in tools
│   ├── client/          # Python SDK
│   └── cli/             # CLI commands
├── dashboard/           # Next.js frontend
└── examples/            # Example scripts

---

CLI Reference

Server Commands

Command	Description
syra server start	Start API server and dashboard
syra server start --reload	Start with auto-reload
syra health	Check API health

Network Commands

Command	Description
syra network create <name>	Create a new network
syra network list	List all networks
syra network get <id>	Get network details
syra network delete <id>	Delete a network

Agent Commands

Command	Description
syra agent create	Create a new agent
syra agent list	List all agents
syra agent get <id>	Get agent details
syra agent update <id>	Update an agent
syra agent sleep <id>	Put agent offline
syra agent wake <id>	Wake agent up
syra agent deploy <id>	Deploy to ERC-8004

Task Commands

Command	Description
syra task create <desc>	Create and run a task
syra task list	List tasks
syra task status <id>	Check task status
syra task decompose <id>	Break task into subtasks
syra task run-all <id>	Run all subtasks
syra task continue <id>	Continue a task
syra task cancel <id>	Cancel a task

MCP Commands

Command	Description
syra mcp list	List MCP servers
syra mcp add	Add a new MCP server
syra mcp connect <name>	Connect to server
syra mcp tools <name>	List tools from server
syra mcp catalog	Browse MCP server presets
syra mcp install <id>	Install preset from catalog

---

API Reference

Endpoints Overview

Method	Endpoint	Description
GET	/api/v1/networks	List networks
POST	/api/v1/networks	Create network
GET	/api/v1/agents	List agents
POST	/api/v1/agents	Create agent
PUT	/api/v1/agents/{id}	Update agent
GET	/api/v1/tasks	List tasks
POST	/api/v1/tasks	Create & run task
POST	/api/v1/tasks/{id}/decompose	Decompose into subtasks
POST	/api/v1/tasks/{id}/run-all	Run all subtasks
GET	/api/v1/mcp/	List MCP servers
POST	/api/v1/mcp/	Create MCP server
GET	/api/v1/mcp/{id}/tools	Get MCP server tools
WS	/ws	WebSocket for real-time updates

SDK Resources

from syra import SyraClient
client = SyraClient(base_url="http://localhost:8000")

# Available resources:
client.networks      # Network management
client.agents       # Agent management
client.tasks         # Task management
client.tools         # Tool listing
client.config        # Configuration & models
client.workspace     # File operations
client.mcp           # MCP server integration

---

Configuration

Environment Variables

# LLM API Keys
SYRA_OPENROUTER_API_KEY=sk-or-v1-...   # Recommended: access all models
SYRA_OPENAI_API_KEY=sk-...
SYRA_ANTHROPIC_API_KEY=sk-ant-...

# Local LLM
SYRA_OLLAMA_BASE_URL=http://localhost:11434

# Default Model
SYRA_DEFAULT_MODEL=openrouter/openai/gpt-5.1

# Server Configuration
SYRA_HOST=0.0.0.0
SYRA_PORT=8000
SYRA_DATABASE_URL=sqlite:///./syra.db

# Dashboard
SYRA_DASHBOARD_PORT=3000
SYRA_AUTO_OPEN_BROWSER=true

# Blockchain (for ERC-8004 deployment)
SYRA_PRIVATE_KEY=0xabc...
SYRA_ETH_SEPOLIA_RPC=https://sepolia.rpc.provider
SYRA_BASE_SEPOLIA_RPC=https://base-sepolia.rpc.provider
SYRA_IPFS_API_TOKEN=pinata_jwt

---

Development

Running in Development Mode

# Start with auto-reload
syra server start --reload

# Or run components separately
uvicorn syra.server.main:app --reload --port 8000
cd dashboard && npm run dev

Running Tests

pip install -e ".[dev]"
pytest

---

Documentation

📚 Comprehensive documentation is available:

Document	Description
Architecture	Technical architecture and data flow
User Guide	How to use Syra Network effectively
API Reference	Detailed API documentation

---

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

---

License

This project is licensed under the MIT License - see the LICENSE file for details.

---