Turn your APIs, data, and scripts into AI tools without writing code.

No. You build a tool by picking one of five templates and filling in the fields — a JSON response, an HTTP request to an API you already have, a subset of an external MCP server's tools, a shell command, or a local executable. There is no SDK to learn, no server to write and no deploy step. If you can fill in a form and paste an API key, you can ship a tool your AI can call.

Only inside a workspace you gave it. Shell commands never run on your host — they run in that node's Docker container, and the read_file and write_file tools are confined to that one workspace folder, with symlinks resolved before the containment check so a link pointing out is caught like a ../ escape. The container drops all capabilities, sets no-new-privileges, runs as an unprivileged user under memory, CPU and process ceilings, and gets an environment built from an allow-list rather than inherited from yours. The one deliberate exception is the admin-only Local Command tool, which runs a fixed program on your host on purpose.

Not if you gate the node. An authorization gate is checked before the HTTP API serves a request and at the moment an MCP session initializes, and it fails closed — a missing token, an unknown mode, a malformed gate or an error all deny. You pick the mode: a list of people this machine knows, a JWT tested against conditions you write, or your own endpoint that has to return 2xx. A node with no gate is open to whatever can reach it, which until you publish means only your own machine — and the app flags a published node with nothing gating it in red.

Yes. Wysebee Desktop is free to download and use, with no account, no sign-in, and no telemetry. You build nodes on your own machine and point your own Claude or ChatGPT at them. We charge for Wysebee Cloud and for on-premises licenses, not for the desktop app.

A node is a named bundle of tools. Give it an MCP server entry point and it is served at an MCP endpoint any MCP client — Claude Desktop, ChatGPT, your own agent — can connect to. Give it the Node API entry point and the same tools are reachable over plain HTTP. Wysebee hosts no model and runs no agentic loop: your AI decides what to call, Wysebee answers.

macOS 12 or later on Apple Silicon or Intel, and Windows 10 or later on 64-bit. The Mac build is Developer ID signed and notarized by Apple, so it opens with no Gatekeeper warning. The Windows installer, app and uninstaller are Authenticode-signed with an EV certificate and timestamped, so Windows names Wysebee Inc. as the publisher instead of warning about an unknown one — and it installs for your user only, with no administrator prompt. A Linux build is not available yet.

Not to run the app. Wysebee Desktop starts, serves nodes, and answers your AI without it. Docker Desktop becomes necessary only the moment a node needs to run a shell command — that is, the moment you create a workspace and connect it to a node.

When the tools stop being yours alone. Cloud gives your team shared nodes, accounts, SSO, and audit logs with no infrastructure to run. On-premises gives you the same platform inside your own VPC — AWS, GCP, Azure, or bare metal — when compliance requires that customer data never leaves your infrastructure.

On the desktop, nowhere: everything durable is a SQLite file in your user data directory and a folder per workspace, both on your machine. On-premises, nothing leaves your infra. On Cloud, your data is processed in-memory for the request and is never used to train anyone's models, with encryption in transit and at rest and audit logs throughout.

No — that's the point. Wysebee is the AI platform delivered as a product. Your existing engineers wire it up the same way they integrate any other API, and the retrieval, guardrails, cost caps, logging, and evals are already there.

The desktop app is free. Wysebee Cloud is usage-based, and on-premises is a flat license — both quoted after a 30-minute scoping call. No hourly billing, no surprises.