Floe-Guard AI 账单卫士

floe-guard

A local budget guardrail for AI agents. It hard-stops your agent before its next LLM call when it would cross a spend ceiling — so a runaway loop dies at $0.10 instead of $4,000. No account, no signup, no network, no telemetry. Runs in your process.

Works with CrewAI · LiteLLM · LangChain · OpenAI · Anthropic · Vercel AI SDK — or any stack, via plain check() / record().

pip install floe-guard        # Python
npm i floe-guard              # TypeScript (Vercel AI SDK) — see js/

from floe_guard import BudgetGuard

guard = BudgetGuard(limit_usd=5.00)   # your ceiling
guard.check()                         # before each LLM call — raises if it'd cross
response = call_your_llm(...)         # your existing call
guard.record("gpt-4o", response.usage.prompt_tokens, response.usage.completion_tokens)

When the next call would cross the ceiling, the guard raises BudgetExceeded and prints:

BUDGET EXCEEDED — call blocked
  spent so far: $5.001250  |  ceiling: $5.000000
  The next call would cross your budget; floe-guard stopped your agent before it ran.

Run it yourself: python examples/runaway_loop.py — no API key, no account, no network.

Honest about what this is

floe-guard is a local, estimate-based guardrail. It prices tokens from a vendored cost map inside your process:

- The cost map can drift as vendors change prices — refresh it like any snapshot. - It only sees the vendors you instrument. - A determined agent or a bug could route around an in-process check. - Under heavy or cold-start concurrency it bounds steady-state spend, not the first parallel wave. Reservations size from the last call's cost (0 until the first record()), so the opening fan-out has nothing to estimate from. Pass a known per-call max to reserve() to bound it, or use hosted Floe for a hard cap under arbitrary concurrency.

It's genuinely useful on its own, and it's honest about its limits. No inflated metrics, no "zero defaults" claims — it's a free local stop, not a vault.