What is AgentSecrets?
The Zero-Knowledge Difference
How AgentSecrets Works
Installation
Quick Start
Migrating from .env Files
Migrating from Vault / AWS
Migrating from dotenv-vault
Production Checklist
Credential Exposure
What Zero-Knowledge Means
The Proxy Model
The Three-Layer Model
Environments
Agent Identity
Storage Modes
The No get() Principle
Secret-Level Policies
Cloud Overview & Architecture
The Dual-Engine Model
Cloud Resolver Data Plane
Workload & Agent Tokens
Egress Allowlists & Audit Streams
Cloud REST API Reference
Account (init / login)
Server & Self-Hosting (server)
Docs
Shell Autocompletion
Keychain Auth
Secrets
Environments
Credential Proxy
env Injection
Workspaces & Teams
Projects
Agent Identity
Audit & Governance
Integrations Overview
Claude Desktop
Cursor
OpenClaw
HTTP Proxy (Any)
LangChain (Soon)
CrewAI (Soon)
CI/CD Pipeline
SDK Overview
Python SDK
Python API Reference
Python SDK Manual Testing
JavaScript SDK (Soon)
Ecosystem Overview
Zero-Knowledge MCP Server
Server Overview
5-Layer Architecture
Self-Hosting Guide
Authentication & Keys
Workspaces & Teams
Projects & Scope
Environments
Secrets & Sync Protocol
Agent Identity Resolution
Telemetry & Metrics Engine
Audit Log Sync
API Endpoint Reference
Security Overview
Anti-Impersonation & Process Verification
Encryption Model
Zero-Knowledge Sync
Proxy Security Layers
Threat Model
OWASP Top 10 Mitigation
Security FAQ
Third-Party Audit
Reporting Vulnerabilities
Guides Overview
Building on the SDK
Stripe Integration
OpenAI Integration
Multi-Agent Setup
Onboarding Team
CI/CD Pipeline
Publishing ZK MCP
Rotating Credentials
Auditing Team Activity
Dev to Production
Kubernetes Deployment
Monorepo Setup
Production Proxy Hardening
vs .env Files
vs HashiCorp Vault
vs AWS Secrets Manager
vs dotenv-vault
vs Infisical
When Not to Use
Proxy Not Starting
Proxy Not Resolving
Domain Blocked
Sync Conflicts
MCP Not Connecting
Session Token Errors
Proxy Session Authorization
Keychain Storage & Backends
SSRF & Destination Rules
Installation Issues
Error Codes Reference
Frequently Asked Questions
v3.1.x
v3.0.0
v2.1.0
v2.0.0
v1.4.0
v1.3.x
v1.2.0
v1.1.x
v1.0.x
SDKSDK Overview

SDK Overview

AgentSecrets SDKs provide a secure, zero-knowledge interface for integrating credentials and API calls into your applications and AI agent workflows.

Following the No get() Principle, our SDKs are structurally incapable of retrieving decrypted secret values into your application's process memory. Instead, they provide clean abstraction layers to route operations through the local secure proxy daemon.


Supported Integration Models

You can integrate AgentSecrets into your codebase using two distinct methods depending on your requirements:

This method monkey-patches standard HTTP libraries (such as requests and httpx in Python) upon initialization. Outgoing requests containing special placeholder tokens (e.g. AS_SECRET_OPENAI_KEY) are automatically intercepted, stripped of the placeholder, and routed through the local proxy daemon.

This enables:

  • Zero code modifications to third-party SDKs (such as openai or stripe clients).
  • Easy onboarding: You initialize standard clients with the placeholder token format, and they work out-of-the-box.
  • Security boundary: Keys never touch the process memory of your AI agent or main application.

2Explicit Client Calls

For custom integrations or if you prefer explicit proxy routing, the SDK provides a unified client.call() interface. You pass the target URL, method, body, and the metadata reference names of the credentials to inject (e.g., bearer="STRIPE_KEY"). The SDK formats and forwards the request to the proxy.


Language Support & SDK v3 Architecture

  • Python SDK (agentsecrets):
    • Modern Architecture: Full PEP 561 type safety (py.typed) with 100% mypy --strict compliance.
    • Dual-Mode Execution:
      • Local Mode (Default): Delegates to local CLI proxy and OS Keychain via keychain-auth.
      • Cloud Mode (AGENTSECRETS_MODE=cloud): Direct cloud API credential resolution for containerized and serverless environments.
    • Agent Identity Module: Dedicated from agentsecrets import agent module for programmatic agent lifecycle and capability management.
    • See the Python SDK Guide and Python API Reference.
  • JavaScript/TypeScript SDK: Coming Soon — designed for Node.js, Bun, and Deno environments.

Testing Agent Workflows

To support automated testing and CI/CD pipelines without exposing production keys or requiring a running proxy daemon, the SDK includes mock interfaces (MockAgentSecrets in agentsecrets.testing).

These mock clients:

  • Act as drop-in replacements for testing without a running proxy daemon.
  • Record target endpoints, HTTP methods, and key references of calls made.
  • Maintain complete zero-knowledge integrity (no plaintext credential values exist).
Was this helpful?
Thanks for your feedback!
Your feedback helps us improve the platform.