thcThought Control

Thesys C1 (now OpenUI Cloud) and OpenUI

Hosted generative-UI API plus open compact UI language.

thesys.dev ↗repo ↗docs ↗OpenUI Cloud (formerly C1 API) ↗OpenUI playground ↗

license
MIT · OpenUI (framework, OpenUI Lang, renderers) is MIT. C1 / OpenUI Cloud and OpenUI Gateway are proprietary hosted services.
language
TypeScript
backing
Thesys (company); funding not verified
stars
10,546 (as of 2026-10-09)
downloads
@openuidev/react-lang 135,398/week (npm, week ending 2026-10-07); site claims 642,626/month
latest release
@openuidev/react-lang 0.3.2, 2026-10-08
first release
2026-03
ignore

A web generation service; only its compact-language token-cost lesson applies to scene.

Ignore it for this purpose.

the steelman: the best honest case for it

Thesys attacks the real cost of generative UI: tokens and latency. OpenUI Lang is a purpose-built compact language that, by its own reproducible tiktoken benchmark, needs roughly half to a third of the tokens of json-render or C1's own old JSON, which means faster first paint and cheaper turns. The framework is MIT, renders in four web frameworks, interoperates with A2UI and AG-UI, and the hosted OpenUI Cloud adds the unglamorous production parts (validation, correction, fallbacks, model gateway, observability) teams otherwise build themselves.

scores
datadriveseeedittimeratetermpxteachmatureopen
UI as data4 scene 5OpenUI Lang is a serializable text format, but not JSON.
Agent can drive it2 scene 5More than code generation (constrained DSL rendered safely) but no protocol to change a live instance.
Agent can see it1 scene 5No readback mechanism found in docs reviewed.
Small, targeted edits1 scene 5
Time travel0 scene 0
Live data rate1 scene 5
Terminal native0 scene 5
Pixel graphics3 scene 4Web charts and components.
Teaching0 scene 3
Maturity3 scene 1
Openness3 scene 4MIT framework, proprietary hosted API.

Thesys C1 (now OpenUI Cloud) and OpenUI scene now scene planned

how agents use it

How

Generation API/SDK: the model outputs UI as OpenUI Lang (or C1 responses) that a client renders; no live control channel.

Wiring it in

Low for web apps: swap the LLM endpoint (C1) or add the OpenUI renderer and prompt.

Seeing the result

Not documented beyond normal chat/app state (not verified).

Small edits

Not documented; responses are regenerated per turn (not verified).

History

None documented.

In short

Optimised for cheap, fast generation of web UI, not for operating a live interface.

architecture

C1 was an OpenAI-compatible LLM API that returns UI (charts, forms, tables, cards) instead of text, rendered by Thesys's React SDK. It is now 'OpenUI Cloud', built on the open OpenUI framework: developers define a component library (Zod-typed), generate a system prompt from it, the model streams OpenUI Lang (a compact text language, not JSON), and React/Vue/Svelte/Angular renderers draw it progressively. @openuidev/a2ui offers an A2UI v1.0 client with OpenUI Lang component payloads; @openuidev/langchain streams OpenUI through AG-UI.

performance

Token benchmark is published in the repo (reproducible); render-speed and user-preference claims are marketing without published method.

adoption and upkeep

Adoption

Commercial generative-UI API rebranded as OpenUI Cloud, with an open-source OpenUI framework that is growing quickly (10.5k stars).

Used by: Entelligence (Ask Ellie), per thesys.dev, CTRLAgent, FieldCamp (logos on thesys.dev)

Maintainability

Active open-source repo backed by a commercial product.

Releases: Frequent package releases (five packages released 2026-10-08) · Contributors: ~50 (GitHub contributors API incl. anonymous) · Recent: 361 commits on main since 2026-07-11 (GitHub API) · Bus factor: medium: one company

weaknesses
and thc-scene

Overlap

Agent-generated UI constrained to a trusted component library.

What scene would be reinventing

Little; scene does not target model-generated UI token cost.

The gap it leaves

Terminal rendering, live control, readback, data streams bypassing the model, pixels, history.

What to borrow

  • A compact text form for agent-written scenes to cut tokens (the token benchmark is a useful yardstick)
  • Prompt generation from the component library
sources
  1. Thesys homepage (OpenUI Cloud, formerly C1 API) thesys.dev
  2. thesysdev/openui README (token benchmark) github.com
  3. npm downloads API api.npmjs.org