AgentTask
An AI-powered task planning assistant that helps you understand, plan, and schedule your projects with ease.
Features
- Task Understanding: Converts PDF documents to markdown and generates a comprehensive summary
- Task Planning: Creates a detailed plan based on your deadline, priority, and preferred working hours
- Calendar Generation: Generates a calendar file (.ics) that you can import into your calendar app
Installation
pip install agentask
Requirements
- Python 3.8 or higher
- Mistral API key (for OCR functionality)
- Gemini API key (for summary and plan generation)
Setup
- Create a project folder (e.g.,
project) - Inside the project folder, create a folder called
info - Place your task description files (PDFs) in the
infofolder - Create a
.envfile in the project folder with your API keys:
MISTRAL_API_KEY=your_mistral_api_key
GEMINI_API_KEY=your_gemini_api_key
Usage
Understanding Your Task
understand project
This command will:
- Check if the
infofolder exists and contains PDF files - Convert the PDF files to markdown using Mistral OCR
- Generate a summary of the task using Gemini API
- Save the summary as
summary.mdin theinfofolder
Planning Your Task
plan project
This command will:
- Ask for your project deadline in the format day/month/year
- Ask for your project priority (0-100%)
- Ask for your preferred working hours (e.g., "7-9, 22-23")
- Generate a detailed plan using Gemini API
- Save the plan as
plan.mdin theinfofolder
Generating a Calendar
generate calendar project
This command will:
- Check if the plan file exists
- Generate a calendar file (.ics) based on the plan
- Save the calendar file as
calendar.icsin theinfofolder
Example Workflow
# Create project structure
mkdir -p project/info
# Add your PDF files to the info folder
cp your_task_description.pdf project/info/
# Create .env file with your API keys
echo "MISTRAL_API_KEY=your_mistral_api_key" > project/.env
echo "GEMINI_API_KEY=your_gemini_api_key" >> project/.env
# Understand the task
understand project
# Plan the task
plan project
# Generate a calendar
generate calendar project
License
MIT
Metadata
Release files for agentask 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentask-0.1.3.tar.gz | 16.9 kB | Without provenance | Details for agentask-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentask-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for agentask-0.1.3-py3-none-any.whl |
Total release size: 38.3 kB
Release files / agentask-0.1.3.tar.gz
| Download URL | agentask-0.1.3.tar.gz |
|---|---|
| Size | 16.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ee1e973020f15cbe266cf81cd2362066e629612afdf0063628e49bf2d16e13e4
|
|
BLAKE2b-256 checksum How to use checksums |
0928e9211b14be586b4f2039a4fa65a0af43cf8760c6bbbd95a8e15cdb1685a9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.3
|
Release files / agentask-0.1.3-py3-none-any.whl
| Download URL | agentask-0.1.3-py3-none-any.whl |
|---|---|
| Size | 21.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
92f28a801104c4ac0b4c6ce6e727ff68780b1ffa73be33c59fc303479de7e6a8
|
|
BLAKE2b-256 checksum How to use checksums |
78905c000a382c9cbe6c249ae90928b4ec9f0bf0b6f26ad4c0e2fb468d22262f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.3
|
Security for agentask 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.