Modern app development is quickly becoming AI-assisted, or entirely vibe-coded. Can you trust these apps in production? Yes, but only if you build on a framework that handles the hard stuff and forces AI agents to ship clean, modular software.
Reboot solves the hard problems once, at the framework level, so neither you nor your coding agent has to. What Rust's borrow checker did for memory management, and React did for component-based frontends, Reboot does for your backend: backend safety and data encapsulation, enforced by the framework rather than by review.
Try Reboot with Claude Code or Codex
Install the Reboot plugin:
curl -fsSL https://reboot.dev/install.sh | bash
Then describe what you want:
Build me a todo-list app I can use from a browser and from Claude and ChatGPT
The agent proposes a design, scaffolds the project — API, backend, frontend, sign-in, tests — and runs it. See Build with Claude Code or Build with Codex, or build one by hand to see every file.
Why a new framework?
Agents are blazingly fast, junior engineers. You cannot trust them to build your application correctly without a rock-solid foundation to stand on. A harness isn't enough.
- Correct concurrency and retry safety. Coding agents reliably
ship bugs in these two areas. The only way to fix this is to give
them constraints that make those bugs impossible by construction:
every method declares its kind —
reader,writer,transaction, orworkflow— and Reboot enforces what each one may do. - Lose nothing on reboot. Agents don't expect their code to
crash. Until now, the fix was to build on a durable execution
engine. Reboot goes further with durable applications: the
moment a function returns, its
stateis saved. Workflows resume where they failed — the steps that already finished are memoized rather than run again — and transactions keep everything atomic. No database, no cache, no queue. - Agents are lazy. You asked for a frontend, but what you really wanted was a reactive one. You wanted it to retry on an intermittent network failure, but instead it threw an error and never cleaned up its local React state. With Reboot you get these features, and many more, without ever having to ask.
- Agents make code hard to review. Even if some harness could get an agent to handle all of the concerns above, would you want to review that diff? Could you be sure it didn't introduce bugs? Reboot's semantics are simple enough, for humans and agents alike, that you can.
What it looks like
Define your API with Pydantic in Python (or Zod in TypeScript). Every method declares its kind, and whether an AI may call it:
from reboot.api import API, Field, Methods, Model, Reader, Tool, Type, Writer
class AccountState(Model):
balance: int = Field(tag=1, default=0)
class DepositRequest(Model):
amount: int = Field(tag=1)
class BalanceResponse(Model):
balance: int = Field(tag=1)
api = API(
Account=Type(
state=AccountState,
methods=Methods(
deposit=Writer(
request=DepositRequest,
response=None,
description="Add funds to the account.",
mcp=Tool(),
),
balance=Reader(
request=None,
response=BalanceResponse,
description="The account's current balance.",
mcp=Tool(),
),
),
),
)
Implement it. self.state is durable: when the method returns, the
new state is saved, all of it or none of it.
class AccountServicer(Account.Servicer):
async def deposit(
self,
context: WriterContext,
request: Account.DepositRequest,
) -> None:
self.state.balance += request.amount
async def balance(
self,
context: ReaderContext,
) -> Account.BalanceResponse:
return Account.BalanceResponse(balance=self.state.balance)
Call it from React through generated, typed hooks. useBalance
re-renders whenever the balance changes, whether this user, another
user, a workflow, or an AI changed it:
const account = useAccount({ id });
const { response } = account.useBalance();
await account.deposit({ amount: 50 });
The same two methods are tools for Claude, ChatGPT, or any other MCP
client, because they were declared with mcp=Tool().
One backend, many frontends
One app to serve every user — human or machine. You and your agents can build any kind of app with Reboot:
- Humans reach it through a
web app, a
React Native app
(alpha), or an
MCP UI inside
ChatGPT, Claude, or VS Code, where
UImethods render React components in the conversation. - Agents reach it over MCP: every method marked
mcp=Tool()is a tool. An agent can also run inside your app, with durable, replay-safe model and tool calls. - Services reach it from your own backend code, a script, or a plain HTTP request.
Signed-in users come built in. Plug in your favorite auth provider —
Google, GitHub, Auth0, Ory — and Reboot runs the OAuth server in front
of it, so a person signing in auto-constructs their User: the
per-user entry point the rest of your app hangs off, and the same
User on every frontend. See
Users and sign-in.
Status
Python backends are supported today. TypeScript backends and React
Native frontends are in alpha: the core of Reboot works in both
languages, but MCP UIs, UI methods, the built-in OAuth sign-in
flow, and durable agents are Python-only for now. More languages are
coming.
Get started today
Reboot is open source. Run a Reboot app on your own infrastructure or on Reboot Cloud.
- Reboot Cloud — deploy with
rbt cloud up. - Deploy on your own —
rbt serveon your own machines or Kubernetes. - Documentation — start with How Reboot works.
- Examples — complete applications to run and take apart.
Community
- Discord: discord.gg/cRbdcS94Nr — fastest way to get help or share what you're building
- Issues: github.com/reboot-dev/reboot/issues
Contributions are welcome. Open an issue to discuss substantial changes before sending a pull request.
License
4 maintainers
Release files for reboot 1.6.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| reboot-1.6.0-py3-none-manylinux_2_34_x86_64.whl | Python 3 | none | Linux glibc 2.34+ x86-64 | Details |
| reboot-1.6.0-py3-none-manylinux_2_34_aarch64.whl | Python 3 | none | Linux glibc 2.34+ ARM64 | Details |
| reboot-1.6.0-py3-none-macosx_14_0_arm64.whl | Python 3 | none | macOS 14.0+ ARM64 | Details |
Total release size: 73.4 MB
Release files / reboot-1.6.0-py3-none-manylinux_2_34_x86_64.whl
| Download URL | reboot-1.6.0-py3-none-manylinux_2_34_x86_64.whl |
|---|---|
| Size | 25.8 MB |
| Tags | Linux glibc 2.34+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
c658556cfed4c53f413c9f675a8dda259e0076311f74dc8d04c480b55e9aa069
|
|
BLAKE2b-256 checksum How to use checksums |
3df76d56b46c00980bb94e577edeb6f2a5813d5fe466fa54b49a8323dcc69b92
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.12
|
Release files / reboot-1.6.0-py3-none-manylinux_2_34_aarch64.whl
| Download URL | reboot-1.6.0-py3-none-manylinux_2_34_aarch64.whl |
|---|---|
| Size | 25.7 MB |
| Tags | Linux glibc 2.34+ ARM64 Python 3 |
|
SHA-256 checksum How to use checksums |
455128ee678386745843c41dae0f7e2774489d7ea9461cc8b44462bb58c2b14d
|
|
BLAKE2b-256 checksum How to use checksums |
f40067cd65203fd0479b299143345ab7d06c9d70ef924ed8738e34d7f224089f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.12
|
Release files / reboot-1.6.0-py3-none-macosx_14_0_arm64.whl
| Download URL | reboot-1.6.0-py3-none-macosx_14_0_arm64.whl |
|---|---|
| Size | 22.0 MB |
| Tags | Python 3 macOS 14.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
96ceaace42f82a23a7a6d116667406aa2661b7f3e41a530b42f5e8e573c21086
|
|
BLAKE2b-256 checksum How to use checksums |
6153f879431323eeb89fd1cd1f3e234f0701b8fbc4610955c995e69ba5c455c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.12
|
