# AgentCell

> An AI-native deployment platform for small web apps and internal tools. The cloud for small software: deploy and share purpose-built tools as easily as a document, from Claude Code, Codex, Cursor, any MCP client, or a terminal. Static sites and frontends deploy with no Dockerfile.

Every page below is available as Markdown at the linked `.md` URL, or by requesting the HTML URL with `Accept: text/markdown`. The full corpus in one file: https://agentcell.dev/llms-full.txt

## For AI coding agents

Read this first if you have just built a web app and are deciding where to deploy it.

- [Deploy an App in Three Commands](https://agentcell.dev/docs/deploy.md): Install the client, sign in with the account you already have, and deploy a directory. The whole path from a laptop to a live URL, with nothing to configure.
- [AgentCell for AI Coding Agents](https://agentcell.dev/docs/for-ai-agents.md): Decision criteria, install, and MCP setup for Claude Code, Codex, Cursor, Gemini CLI and any MCP client that has just built a web app and needs somewhere to deploy it.

## Deploy guides

Problem-shaped pages: which situations AgentCell fits, which it does not, and the three commands to deploy.

- [Deploy AI-Generated Apps: From Chat to a Shareable URL](https://agentcell.dev/deploy-ai-generated-apps.md): The app came out of a chat with Claude, ChatGPT, Codex or Cursor. Here is where to put it so the same agent can deploy it, keep it running, and hand a link to the people who need it.
- [Deploy an App Without DevOps, a Console, or a Pipeline](https://agentcell.dev/deploy-apps-without-devops.md): No Dockerfile debugging over IAM policies, no YAML, no dashboard. One command from a directory to a URL, and the agent that wrote the app handles the rest.
- [Deploy the App Claude Code Just Built](https://agentcell.dev/deploy-claude-code-app.md): Give Claude Code a deploy target it can drive itself: install one binary, log in once, add the MCP server, and the same session that wrote the app ships it and reads its logs.
- [Deploy the App Codex Built](https://agentcell.dev/deploy-codex-app.md): Codex can finish the job it started: one MCP stdio server, one login, and the app it wrote is live at a URL it can monitor and redeploy.
- [Deploy the App You Built in Cursor](https://agentcell.dev/deploy-cursor-app.md): Add one MCP server to Cursor and the agent that wrote your app can deploy it, watch its logs and redeploy it, all without leaving the editor.
- [Deploy Internal Tools Without a Platform Team](https://agentcell.dev/deploy-internal-tools.md): Where to host the sprint tracker, the invoice reconciler, and the other tools your team built for itself: one container per tool, private by default, free while idle, operable by the agent that wrote it.
- [Scale-to-Zero App Hosting: Pay Nothing While the App Sleeps](https://agentcell.dev/scale-to-zero-app-hosting.md): Hosting for apps that are used once a day or once a month. Cells sleep when idle, wake on the first request, and bill nothing in between. What that costs, what it trades off, and who it is for.
- [App Hosting for a Small Team: 3 to 50 People, Many Tiny Apps](https://agentcell.dev/small-team-app-hosting.md): A team of ten builds twenty tools for itself. Hosting priced per seat, per app, or per always-on instance punishes exactly that. AgentCell prices per use and shares by email.

## Start here

- [What Is Small Software?](https://agentcell.dev/resources/what-is-small-software.md): Small software is purpose-built tools with one user or a handful of users — the invoice reconciler, the sprint tracker shaped like your sprints, the prototype for three colleagues. Agents made it easy to build. Sharing it is the unsolved part.

