dipampaul17/AgentGuard

Real-time guardrail that shows token spend & kills runaway LLM/agent loops.

37
/ 100
Emerging

This helps developers who are building applications using large language models (LLMs) prevent unexpectedly high costs. It automatically monitors the real-time spending of AI API calls, and if a pre-set budget limit is reached, it immediately stops the process. The outcome is avoiding massive bills from runaway AI agents, instead getting a report on the money saved.

157 stars. No commits in the last 6 months.

Use this if you are a developer building or testing AI agents and want to automatically cap your spending on LLM API calls in real-time.

Not ideal if you are not a developer working with AI agents or if you only need cost tracking after an AI process has already finished.

AI-development LLM-ops cost-management developer-tools API-budgeting
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 10 / 25

How are scores calculated?

Stars

157

Forks

8

Language

JavaScript

License

MIT

Last pushed

Jul 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/dipampaul17/AgentGuard"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.