MeshGuard Examples

Production-ready examples of AI agents governed by MeshGuard.

Examples

Example	Framework	Description
langchain-customer-service	LangChain	Complete customer service agent with tiered permissions
crewai-research-team	CrewAI	Multi-agent research team with delegation control
autogpt-governed	AutoGPT	Cost-controlled autonomous agent with rate limiting
bedrock-data-analyst	AWS Bedrock	Governed data analyst agent with controlled data access
vertex-ai-multiagent	Google Vertex AI	Multi-agent workflow with delegation + audit
openai-agents-support	OpenAI Agents SDK	Customer support agent with governed built-in tools

Getting Started

Each example is self-contained with its own:

• README.md — Setup and usage instructions
• requirements.txt — Python dependencies
• .env.example — Required environment variables
• policies/ — MeshGuard policy configurations
• docker-compose.yml — One-command deployment

Prerequisites

• Python 3.10+
• A MeshGuard account (sign up free)
• OpenAI API key (or other LLM provider)

Quick Start

# Clone the repo
git clone https://github.com/meshguard/meshguard-examples.git
cd meshguard-examples

# Pick an example
cd langchain-customer-service

# Copy environment template
cp .env.example .env
# Edit .env with your API keys

# Install dependencies
pip install -r requirements.txt

# Run the example
python main.py

Learn More

• MeshGuard Documentation
• MeshGuard Learning Center
• Python SDK Reference

License

MIT License - Use these examples as starting points for your own governed agents.