All activity
Victor Kuzennyyleft a comment
Hey Product Hunt! I'm the maker of agent-express. I was building AI agents in TypeScript and kept noticing that every framework invents its own abstraction for things that are fundamentally middleware — intercept context, do something before/after the LLM call, pass control downstream. Memory management? That's middleware that trims ctx.history before the model call. Budget caps? Middleware...
Agent ExpressMiddleware framework for AI agents — Express.js for LLMs
Agent Express is an open-source middleware framework for building AI agents in TypeScript.
If you've written Express.js middleware, you already know how to build agents. The model-tool-model loop in an agent is structurally identical to the request-response cycle in a web server — a context flows through composable (ctx, next) functions.
Three concepts: Agent, Session, Middleware. Five hooks. Built-in middlewares for budget tracking, guardrails, observability, memory compaction and others.
Agent ExpressMiddleware framework for AI agents — Express.js for LLMs
Victor Kuzennyystarted a discussion
Do AI agents really need their own framework, or is middleware enough?
Most agent frameworks invent graphs, chains, and orchestration layers. But when you break it down — retry, budget caps, memory, logging — each one is just a (ctx, next) function. Same pattern web developers have used for 15 years. Where do you think the middleware model breaks down for agents?
Victor Kuzennyystarted a discussion
What's the #1 reliability issue you've hit with AI agents in production?
We built agent-express around the idea that most agent failures aren't about the LLM — they're about everything around it: cost runaway, context overflow, silent tool errors, no retry logic. Curious what's been the biggest pain point for others building agents for real workloads?