Skip to main content
Use this page when a user asks an AI agent to connect, configure, or use AIsa inside an agent environment such as OpenClaw, Hermes Agent, Claude Code, Cursor, Codex, or another tool-calling assistant. Goal: get the agent to the smallest safe next step without loading broad documentation indexes.

​
Minimal setup facts

AIsa provides two endpoint families: For most model clients:
Use the API key as a Bearer token. Do not print, log, commit, or hardcode it. Prefer environment variables or the agent runtime’s secret store.
If the user has not provided a key, explain where to create one instead of inventing a placeholder value.

​
Choose one path

First identify what the user wants, then read only the docs for that path.

​
Agent behavior

  • Ask one clarifying question only if the target path is unclear.
  • Load the smallest relevant doc set for the task.
  • Do not open unrelated API pages.
  • Do not paste large docs into the conversation when a short summary and links are enough.
  • Do not choose image, video, embedding, Whisper, or TTS models as the main conversational model.
  • Before saying setup works, verify the relevant part with a small safe check.
  • For secrets, verify storage without revealing the key.

​
Evidence rule for research tasks

For factual claims, prefer official docs, API references, README files, changelogs, or runtime/API results over third-party summaries.

​
Copy prompt

Copy this prompt into an agent environment:

​
Fallback discovery

Use these only when the targeted docs above are not enough:
  • llms.txt: docs index for discovering additional AIsa pages.
  • llms-full.txt: full documentation bundle. Do not read it unless the user explicitly asks for full documentation ingestion.