How We Host Apps Built by AI Agents

Learn how to host personal apps built by AI agents like ChatGPT and Claude. See the demo, code, and technical choices for safe hosting, databases, and secure execution.

MCP HTTP API Server AGENTS MCP apps Agent Render Claude

Overview

I’m building Charming, which hosts personal apps made by ChatGPT, Claude, Codex, and other agents. In the demo, I’ll create an app, open its URL, and update the same data from chat and the browser. I’ll show the code, API calls, and logs.

Links

https://usecharming.com
Charming deploys AI-built ES-module apps with KV storage via MCP.
https://github.com/tambo-labs/charming-mcp
Charming MCP hosts, deploys, and updates agent-generated web apps.

Tech stack

MCP

MCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.

The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .

https://modelcontextprotocol.io/

View projects
HTTP API

An HTTP API is a software interface that uses Hypertext Transfer Protocol to enable seamless, stateless data exchange between clients and servers.

An HTTP API serves as the backbone of modern web communication, leveraging standard HTTP methods (such as GET, POST, PUT, and DELETE) to transfer structured data (frequently JSON or XML) between systems. Unlike strict RESTful architectures that require adherence to specific hypermedia constraints, a general HTTP API focuses on straightforward, stateless communication over port 80 or 443. This flexibility makes it the go-to choice for developers building everything from simple microservices to high-throughput mobile backends, ensuring reliable interoperability across diverse programming languages and platforms.

https://developer.mozilla.org/en-US/docs/Web/HTTP

View projects
Server

This is a dedicated, high-availability machine (e.g., Dell PowerEdge R760) providing centralized resources: compute, storage (e.g., 50TB RAID array), and network services (e.g., 25GbE) to client systems on demand.

A server is the core workhorse of any serious IT infrastructure, purpose-built for continuous operation (24/7 uptime). Unlike a desktop PC, it features redundant components (PSUs, fans) and high-density architecture (1U or 2U rack-mount form factors). We deploy these units with multi-core CPUs (e.g., Intel Xeon Scalable processors) and massive RAM (often 512GB+ ECC memory) to handle thousands of concurrent requests. Common roles include hosting critical applications (like Apache or Nginx web servers), running virtual machines (VMs), and managing enterprise databases (PostgreSQL, MS SQL Server). It’s the single point of truth for data and services, requiring robust security and meticulous management.

https://www.serverwatch.com/guides/what-is-a-server/

View projects
AGENTS

Autonomous software entities using large language models to reason, select tools, and execute complex workflows independently.

Agents shift the focus from conversation to execution: they use frameworks like LangGraph or CrewAI to break down complex objectives into actionable tasks. These systems leverage external tools (Tavily for search, GitHub for code, or Salesforce for CRM) to operate across digital environments. Current benchmarks show agents can automate up to 80% of routine knowledge work by managing their own reasoning loops. These entities deliver finished outputs (validated data, resolved tickets, or deployed software) with minimal human intervention.

https://www.langchain.com/agents

View projects
MCP apps

MCP Apps (Model Context Protocol) delivers interactive, sandboxed user interfaces directly into AI agent conversations, standardizing complex, multi-step workflows.

MCP Apps is the Model Context Protocol Extension (SEP-1865) that enables MCP servers to render portable, secure UI elements in-conversation, moving beyond text-only interactions. This architecture uses sandboxed iframes and auditable JSON-RPC over postMessage for communication, ensuring a strong security boundary. It supports critical enterprise functions: for instance, providing an interactive audit dashboard for database access requests or a structured approval interface for infrastructure changes. Hosts like Claude, Goose, and Visual Studio Code are adopting this extension, making dynamic interfaces standard across the agent ecosystem.

https://modelcontextprotocol.io

View projects
Agent

An Agent is an autonomous software system (often LLM-driven) that perceives its environment, makes goal-directed decisions, and executes multi-step actions without continuous human oversight.

This is the next-generation automation layer: a software entity capable of independent operation. Agents utilize a core perception-action loop, integrating memory and planning systems to break down complex objectives (e.g., 'book a full business trip') into actionable subtasks. They are distinguished by their autonomy, moving beyond simple chatbots or rule-based scripts. Modern examples like AutoGPT and Devin AI demonstrate their capacity to use external tools (APIs, web browsers) and adapt their strategy in real-time, delivering a step-change in efficiency for enterprise workflows and complex data analysis.

https://en.wikipedia.org/wiki/AI_agent

View projects
Render

Render is the unified cloud platform: build, deploy, and scale your full-stack applications and services with automatic zero-downtime deploys and managed infrastructure.

Render delivers accessible, reliable cloud infrastructure, simplifying deployment for all service types: Web Services, Static Sites, Background Workers, and managed databases like Render Postgres. The platform supports native runtimes (Node.js, Python, Ruby) or Docker, offering features like load-based autoscaling and Private Networking. Teams leverage Infrastructure as Code (IaC) via Blueprints to define and replicate entire environments quickly. With over $155M in funding, Render is engineered for speed and reliability, supporting everything from prototypes to applications with hundreds of services at global scale.

https://render.com/

View projects
Claude

Claude is Anthropic's flagship family of large language models (LLMs): a high-performance, Constitutional AI system built for safety, complex reasoning, and expert-level collaboration.

Claude is a next-generation AI assistant developed by Anthropic, a research firm prioritizing AI safety. The models (including Opus, Sonnet, and Haiku) leverage Constitutional AI to ensure helpful, honest, and harmless outputs, a key differentiator from competitors. Claude excels at complex enterprise tasks: processing massive context windows for in-depth data analysis, generating and reviewing code, and providing expert-level summarization for documents up to 200,000 tokens. It is deployed as a conversational chatbot and via API, offering scalable AI solutions for developers and businesses.

https://claude.ai/

View projects

How We Host Apps Built by AI Agents

Related talks