Some interfaces need computation the A2UI vocabulary can’t express: a custom calculation, a live-updating value, a transformation of fetched data. For those, MeghaOS uses Just-in-Time (JIT) code: the LLM writes scripting code, the agent runs it in a sandbox, and the result is bound into the rendered UI.

​
How it works

compose_ui returns A2UI JSON. When custom logic is required, the LLM embeds a __jit__ key holding scripting code inside the same response (no separate code-generation call).

​
The sandbox

The sandbox runs generated code safely. It is a restricted environment that blocks unauthorized filesystem and network access. Code execution is designed to be fully isolated to protect the host system.

​
Binding output to the UI

A UI component can declare "jit_bind": "key". After the code runs and returns a dict, the value at that key is bound into the component deterministically. No guessing which output maps to which widget.

​
Streaming (live widgets)

For widgets that update continuously, the streaming engine runs a loop that re-executes the code on an interval and pushes updates to the shell:
  • Drift-free timer: each cycle sleeps just enough so ticks don’t drift.
  • JSON diffing: computes the delta each tick and sends only a patch, minimizing payload size.
  • Updates are broadcast straight to the shell.
A streaming app is auto-detected when its code references the injected elapsed_time value (seconds since the stream started), letting the code animate or recompute against a live clock each tick.

​
Reactive actions

When the user interacts with a JIT widget (e.g. changes a parameter), the system performs reactive binding: it re-substitutes dynamic values into the original template, requiring zero additional LLM calls. Fast, deterministic, cheap.

​
Semantic code cache

Generated code is cached semantically. The system uses text embeddings so a similar query reuses prior code instead of regenerating.