agentgate-sdk

agentgate

The security gateway for AI agents. Enforce authentication, rate limiting, and policy controls between users and AI agents — in one line of code.

Install

pip install agentgate

With LangChain:

pip install "agentgate[langchain]"

With OpenAI Agents SDK:

pip install "agentgate[openai]"

Everything:

pip install "agentgate[all]"

Quickstart

Get your free API key at https://agent-gate-rho.vercel.app/

Any agent (generic)

from agentgate import with_agent_gate, AgentGateOptions

secured = with_agent_gate(my_agent, AgentGateOptions(
    api_key="ag_your_key_here"
))
result = secured.run("delete_file", {"path": "/etc/passwd"})

LangChain

from agentgate import AgentGateLangChainCallback, AgentGateOptions
from langchain.agents import AgentExecutor

callback = AgentGateLangChainCallback(
    AgentGateOptions(api_key="ag_your_key_here")
)
agent_executor = AgentExecutor(
    agent=agent,
    tools=tools,
    callbacks=[callback],
)

OpenAI Agents SDK

from agentgate import wrap_openai_agent, AgentGateOptions
from agents import Agent, Runner

secured = wrap_openai_agent(agent, AgentGateOptions(
    api_key="ag_your_key_here"
))
result = await Runner.run(secured, "Send email to all users")

MCP middleware

from agentgate import AgentGateMiddleware, AgentGateOptions

gate = AgentGateMiddleware(AgentGateOptions(api_key="ag_your_key_here"))

# Inline check
result = gate.check("send_email", args, lambda: send_email(args))

# As a decorator
@gate.guard()
def delete_user(user_id: str):
    ...

Fail-open vs Fail-closed

# Development (default)
AgentGateOptions(api_key="ag_xxx", on_network_error="fail-open")

# Production (recommended)
AgentGateOptions(api_key="ag_xxx", on_network_error="fail-closed")

Policy decisions

Links

Dashboard: https://agent-gate-rho.vercel.app/ GitHub: https://github.com/wiserautomation/agentgate Issues: https://github.com/wiserautomation/agentgate/issues