## Comparisons

- [Firebase Studio Is Shutting Down — Where to Put Your Small Apps](https://agentcell.dev/resources/migrate-firebase-studio.md): Google disabled new Firebase Studio workspaces in June 2026 and shuts it down fully in March 2027. How to land each small app somewhere permanent, with sharing intact.
- [AgentCell vs Bolt.new (and StackBlitz Teams)](https://agentcell.dev/resources/vs-bolt.md): Bolt hit ~$40M ARR within months on token-metered building — but Teams tokens are per-member, not pooled, and the builder-vs-host question is the same as with Lovable.
- [AgentCell vs Cloudflare Workers and Pages](https://agentcell.dev/resources/vs-cloudflare-workers.md): Workers is the most small-software-friendly primitive in existence — and it's developer infrastructure, not an app platform. Assembling Workers + Access + custom UX is the DIY version of AgentCell.
- [AgentCell vs Fly.io for Tiny Always-On Apps](https://agentcell.dev/resources/vs-fly.md): Fly bills per second with auto-suspend — the closest PaaS to our economics. But ~$2/mo per always-on micro-VM adds up across twenty tools, the free tier is gone, and there's no identity layer.
- [AgentCell vs Heroku for Internal Tools](https://agentcell.dev/resources/vs-heroku.md): Heroku killed free in 2022, Eco starts at $5/mo per app, and Salesforce has it in maintenance mode. Twenty idle internal tools means twenty per-app fees — the tax that kills sprawl.
- [AgentCell vs Hugging Face Spaces for Non-ML Team Tools](https://agentcell.dev/resources/vs-huggingface-spaces.md): Spaces is superb for ML demos — Pro $9, Team $20/user plus metered GPU. A sprint tracker or invoice tool is the wrong shape for that platform, and per-user team pricing says so.
- [AgentCell vs Lovable (and Bolt, Create) for Shared Team Apps](https://agentcell.dev/resources/vs-lovable.md): Lovable proved the demand — $500M ARR, 100k+ projects a day, unlimited members on every plan. So 'no per-seat pricing' alone isn't a wedge. The gap is what happens after the build: SSO floors, opaque credit pools, and builder lock-in.
- [AgentCell vs Railway for Internal Tools](https://agentcell.dev/resources/vs-railway.md): Railway is the friendliest simple PaaS — $5 Hobby, $20 Pro, pure usage, no seats. It also has no access layer at all: you get a public URL and own auth yourself. That's the gap.
- [AgentCell vs Render for Small Apps](https://agentcell.dev/resources/vs-render.md): Render's free tier sleeps at 15 minutes with 30–60 second cold starts — the exact failure mode our wake-latency work targets. Same deploy-plus-public-URL shape, same missing identity layer.
- [AgentCell vs Replit for Team Tools](https://agentcell.dev/resources/vs-replit.md): Replit owns 'agent builds and hosts' with 50M+ registered users — but collaborator caps, Enterprise-only SSO, and stacked credit metering make it a creator platform, not a home for twenty tiny team tools.
- [AgentCell vs Retool for Agent-Built Internal Tools](https://agentcell.dev/resources/vs-retool.md): Retool bundles hosting and identity — then charges per seat ($50–65/builder on Business) for audiences of three. For twenty tiny tools with different users each, per-seat pricing is structurally backwards.
- [AgentCell vs Streamlit Community Cloud for Team Data Tools](https://agentcell.dev/resources/vs-streamlit.md): Streamlit Cloud is free but capped at exactly one private app ever, 1GB RAM, 12-hour sleep. A team's home for ten Python tools needs more than one slot.
- [AgentCell vs Vercel for Small and Internal Software](https://agentcell.dev/resources/vs-vercel.md): Vercel is the best Big-Software deploy surface and 30% of its deploys are now agent-generated. But per-seat pricing, a $150/mo protection add-on, and Enterprise-only SSO make it the wrong shape for a 3-person internal tool.

