AgentWatch adds spending limits for runaway AI agents
AgentWatch is a middle layer that checks before an AI agent sends a request to OpenAI, Anthropic, Gemini, or another . If an agent gets stuck in a loop or tries to go past a set dollar limit, the request can be blocked before the model is called. Setup is described as changing the base URL and combining the AgentWatch key with the provider key, without installing an SDK.
It says it supports OpenAI, Anthropic, Gemini, Azure OpenAI, Bedrock, Groq, Mistral, Cohere, and other providers, plus tools such as Cursor, Claude Code, Windsurf, Aider, and Cline. Main features include per-session budgets, loop alerts, provider failover choices, and records of metadata such as cost, tokens, and latency. AgentWatch says it does not store prompts or model answers, only metadata.
The free plan includes 50,000 requests per month with budget enforcement, while the paid plan adds 500,000 requests, caching, failover, and Slack alerts.
Key points
- AgentWatch checks each AI agent request before it reaches the .
- It can block a session when the set dollar budget has been reached.
- It says it works with OpenAI, Anthropic, Gemini, Azure OpenAI, Bedrock, and more.
- It can be used with tools such as Cursor and Claude Code by changing endpoint settings.
- It says it stores metadata like cost and latency, not prompts or model answers.