Asha, in your product.

1. 1

   Install and get a key

   One file, no dependencies. asha init creates a free key and walks you through steps 2 and 3.

   Terminal Copy

   curl -fsSL https://askasha.org/cli/install.sh | sh
   asha init

2. 2

   Make it yours

   Your product's name, who reads the answers, how long they are, emoji or none. Saved on your key.

   Terminal Copy

   asha config set name=CareBot verbosity=brief emoji=off

3. 3

   Ship it, or hand it to your agent

   Call the API from your backend, or give Claude Code, Codex, Cursor, or Gemini CLI Asha as a tool.

   Terminal Copy

   asha mcp add claude-code

curl -X POST https://api.askasha.org/a2a/v1/message:send \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "asha",
    "message": {
      "role": "user",
      "parts": [{"text": "Which antihypertensives are safe in pregnancy?"}]
    },
    "metadata": {"audience": "clinician", "session_id": "visit-2041"}
  }'

Already on OpenAI SDKs, LangChain, LiteLLM, or Vercel AI? Change base_url and the key: Drop-in with OpenAI SDKs. Terminal: Command line. Every field: Send a message and Stream a response.

claude mcp add asha -- asha mcp

Then ask your agent: "Use Asha to check whether ibuprofen interacts with lisinopril, for a patient." BAA acceptance stays with a person (asha baa accept); the agent can read the text and the status. No MCP? Point it at llms-full.txt. Details: Use with your agent.

Limits, rate windows, and error codes: Plans, limits, and errors. BAA: read, accept, and check it from the API or asha baa accept, see BAA, self-serve. Higher volumes: [email protected].