Per-user isolated environments for AI agents
Per-user agent environments with persistent DB and storage that pause when idle.

Persistent apps with MCP access so AI agents can actually use them.
Developers building personal apps with AI agents
Replit · Bolt.new · v0
More and more people seem to be building personal software, including myself. But I keep re-implementing the same things: authentication, database setup, creating an API/MCP server to integrate them into my AI agent.
We built Buildy for LLM generated personal apps.
How it works: Buildy exposes an API and MCP that the agent can call with an ES module plus an optional UI and CSS. We run the ES module on a workerd isolate with a persistent KV store, then release your UI to a live URL only accessible by you. Not only that, but your app APIs are exposed securely over both HTTP and MCP so your agent can call them and use the apps you build (log a meal, create a workout plan, update a note, etc.)
If your AI chat client supports MCP Apps, we can also render your app inline via an iframe. This works today with ChatGPT and Claude.
Here is an app I built to track my nutrition: https://app.buildy.so/app/f5da0700-0db7-44ef-9aa2-b9499b484d... ← You can actually claim this app and remix it with your own agent.
To ship a completely new app, drop this prompt into your agent: Read https://buildy.so/start.md then help me create my first app.
Or check out our landing page (https://buildy.so) to use our ChatGPT app or connect it to Claude via MCP.
I personally use apps I built every day. I'd love to hear from other people building and using their own personal apps.
Would love feedback from people building and using their own personal apps.
Per-user agent environments with persistent DB and storage that pause when idle.
Persistent cloud workspaces for AI agents; impressive demo, but execution complexity remains unproven at scale.
Fixes real agent deployment pain — but Replicate, Modal, and Railway already do this well.
Agent fleets in hardened Docker with per-agent budgets—assumes agents will be compromised.
VM isolation for coding agents beats container-based sandboxing for true environment separation.
Chowder gives you one API call to spin up sandboxed OpenClaw instances with built-in channels (Telegram, Slack, WhatsApp, Signal) and session memory — plus a Skills marketplace for browsing, file access and code execution. The OpenAI Responses-compatible surface and scoped org/instance keys with rotation are the practical wins: less infra to manage and an easy migration path for tools that already speak that API. It’s a sensible, developer-friendly stitch of agent orchestration and multi-channel routing, not a radical re-think of the space.