Getting Started

​

Requirements

• Python 3.9+
• At least one supported provider SDK (OpenAI, Anthropic, or Google GenAI)

​

Install

pip install actguard

​

Configure the runtime client

import actguard

client = actguard.Client.from_env()

• Base64 JSON payload
• Path to a JSON file

{
  "gateway_url": "http://localhost:8085",
  "api_key": "ag_live_...",
  "event_mode": "verbose"
}

​

Run + budget scope

import actguard

client = actguard.Client.from_env()

with client.run(user_id="alice", run_id="req-123"):
    with client.budget_guard(usd_limit=0.05) as guard:
        # call your LLM SDKs/tools here
        ...

print(f"tokens={guard.tokens_used} usd={guard.usd_used:.6f}")

​

budget_guard vs decorators

• budget_guard checks and enforces budget constraints before and during model execution.
• Tool decorators (rate_limit, circuit_breaker, max_attempts, timeout, idempotent, prove, enforce, tool) guard tool invocation behavior and emit runtime events.

​

Runtime-scoped decorators

from actguard import max_attempts

@max_attempts(calls=2)
def lookup_customer(customer_id: str) -> dict:
    ...

with client.run(run_id="req-123"):
    lookup_customer("cus_1")

​

Chain-of-custody decorators

import actguard

with client.run(run_id="req-123"):
    with actguard.session("req-123", {"user_id": "alice"}):
        ...

​

Examples from the repository

• actguard/examples/10_langchain
• actguard/examples/20_langgraph
• actguard/examples/30_google_adk
• actguard/examples/40_prove_enforce

• client = actguard.Client.from_env()
• with client.run(...)
• optional with client.budget_guard(...)