dipampaul17/AgentGuard
Real-time guardrail that shows token spend & kills runaway LLM/agent loops.
Intercepts all API calls (fetch, axios, undici, got) to track costs from OpenAI, Anthropic, and other providers in real-time, with configurable protection modes ("throw" for recoverable errors, "kill" for immediate termination, "notify" for warnings). Supports multi-process deployments via Redis for shared budget tracking across distributed agents, and integrates with webhooks for Slack/Discord alerts when limits are approached or exceeded.
157 stars. No commits in the last 6 months.
Stars
157
Forks
8
Language
JavaScript
License
MIT
Category
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.
Higher-rated alternatives
aptible/unpage
Unpage is the open source framework for building SRE agents with infrastructure context and...
valmi-io/value
⚡ "Value" - https://value.valmi.io . Valmi Value is Outcome-based billing and payments...
driftbase-labs/driftbase-python
Local-first behavioral drift monitoring for AI agents. One decorator, SQLite, no cloud.
Harshit-J004/toolguard
Pytest-style reliability testing for AI agent tool chains. Catches hallucinated payloads, schema...
govynAI/govyn
Governance proxy for AI agents — per-agent budgets, cost tracking, loop detection, and policy...