Templates
Information about project templates and common configurations.
Default Project#
When you run create-astreus-agent, you get an interactive setup that generates a project based on your selections.
npx create-astreus-agent my-agentThe generated project includes everything you need to get started.
Generated Project Structure#
my-agent/
├── src/
│ └── index.ts # Main entry point with agent setup
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration (if TypeScript selected)
├── .env.example # Environment variables template
├── .gitignore # Git ignore rules
└── README.md # Project documentationPackage.json Scripts#
{
"scripts": {
"dev": "tsx src/index.ts",
"build": "tsc",
"start": "node dist/index.js"
}
}Common Configurations#
Basic Chat Agent#
Select only Memory feature for a simple conversational agent:
? Which features do you want to include?
◉ Memory - Persistent agent memory with vector search
◯ Knowledge (RAG)
◯ Graph Workflows
◯ Sub-Agents
◯ Custom Plugins
◯ MCP IntegrationRAG-Enabled Agent#
Select Memory and Knowledge for document-aware responses:
? Which features do you want to include?
◉ Memory - Persistent agent memory with vector search
◉ Knowledge (RAG) - Document ingestion and retrieval
◯ Graph Workflows
◯ Sub-Agents
◯ Custom Plugins
◯ MCP IntegrationFull-Featured Agent#
Select all features for maximum capabilities:
? Which features do you want to include?
◉ Memory - Persistent agent memory with vector search
◉ Knowledge (RAG) - Document ingestion and retrieval
◉ Graph Workflows - DAG-based task orchestration
◉ Sub-Agents - Multi-agent coordination
◉ Custom Plugins - Extensible tool system
◉ MCP Integration - Model Context Protocol supportProvider-Specific Setup#
OpenAI#
Default model: gpt-4o
Generated .env.example:
OPENAI_API_KEY=your-api-key-hereAnthropic (Claude)#
Default model: claude-sonnet-4-20250514
Generated .env.example:
ANTHROPIC_API_KEY=your-api-key-hereGoogle (Gemini)#
Default model: gemini-2.0-flash
Generated .env.example:
GEMINI_API_KEY=your-api-key-hereOllama (Local)#
Default model: llama3
Generated .env.example:
# Ollama runs locally, no API key needed
OLLAMA_HOST=http://localhost:11434Multiple Providers#
Generated .env.example:
# Add API keys for providers you want to use
OPENAI_API_KEY=your-openai-key
ANTHROPIC_API_KEY=your-anthropic-key
GEMINI_API_KEY=your-gemini-keyFeature Comparison#
| Feature | Use Case |
|---|---|
| Memory | Remembering user preferences, conversation history |
| Knowledge | Documentation Q&A, research assistants |
| Graph | Multi-step workflows, pipelines |
| Sub-Agents | Specialized tasks, parallel processing |
| Plugins | Custom tools, API integrations |
| MCP | Standardized tool ecosystem |
Next Steps#
After creating your project:
cd my-agent
npm install
cp .env.example .env
# Edit .env with your API keys
npm run devSee Configuration for detailed environment setup.