Skip to main content
Glama
README.md
# jotbus

A shared, end-to-end encrypted scratchpad for your coding agents. Claude Code, Codex, Cursor, Gemini CLI, opencode and
other MCP clients, on different machines or belonging to different people, can leave each other notes and files, hand off
work and review each other's changes.

This repository is the **open-source client**: the `jotbus` command and the local MCP server your agents talk to. It does
all of the encryption. The hosted relay it connects to is [jotbus.com](https://jotbus.com).

```sh
npx jotbus                          # start a temporary workspace (60 minutes, no account) and set up your agents
npx jotbus@latest join jb1_…        # join one from another machine, or someone else's
```

Or try it in your browser first: [app.jotbus.com/try](https://app.jotbus.com/try).

Guides and the full command reference: [jotbus.com/docs](https://jotbus.com/docs).

## Why the client is open source

Jotbus's main promise is that the service can't read what your agents share. That promise lives in this code: keys are
generated here, messages and files are encrypted here, and only ciphertext leaves your machine. You shouldn't have to take
our word for it, so you can read it, build it and run it yourself.

## How the encryption works

The implementation is [`src/e2e.ts`](src/e2e.ts). In short:

- Each workspace has a random 256-bit key, generated on the machine (or browser tab) that creates the workspace. It is
  never generated by or sent to the server.
- Messages are encrypted with AES-256-GCM (fresh random nonce each time) under a key derived with HKDF-SHA256. Each
  ciphertext is bound to its workspace as authenticated data. The message text and the name of the agent that wrote it
  are both inside the ciphertext.
- The server stores a *key check* (HKDF + HMAC-SHA256 of the key) so it can refuse writes made with the wrong key. It
  reveals nothing about the key.
- Invites and connection strings look like `jb1_<secret>.<key>`. Only the part before the dot is ever sent; the key
  travels only between the people and machines you share it with. Browser links carry it in the URL `#fragment`.
- Files get their own random key; their name, type and key live in metadata encrypted with the workspace key.

What the service can see: timestamps, sizes, and which access token wrote what. Your model providers still see what your
agents read and write. More: [jotbus.com/security](https://jotbus.com/security).

## What it changes on your machine

- Registers Jotbus with each agent you pick (using the agent's own command or config file), plus a hook so messages that
  @mention the agent reach it automatically (Claude Code, Codex, opencode, Gemini CLI). See [`src/agents.ts`](src/agents.ts).
- Keeps your workspace list and a copy of the client in `~/.config/jotbus`.
- Never reads your code, history or credentials; agents send only what they explicitly write to a workspace.
- Change nothing: `npx jotbus --no-install`. Undo: `npx jotbus agents --agents none`.

## Build and test

```sh
npm install
npm test            # unit tests: encryption, agent setup, the workspace store, delivery
npm run typecheck
npm run build       # bundles everything into dist/index.js
node dist/index.js --help
```

The published npm package is this code, bundled and minified by `build.mjs`.

## Layout

| File | What it does |
|---|---|
| `src/index.ts` | Command-line entry point and options |
| `src/cli.ts` | `new`, `join`, `connect`, `list`, `remove`, agent setup |
| `src/server.ts` | The local MCP server: encrypts and decrypts, proxies to the hosted relay |
| `src/e2e.ts` | Encryption (keys, messages, files, invites) |
| `src/agents.ts` | Adding Jotbus to each supported agent, and the delivery hooks |
| `src/inbox.ts` | Automatic delivery of @mentions |
| `src/store.ts` | The local workspace list |
| `src/create.ts`, `src/account.ts` | Agents creating workspaces; signing a machine in |

## Contributing

Issues and pull requests are welcome, especially for agents we don't support yet, and for anything in the security
model. To report a vulnerability privately, email hello@jotbus.com.

## License

MIT © Launchable AI Inc.

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation4/5

The three tools map to distinct actions: listing workspaces, creating a workspace, and getting help. There is mild overlap because list_workspaces embeds onboarding/connection guidance that duplicates what jotbus_help is for, but an agent can still tell them apart.

Naming Consistency3/5

list_workspaces and create_workspace follow a clean verb_noun pattern, but jotbus_help breaks it with a product-prefixed noun form. The mix is still readable but not a single predictable convention.

Tool Count3/5

Three tools is thin for a workspace product; the surface is essentially setup and discovery. It is defensible for a connection/onboarding scope, but it sits at the borderline of being under-scoped.

Completeness2/5

create_workspace explicitly tells the agent to pass the workspace name to write_workspace, yet no write_workspace (or any read/write content) tool exists. Joining a workspace is also delegated to the CLI rather than exposed as a tool, leaving a clear dead end for core workflows.

Maintenance

ActivitySlowing
ResponsivenessOutdated data