llmcap 0.1.0

Real-time LLM spend enforcement — CLI and tray app

LLMCap

Hard dollar caps on AI API calls. When you hit $50, it stops. Not an alert — it stops.

Install

pip install llmcap

Configure

llmcap configure
# Enter your LLMCap API URL and workspace ID

Commands

llmcap status      # Today's spend, burn rate, blocked requests
llmcap logs -n 20  # Last 20 requests
llmcap keys        # List API keys
llmcap budgets     # List budget rules

How it works

Change one line in your code:

# Before
client = Anthropic(api_key="sk-ant-...")

# After
client = Anthropic(
    api_key="sk-ant-...",
    base_url="https://proxy.llmcap.io/anthropic"
)

When you hit your dollar cap, the next request returns 429 instead of forwarding to Anthropic. The token is never consumed. The money is never spent.

Links

• Website: llmcap.io
• Dashboard: app.llmcap.io
• GitHub: github.com/celikkanat/llmcap