openai-agents-valta 0.1.0

OpenAI Agents SDK tool for hard spending limits on AI agents via Valta

openai-agents-valta

Hard spending limits for OpenAI Agents SDK. Enforces budget policies before any paid operation fires.

Install

pip install openai-agents-valta

Quickstart

from openai_agents_valta import make_valta_tool
from agents import Agent, Runner

guard = make_valta_tool(
    api_key="vk_live_...",   # from valta.co/dashboard/api-keys
    agent_id="research-agent",
)

agent = Agent(
    name="Research Agent",
    instructions=(
        "Before any paid operation, call check_spend with the estimated cost. "
        "Only proceed if the result is 'approved'."
    ),
    tools=[guard, ...your_other_tools],
)

result = await Runner.run(agent, "Research the latest AI news")

How it works

The agent calls check_spend before any paid operation. Valta evaluates the request against the user's policy and returns approved or denied: <reason> before the charge fires.

Response	Meaning
approved	Spend is within policy — proceed
denied: daily_limit_exceeded	Would exceed daily budget
denied: insufficient_balance	Wallet balance too low
denied: requires human approval	Above approval threshold — check dashboard

Policy management

Set limits at valta.co/dashboard/policies. Changes take effect immediately — no redeploy needed.

Links

• valta.co
• Documentation
• Get an API key