Skip to main content
Babelfish is TAI42’s paid product family for teams that need agent work to run deterministically in production. It is built on the same open platform this site documents, and it reaches a running server the same way any other plugin does.
Babelfish is proprietary and licensed commercially — it is not part of the Apache-2.0 platform and is not published to PyPI or listed in the marketplace. Product details and pricing live at tai42.ai/babelfish.

​
What it adds

Babelfish Flows ships as one installable plugin carrying two halves:
  • A flow engine. Deterministic flows registered as ordinary tools through the public contract — run a flow, step it, read its state, and abort it. Because they are tools, everything the platform already does to a tool applies: access control, backends, schedules, and tracing.
  • A flow editor in the Studio. A front-end bundle the runtime serves to the Studio through its integrity-pinned import map, contributing a top-level Flows page and its nav entry.
A saved flow is a versioned preset with the graph carried in the preset’s fixed arguments, so flows version, diff, and roll back through the versioning spine like everything else.

​
How it plugs in

It is wired like any other plugin — a tools entry for the engine, a studio_plugins entry for the editor bundle, and the host routers the flow UI rides:
manifest.yml
The routers_modules order is load-bearing: tai42_skeleton.routers.plugins must be last, because its SPA catch-all matches any path and routers register in import order. The bundle is committed inside the distribution, so installing it needs no JavaScript toolchain on the server. The plugin adds no HTTP route of its own and claims no backend — see Studio plugins for how the Studio loads a plugin bundle and pins it.

​
See also