Click → URL
Pick a template from the catalog. Click create. Get a dedicated subdomain that proxies to your Machine via authenticated edge.
PRODUCT
Gentity. Give every AI agent its own machine.
Gentity spins up isolated AI agent instances on Fly Machines — each with its own URL, its own state, and its own runtime. Pick a template, click create, open the link.
~/gentity
$ gentity create --template openclaw→ Spawning Fly Machine in iad …→ Mounting Volume agent-oc-x7k2 …→ Reverse proxy ready✓ https://oc-x7k2.gentity.app
WHAT IT IS
An agent, an isolated box, a URL.
Every Gentity instance is its own Firecracker microVM with a mounted Volume. Auth lives in front. State lives in back. You get a link.
Persistent state
Each instance has its own Fly Volume. Restart, stop, resume — agent memory, files, and config survive.
Cold start in seconds
Fly Machines boot Firecracker microVMs in under a second. Sleep when idle, wake on request. Pay for what runs.
HOW IT WORKS
Four steps. Nothing else.
No Docker Compose, no Kubernetes, no reverse proxy to babysit. Gentity composes Fly Machines, Volumes, and the edge proxy for you.
- 01
Sign in with GitHub
Allowlist-gated OAuth. Cookies are scoped to your subdomain tree so every agent inherits auth.
- 02
Pick a template
Choose an agent image and resource shape. Templates are typed: image, internal port, data path, env schema.
- 03
Click create
Gentity provisions a Fly Machine plus a Volume, persists the encrypted env, and registers the subdomain.
- 04
Open the URL
Hit <id>.gentity.app. The control plane authenticates the request and proxies through Fly's internal DNS to your Machine.
EVALUATION POINTS
What to check before putting AI agents into production.
Gentity is built for teams that have moved beyond demos and need a repeatable way to run agents with isolation, state, URLs, and operational control.
Isolation per customer or workspace
Run each agent in its own microVM so credentials, files, and runtime state do not leak across users or teams.
A stable URL for every agent
Every instance gets a dedicated subdomain behind authentication, which makes it easier to hand an agent to a teammate or customer.
Persistent state for real work
Use persistent volumes for agents that need memory, files, cloned repositories, or long-running task context.
USE CASES
What teams put on Gentity.
Per-user agent sandboxes
Give every customer or every internal user their own agent box. State and credentials stay isolated; auth lives at the edge.
Long-running task agents
Spin up a Machine for an agent that crawls, watches a repo, or runs a multi-hour workflow. Pause and resume without losing state.
Self-hosted MCP / tool servers
Run an MCP or tool server per workspace. Gentity gives each one a dedicated subdomain, persistent volume, and access control.
BUILT ON
Fly Machines
Firecracker microVMs, sub-second cold start
Fly Volumes
Persistent storage per agent
Next.js 16
Control plane + edge proxy
Auth.js
GitHub OAuth + allowlist
Prisma + Neon
Postgres for instance state
AES-256-GCM
Encrypted env per instance
WHAT YOU GET
Sensible defaults, no Kubernetes.
- Firecracker microVM isolation per instance
- Encrypted env vars at rest (AES-256-GCM)
- Allowlist-gated GitHub OAuth at the edge
- Persistent Fly Volume per agent
- Sub-second cold start, sleep when idle
- Open source — fork or self-host the control plane
READY?
Sign in and spin up your first agent.
FAQ
Gentity questions teams ask first.
What is Gentity?
Gentity is an AI agent runtime from RootTeam. It provisions isolated Fly Machines with persistent volumes, authenticated URLs, and runtime state for agents, MCP servers, and long-running workflows.
When should a team use Gentity instead of a simple chatbot?
Use Gentity when an agent needs its own runtime, files, secrets, state, or a long-running process. A simple chatbot is enough for stateless conversations, but production agents often need a dedicated environment.
Can Gentity run MCP or tool servers?
Yes. One common use case is running a workspace-specific MCP or tool server with a dedicated URL, persistent volume, and access control.
How does Gentity compare to running AI agents on AWS Lambda or Cloud Run?
Lambda and Cloud Run are optimized for short-lived stateless functions. Gentity is built for agents that need persistent state — files, memory, cloned repositories — between runs, long-running processes measured in hours, isolated credentials per user or workspace, and a stable URL to share with teammates or customers. If your agent needs to pause, resume, or hold a persistent volume, Gentity fits better than a serverless function.
Can I self-host Gentity?
Yes. Gentity's control plane is open source. You can fork the repository and deploy it to your own Fly.io organization or infrastructure. The hosted version at gentity.ai lets teams start immediately without any infrastructure setup.
What does isolated Fly Machine mean in practice?
Each agent runs inside its own Firecracker microVM — a lightweight virtual machine that starts in under one second. Isolation means one agent's files, environment variables, and network cannot reach another agent's, which is important for multi-tenant products where different customers share the same deployment.
Is Gentity framework-agnostic?
Yes. Gentity is runtime-agnostic — you bring your own agent code, model, and framework (LangChain, Claude, GPT-4, or custom). Gentity provides the isolated execution environment, persistent storage, URL routing, and authentication. It does not dictate which AI model or SDK your agent uses.