Skip to content

Your editor found the spec. Your script didn't.

Chat apps and automations shouldn't need a second knowledge stack to answer from the same files.

What goes wrong

Scripts and apps already speak the chat APIs you know. Adding “use our docs” usually means forking every client: custom retrieve-then-prompt code, duplicated stores, and drift between “the editor path” and “the automation path.”

Why it matters

You want one hop: intercept the chat request, look up the shared local corpus, inject the relevant passages, then send it on. Same quality bar whether the caller is an SDK you already use or a local model host.

What good looks like

Point existing clients at a local listener and keep using the SDKs you have. Retrieval and injection happen before the upstream model sees the prompt.

How Aura Terran helps

Aura Terran can sit in front of the chat APIs your tools already use (OpenAI-shaped and Ollama-shaped). Each request looks up your local docs, injects context, then forwards — Personal tier and up.

  • Same namespaces and search settings as the Search page, REST, and assistant tools
  • Optional web search and extra tools in the same path on higher tiers
  • Replies can be scored against the injected passages so weak answers are visible

Try Aura Terran

Give AI your project docs without uploading them to the cloud. Index a folder on Windows and search in minutes.

Windows installer — the .exe will not run on Mac, Linux, phones, or tablets. Open the download on a Windows PC.

Digitally signed by Halo Softworks

Prefer the setup download from this site. Verify this download · Download security

Agree to continue

Checkout opens Stripe for a one-time purchase. Please confirm the legal terms first.

Enlarged image