ai-parrot

What it is and what it does

AI-Parrot is an async-first framework for building AI agents and chatbots in Python. It abstracts over multiple LLM providers (OpenAI, Anthropic, Google, Groq, X.AI, HuggingFace, vLLM, OpenRouter, and Ollama), exposing a unified client interface for completions, vision, embeddings, and image generation. The core package provides base abstractions (`AbstractTool`, `AbstractToolkit`, `@tool` decorator) and lightweight built-in tools; heavier implementations and specialized pipelines are split into separate packages (ai-parrot-tools, ai-parrot-loaders, ai-parrot-pipelines) so you install only what you need.

The framework is built on navigator-api and emphasizes async-first design with support for agent-to-agent (A2A) communication, memory management, tool orchestration, and serving agents via the Model Context Protocol (MCP). It includes a CLI (`parrot`) for interactive setup, configuration, MCP server startup, and autonomous agent deployment as systemd services. Whether you need a simple chatbot, multi-agent workflows, or a production-ready AI service, the framework exposes the primitives to build it efficiently.

Use it for:

• Build a chatbot with tool-calling capabilities that queries weather APIs, databases, or custom services in response to user queries.
• Orchestrate multi-agent workflows where agents communicate with each other to solve complex tasks (e.g., research agent + summarizer agent).
• Deploy an autonomous agent as a systemd service using the CLI, with configuration-driven LLM provider selection and credential management.
• Serve agents via the Model Context Protocol (MCP) to integrate with external tools and clients that speak the MCP protocol.
• Rapidly prototype AI applications by switching between LLM providers (OpenAI, Claude, Gemini, etc.) without rewriting agent logic.
• Build RAG (Retrieval-Augmented Generation) pipelines using the document loaders package for PDF, YouTube, audio, and web content.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

AI-Parrot is an async-first Python framework for building, extending, and orchestrating AI agents and chatbots with unified LLM provider support, tool management, agent-to-agent communication, and Model Context Protocol (MCP) serving.

Yes, with conditions. AI-Parrot is actively maintained, has no known vulnerabilities, and offers a well-structured async framework for agent and chatbot development with broad LLM provider support. The modular monorepo design lets you install only what you need. However, the 44 runtime dependencies create medium install friction; verify that the dependency footprint is acceptable for your deployment environment. Best suited for developers building production AI agents or multi-agent orchestration systems who can tolerate the dependency load and require async-first design.

Install

ai-parrot on PyPI

pip install ai-parrot

uv add ai-parrot

poetry add ai-parrot

Installing ai-parrot

Before you install

Medium install friction: 44 runtime dependencies including Cython, pydantic, aiohttp, and navigator ecosystem packages. Active maintenance (last commit 2026-08-14, released 2026-08-13) with binary wheels for Python 3.11–3.14 on Linux. No known vulnerabilities.

License in practice

MIT license (permissive): you can use, modify, and distribute this package freely in commercial and open-source projects with minimal restrictions—only attribution required.

Quickstart

import asyncio
from parrot.bots import Chatbot
from parrot.tools import tool

@tool
def get_weather(location: str) -> str:
    return f"Weather in {location} is Sunny, 25C"

async def main():
    bot = Chatbot(
        name="WeatherBot",
        llm="openai:gpt-4o",
        tools=[get_weather],
        system_prompt="You are a helpful weather assistant."
    )
    await bot.configure()
    response = await bot.ask("What's the weather in Madrid?")
    print(response)

asyncio.run(main())

Requires Python 3.11+; LLM provider API keys (e.g., OpenAI, Anthropic, Google) must be configured via environment or the `parrot setup` CLI wizard.

Verify before relying

• Exact scope of the 44 runtime dependencies and whether all are required for basic usage or only for optional features.
• Performance characteristics and scalability limits for multi-agent orchestration workflows.
• Stability guarantees for the monorepo split (ai-parrot-tools, ai-parrot-loaders, ai-parrot-pipelines) and backward compatibility across versions.

Package facts

Evidence: ai_parrot-0.25.35-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; ai_parrot-0.25.35-cp311-cp311-musllinux_1_2_x86_64.whl; ai_parrot-0.25.35-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; ai_parrot-0.25.35-cp312-cp312-musllinux_1_2_x86_64.whl; ai_parrot-0.25.35-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; ai_parrot-0.25.35-cp313-cp313-musllinux_1_2_x86_64.whl; ai_parrot-0.25.35-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; ai_parrot-0.25.35-cp314-cp314-musllinux_1_2_x86_64.whl

Keywords: asyncio, asyncpg, aioredis, aiomcache, artificial intelligence, ai, chatbot, agents

Tags

More Python Modules packages

Further reading