Jangada AI

A thin, adaptable layer over the LLM SDKs — swap provider/model/api_key without changing the rest of your code.

Get started Browse the docs

pip install "jangada-ai[all,rag,mcp]"

🤖 Feed it to Claude Code, Cursor, Codex & other AIs to integrate faster: llms.txt · llms-full.txt

Works with:

Anthropic

OpenAI

Groq

Gemini

Mistral

OpenRouter

AWS Bedrock

Azure OpenAI

Vertex AI

🔌 Docs via MCP

Connect these docs to your assistant

A hosted MCP server hands your AI assistant the ENTIRE documentation — so it writes code with the current, correct API, without inventing functions, signatures or parameters. It's Jangada itself acting as an MCP server.

Endpoint (HTTP)https://mcp.jangada.dev.br/mcp/

Claude Code (in the terminal)

claude mcp add jangada-mcp --transport http https://mcp.jangada.dev.br/mcp/

Cursor / Claude Desktop (MCP config)

{
  "mcpServers": {
    "jangada-mcp": {
      "url": "https://mcp.jangada.dev.br/mcp/"
    }
  }
}

Works with any client that supports MCP over HTTP — Claude Code, Claude Desktop, Cursor, Windsurf, Zed and more.

Explore

Getting started

Install, set your key and make your first call in minutes.

Providers

Anthropic, OpenAI, Groq and Gemini with the same API.

Structured Output

Pydantic-validated output on any provider.

Tools & MCP

Function calling and Model Context Protocol, provider-agnostic.

RAG

Chunk, embed, vector store (pgvector/Mongo) and hybrid search.

Reliability

Retry, error-based fallback, cost on the response and step-by-step debug.