Metadata-Version: 2.4
Name: crewai-valta
Version: 0.1.1
Summary: CrewAI tool for hard spending limits on AI agents via Valta
Author-email: Valta <debo@valta.co>
License: MIT
Project-URL: Homepage, https://valta.co
Project-URL: Documentation, https://valta.co/docs
Project-URL: Repository, https://github.com/billionaire664/valta.co
Keywords: crewai,ai,agents,spending,budget,cost-control,guardrails
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: pydantic>=2.0.0

# crewai-valta

Hard spending limits for CrewAI agents. Enforces budget policies before any paid operation fires.

## Install

```bash
pip install crewai-valta
```

## Quickstart

```python
from crewai_valta import ValtaSpendTool
from crewai import Agent, Task, Crew

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

researcher = Agent(
    role="Research Analyst",
    goal="Find and summarise market data",
    backstory="...",
    tools=[guard, ...your_other_tools],
)
```

Add this to your task description:
> "Before calling any paid API, use the check_spend tool with the estimated cost. Only proceed if the result is 'approved'."

## How it works

| Response | Meaning |
|----------|---------|
| `approved` | 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 |

## Links

- [valta.co](https://valta.co)
- [Get an API key](https://valta.co/dashboard/api-keys)
- [Manage policies](https://valta.co/dashboard/policies)
