Tools and toolkits for AI-Parrot agents
Project description
AI-Parrot Tools
ai-parrot-tools is a collection of tools and toolkits for AI-Parrot agents. Each tool wraps an external API or service behind a unified interface that agents can discover and invoke automatically.
Installation
pip install ai-parrot-tools
Install only the extras you need:
# Individual extras
pip install ai-parrot-tools[aws]
pip install ai-parrot-tools[slack]
pip install ai-parrot-tools[jira]
pip install ai-parrot-tools[google]
pip install ai-parrot-tools[finance]
pip install ai-parrot-tools[db]
# Everything
pip install ai-parrot-tools[all]
Available Extras
| Extra | Description |
|---|---|
jira |
Jira issue tracking |
slack |
Slack messaging |
aws |
AWS services (EC2, S3, RDS, Lambda, ECS, IAM, etc.) |
docker |
Docker container management |
git |
Git repository operations |
analysis |
Data analysis with pandas, numpy, autoviz |
excel |
Excel and ODF spreadsheet support |
sandbox |
Sandboxed code execution via Docker |
codeinterpreter |
Interactive code interpreter |
pulumi |
Pulumi infrastructure-as-code |
sitesearch |
Website crawling and search |
office365 |
Microsoft 365 / Graph API integration |
scraping |
Web scraping with Selenium |
finance |
Financial analysis (TA-Lib, yfinance, Alpaca) |
db |
Database querying via QuerySource |
flowtask |
FlowTask workflow integration |
google |
Google APIs (Search, Maps, Routes) |
arxiv |
arXiv paper search |
wikipedia |
Wikipedia lookups |
weather |
OpenWeatherMap |
messaging |
MQTT and IMAP messaging |
Quick Start
from parrot.bots import Agent
agent = Agent(
name="assistant",
instructions="You are a helpful assistant.",
tools=["google_search", "weather", "calculator"],
)
response = await agent.chat("What's the weather in New York?")
Tools are registered by name. Pass a list of tool names to any AI-Parrot agent and they are loaded on demand.
Creating Custom Tools
Use the @tool decorator for simple functions:
from parrot.tools import tool
@tool
def get_stock_price(symbol: str) -> str:
"""Get the current stock price for a ticker symbol."""
...
Use AbstractToolkit for multi-tool collections:
from parrot.tools import AbstractToolkit
class MyToolkit(AbstractToolkit):
name = "my_toolkit"
description = "A collection of related tools."
def get_tools(self):
...
Requirements
- Python >= 3.11
- ai-parrot >= 0.23.18
License
MIT
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ai_parrot_tools-0.1.8.tar.gz.
File metadata
- Download URL: ai_parrot_tools-0.1.8.tar.gz
- Upload date:
- Size: 680.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4a345c47d8d47ee463ff592ef023039294e7d8fc88f608a5126baede9f25ebf6
|
|
| MD5 |
54f28260a16146fb3706c6681c9c3fb1
|
|
| BLAKE2b-256 |
40f9b449c346bcf63ea5fa4a5bf3003821013c8726415a86e1fb7c05141e3913
|
Provenance
The following attestation bundles were made for ai_parrot_tools-0.1.8.tar.gz:
Publisher:
release.yml on phenobarbital/ai-parrot
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
ai_parrot_tools-0.1.8.tar.gz -
Subject digest:
4a345c47d8d47ee463ff592ef023039294e7d8fc88f608a5126baede9f25ebf6 - Sigstore transparency entry: 1182356183
- Sigstore integration time:
-
Permalink:
phenobarbital/ai-parrot@fa32569e94d60a06cdbc51ec46135b6ade932bfa -
Branch / Tag:
refs/tags/0.24.9 - Owner: https://github.com/phenobarbital
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@fa32569e94d60a06cdbc51ec46135b6ade932bfa -
Trigger Event:
release
-
Statement type:
File details
Details for the file ai_parrot_tools-0.1.8-py3-none-any.whl.
File metadata
- Download URL: ai_parrot_tools-0.1.8-py3-none-any.whl
- Upload date:
- Size: 798.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b6ce2c2fa45817bbe903c862a69132f5f8d52581155559da8702f49bcb118cac
|
|
| MD5 |
71514c397e82cf0b9dc12b3f39d309b0
|
|
| BLAKE2b-256 |
bc3c00fda7326befc96cd2b0562e3a4164ea730f92276129a3e71194f7d83ee3
|
Provenance
The following attestation bundles were made for ai_parrot_tools-0.1.8-py3-none-any.whl:
Publisher:
release.yml on phenobarbital/ai-parrot
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
ai_parrot_tools-0.1.8-py3-none-any.whl -
Subject digest:
b6ce2c2fa45817bbe903c862a69132f5f8d52581155559da8702f49bcb118cac - Sigstore transparency entry: 1182356243
- Sigstore integration time:
-
Permalink:
phenobarbital/ai-parrot@fa32569e94d60a06cdbc51ec46135b6ade932bfa -
Branch / Tag:
refs/tags/0.24.9 - Owner: https://github.com/phenobarbital
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@fa32569e94d60a06cdbc51ec46135b6ade932bfa -
Trigger Event:
release
-
Statement type: