Lightweight Authentication for AI Agents
Project description
🔐 Encryptly
Give unbreakable trust to your AI agents.
🧠 What is Encryptly?
Encryptly is a powerful, developer-friendly authentication SDK that seamlessly integrates security into your multi-agent AI applications. It serves as the perfect security layer for your AI stack, providing JWT-based authentication and role-based access control that protects your agents from impersonation, unauthorized access, and malicious attacks.
With Encryptly, you can:
- Secure agent authentication with JWT tokens and cryptographic verification
- Prevent agent impersonation through robust identity validation
- Control access with roles to ensure only authorized agents perform specific tasks
- Protect inter-agent communication with signed messages and verification
⭐ Key Features
- Universal Framework Support: Works with CrewAI, LangChain, and any custom AI framework
- JWT Authentication: Industry-standard token-based authentication for agents
- Role-Based Access Control: Define and enforce agent permissions and capabilities
- Message Signing: Cryptographically sign and verify inter-agent communications
- Simple Integration: Clean, consistent API with easy-to-use integrations
- Framework-Agnostic Core: Use the same security features across different AI frameworks
🚀 Getting Started
Installation
pip install encryptly
Quick Start
from encryptly.vault import Encryptly
from encryptly.integrations import CrewAIIntegration
# Initialize Encryptly
vault = Encryptly()
crew_integration = CrewAIIntegration(vault)
# Secure your agents
data_analyst_token = crew_integration.secure_agent(
"data_analyst_001",
"Data Analyst",
"DataAnalystAgent"
)
risk_advisor_token = crew_integration.secure_agent(
"risk_advisor_001",
"Risk Advisor",
"RiskManagementAgent"
)
# Verify agent authentication
is_valid, agent_info = vault.verify(data_analyst_token)
if is_valid:
print(f"Agent verified: {agent_info['agent_id']} ({agent_info['role']})")
# Secure inter-agent communication
message = "Request risk assessment for AAPL"
is_verified = crew_integration.verify_agent_communication(
"data_analyst_001",
"risk_advisor_001",
message
)
📚 Documentation
We've created comprehensive documentation to help you get the most out of Encryptly:
- Quick Start Guide: Get up and running in minutes
- API Reference: Complete SDK documentation
- Framework Integrations: CrewAI, LangChain, and custom frameworks
- Security Best Practices: Protect your AI agents effectively
- Use Cases & Examples: Real-world implementation patterns
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file encryptly-0.1.2.tar.gz.
File metadata
- Download URL: encryptly-0.1.2.tar.gz
- Upload date:
- Size: 18.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
187aec36be668cccbb36e788106fe443322b15dddcad6e152cda9c1c32a46e5f
|
|
| MD5 |
a5cbb1293b7d1a8f564d17c0f3eeb1cc
|
|
| BLAKE2b-256 |
bd25fa35bd5eacd60c470bdb5518d2937b01bec35ab8a50374b2e16c5be720d8
|
File details
Details for the file encryptly-0.1.2-py3-none-any.whl.
File metadata
- Download URL: encryptly-0.1.2-py3-none-any.whl
- Upload date:
- Size: 19.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
082aba55bd8d7cac7c0ca14ea682164640cbb35816b303869e1f48b9e3d4646e
|
|
| MD5 |
de3aff66a95889271d214d86a3cb467b
|
|
| BLAKE2b-256 |
ca5189e65e04903af442fa96cd28716a11ca30a5a60f24e2f493ff914c768969
|