Skip to content

About

Production-ready LangGraph starter template hardened with AgentShield runtime firewall, tool verification, and multi-agent governance.

Topics

Resources

Code of conduct

Contributing

Security policy

Accessibility

Stars

0 stars

Watchers

0 watching

Forks

LangGraph AgentShield Template 🛡️

Use this template PyPI version Python 3.10+ Secured by AgentShield Trust Center

Production Python LangGraph Multi-Agent Architecture with @shield.protect Zero-Leak Sandboxing, Callback Interceptors, and Prompt Redaction.

Documentation • PyPI Package • Security Advisories • Trust Center


⚡ What is this?

When autonomous AI agents built with LangGraph, CrewAI, AutoGen, or LlamaIndex execute tools and retrieve database records, they frequently encounter volatile credentials (database connection strings, bearer tokens, AWS keys, /proc/self/environ reads).

This template provides an enterprise-ready LangGraph multi-agent graph with AgentShield Defense built directly into tool calls and state transitions:

flowchart LR
    A["User Input / Prompt"] --> B["Security Router Node"]
    B --> C["AgentShield Redactor"]
    C --> D["LangGraph StateGraph"]
    D --> E["Protected Tool Execution (@shield.protect)"]
    E --> F["Zero-Leak Sanitized Response"]
Loading

🚀 1-Click Quickstart

1. Click "Use this template"

Click the green Use this template button above to create your own repository.

2. Clone & Install

git clone https://github.com/YOUR_ORG/YOUR_REPO.git
cd YOUR_REPO

# Install dependencies (includes agentshield-defense)
pip install -r requirements.txt

3. Run the Secure Agent

python -m src.agent

4. Run the Test Suite

pytest tests/ -v

🛡️ Key Defense Mechanisms

  1. @shield.protect Decorator: Wraps custom tools and function invocations. Automatically redacts 40+ credential types from tool return values.
  2. AgentShieldCallbackHandler: Attaches to LangChain / LangGraph execution loops to intercept LLM prompts and model outputs.
  3. Subprocess & Sycall Traps: Prevents hostile prompt injection payloads from dumping /proc/self/environ, ~/.ssh/id_rsa, or environment configurations.

📄 License & Responsible Disclosure



💖 Sponsor & Support

If you find this project valuable, consider supporting our open-source development:

Sponsor on Dodo Payments Interactive Donation Portal GitHub Sponsors


🛡️ Community & Governance

About

Production-ready LangGraph starter template hardened with AgentShield runtime firewall, tool verification, and multi-agent governance.

Topics

Resources

Code of conduct

Contributing

Security policy

Accessibility

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages