ai-parrot
Framework for building AI agents for Navigator
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11+; LLM provider API keys (e.g., OpenAI, Anthropic, Google) must be configured via environment or the `parrot setup` CLI wizard.
- 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.
License · maintenance · safety
MIT (permissive) — MIT license (permissive): you can use, modify, and distribute this package freely in commercial and open-source projects with minimal restrictions—only attribution required.
last release 2026-08-13 (1 days) · last repo commit 2026-08-14 · 29 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 86,802 downloads/mo, #13,836 on PyPI
Alternatives
Verify before relying
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())- 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.
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 on it.
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
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.
Requires Python 3.11+; LLM provider API keys (e.g., OpenAI, Anthropic, Google) must be configured via environment or the `parrot setup` CLI wizard.
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())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
| License | MIT permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 44 packagesCythontabulatemarkdown2beautifulsoup4nh3python-datamodelbackofftenacitytyping-extensionspydanticPyYAMLpython-frontmatterxmltodicttiktokenpsutilsemantic-text-splitternavconfignavigator-authnavigator-sessionnavigator-apiasyncdbormsgpackrichrequestsclickprompt_toolkitaiohttp-swagger3aiohttp-sse-clientaiohttp-corsbrotli |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 86,802 / month, #13,836 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaEnvironment :: Web EnvironmentFramework :: AsyncIOIntended Audience :: DevelopersOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Software Development :: Build ToolsTopic :: Software Development :: Libraries :: Python ModulesTyping :: Typed |
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
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “async AI agent framework”
- ai-parrotAI-Parrot is an async-first Python framework for building, extending,…
- chainlitChainlit provides a web UI framework for building conversational AI…
- azure-ai-agentserver-responsesProvides the Responses protocol endpoints for Azure AI Hosted Agent…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also agent-framework-core · stirrup · praisonaiagents · livekit-plugins-anthropic · tooluniverse · leptonai · PraisonAI · xpander-sdk · chainlit · npmai-agents