Show HN: AgentWatch – Prevent runaway AI agents with runtime budget enforcement

[Mohil_Sharma]

https://agent-watch.dev/

Hi HN, I’m a solo developer and built AgentWatch to solve a problem I kept running into while building AI agents: preventing runaway loops and unexpected LLM spend before requests reach the model. AgentWatch sits in front of OpenAI, Anthropic, Gemini, Bedrock, Azure OpenAI, Groq, and others to enforce budgets and runtime policies. I’d really appreciate your feedback. If you’re building AI agents, does this solve a problem you’ve experienced? I’d also love to hear what you’d improve or challenge.

[mohit2502]

Why does this need to be a proxy instead of a middleware inside my app?

[shubh1600005]

Who is this for? Enterprises or individual developers??

[Mohil_Sharma → shubh1600005]

Both,but I would focus on teams building production AI apps.Individual devs can use it also,but the bigger need is usually at the team or enterprise level.

[dshryn]

Are you storing prompts/responses?

[Ipshita_Sharma]

Most of the teams already have an API gateway why would they use another proxy??