Welcome to Aditya documentation
A practical guide to the current source build: choose an interface, understand the runtime, and start with a project you can inspect.
Get started
Aditya is a research project being built around useful language and project work. These guides describe the local agent runtime and the interfaces already represented in the repository. They are not a public API reference or a promise that every research direction is ready for use.
Start with a small, recoverable workspace. Confirm where the model runs and what the selected interface is allowed to do before giving it a task.
Choose a surface
The Python CLI is a compact entry point into the agent loop. The local server supplies the runtime for the web and desktop workspaces. Those paths share concepts, but their startup requirements and permission settings can differ.
- CLI: begin in a selected project directory and inspect the task from the terminal.
- Local server: provide the runtime used by the visual interfaces.
- Model workspace: see the intended interaction on the public website. Its screens are illustrations, not live runs.
Read the guides in context
Setup, execution and verification answer different questions. A command can start the program without establishing that the model service is reachable. A tool can finish without proving that the requested task is complete. The guides keep those distinctions explicit.
Some package names and configuration identifiers still use Aroxa. Keep the identifiers required by the current source rather than substituting an undocumented Aditya command.
What is still research?
NIF explores how capability can be composed, checked, retained and withdrawn. The code contains runtime and adapter-management mechanisms, but broader transfer and consolidation claims require dedicated experiments. Read the research pages for the distinction between implementation and a measured result.
Access to the live model remains private. There are no public API-key, pricing or rate-limit instructions in these guides.