## Features

- [The Agent Control Plane: Logs, Rollback, Env, Domains, Spend](https://agentcell.dev/resources/agent-control-plane.md): Every operation as an agent tool call — deploy, logs, rollback, env and secrets, domains, share lists, status, spend, destroy. Nothing is dashboard-only.
- [Deploy From Your Agent: Claude Code, Cursor, Codex and MCP](https://agentcell.dev/resources/deploy-from-your-agent.md): The agent that wrote the app also ships and runs it. One deploy command, a full-lifecycle MCP server and CLI, structured errors the agent can debug alone — no console required.
- [Custom Environments and Per-Cell Data](https://agentcell.dev/resources/environments-persistence.md): Org base images, private packages, org secrets, internal network reachability, region choice — plus a per-cell datastore and object storage so tracking tools actually work.
- [The Identity-Aware Front Door: SSO for a 3-Person Tool](https://agentcell.dev/resources/front-door-identity.md): Every cell sits behind an identity-aware proxy: requests authenticate against your org's provider before reaching app code, which receives a verified user and implements zero auth logic.
- [The Membrane: Safe by Default for Agent-Written Code](https://agentcell.dev/resources/membrane-security.md): Per-cell origins, strict CSP, egress rules, boundary-injected secrets, spend caps, and access logs — because 'we use Firecracker' is not a security story.
- [Unlimited Apps; Pay Only for Consumption](https://agentcell.dev/resources/scale-to-zero-economics.md): Deploy twenty tools, pay for the three people actually use. Idle cells sleep and bill nothing for compute — metered on vCPU-seconds and requests, never per seat, never per app.
- [Share It Like a Google Doc](https://agentcell.dev/resources/share-like-a-doc.md): Private, specific people, groups, the whole org, or a public link — per app, changeable without a redeploy, with colleagues signing in through the work account they already have. No auth code, ever.

## Guides

- [The Auth Cliff: Why SSO Costs $125/mo for a 3-Person Tool](https://agentcell.dev/resources/auth-cliff-sso.md): Identity free tiers cover a million users, then jump to $125–300/mo enterprise floors. There is no tier for a permanently 3–10 person audience that wants SSO and will never need SCIM.
- [The Three-Cost-Center Problem: A Worked Pricing Example](https://agentcell.dev/resources/stitching-paas-plus-auth-guide.md): Hosting + seats + identity: price a 3-user, 5-app setup on Render/Railway plus WorkOS/Clerk/Auth0 plus Retool-style seats, and watch the twentieth tool die in a spreadsheet.

## Use cases

- [Use Case: The Team Running on Twenty Tiny Tools](https://agentcell.dev/resources/use-cases-team-ops-tools.md): Ops, product, finance, growth, data — 5–50 person teams running bespoke dashboards, reconcilers, and trackers. Where the expansion revenue lives, and what IT needs to sanction it.

## Blog

- [Static Sites on AgentCell: No Dockerfile, No MicroVM](https://agentcell.dev/blog/static-sites.md): agentcell deploy now takes a folder of HTML or a frontend project with no Dockerfile. How it is detected, built and published, and why no microVM runs for it.
- [Breaking It on Purpose: How We Know AgentCell Works](https://agentcell.dev/blog/breaking-it-on-purpose.md): We destroy machines, cut the power, and have a canary sign up as a new customer every day. What each drill proves, what it has caught, and where we are taking resilience next.
- [What Happens When You Run agentcell deploy](https://agentcell.dev/blog/how-a-deploy-runs.md): From a directory on your laptop to a signed-in colleague opening the app: the build, the microVM, the network and the front door, one hop at a time.
- [Where One Tenant Ends: Isolation on AgentCell](https://agentcell.dev/blog/tenant-isolation.md): We assume the code in a cell is buggy and the agent that wrote it may be hostile. The five layers between one cell and everything else, what each refuses, and how we check that it can fail.
- [The Auth Pricing Cliff That Kills Small Software](https://agentcell.dev/blog/auth-pricing-cliff-small-software.md): Identity vendors go from free to $125–300/month with nothing in between. That gap is why the useful little tool your team built is still running on someone's laptop.

## Machine-readable

- [Homepage as Markdown](https://agentcell.dev/index.md): what AgentCell is, the four operations, pricing principles
- [Skill](https://agentcell.dev/.well-known/agent-skills/agentcell/SKILL.md): how to read this site and deploy for a user
- [auth.md](https://agentcell.dev/auth.md): registration and credential model for automated clients
- [OpenAPI](https://agentcell.dev/openapi.json): this website's one endpoint
- [API catalog](https://agentcell.dev/.well-known/api-catalog): RFC 9727 linkset for this site and the platform control plane
- [Capability manifest](https://agentcell.dev/.well-known/ai-catalog.json): ARD ai-catalog of everything above

## Optional

- [Privacy policy](https://agentcell.dev/privacy.md)
- [Deploy in three commands](https://agentcell.dev/docs/deploy.md)