task_researcher
If you are the rightful owner of task_researcher and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Task Researcher is a Python-based task management system designed for AI-driven development, featuring integrated research capabilities using the 'knowledge-storm' library.
Task Researcher is a comprehensive task management system tailored for AI-driven development projects. It leverages the 'knowledge-storm' library to break down complex projects into manageable tasks and subtasks, while also providing automated research capabilities to inform implementation details. The system supports both a command-line interface (CLI) and a Model Context Protocol (MCP) Server, allowing for flexible integration into various development workflows. Key functionalities include parsing project specifications to generate tasks, expanding tasks into subtasks using AI, analyzing task complexity, managing dependencies, and generating detailed research reports. The system is designed to work with multiple LLM providers and requires specific API keys for operation.
Features
- Parse Inputs: Generate initial tasks from project specification files such as 'functional_spec.md' and 'technical_spec.md'.
- Expand Tasks: Break down tasks into subtasks using AI and perform STORM-powered research for complex tasks.
- Update Tasks: Modify pending tasks based on new prompts or requirement changes.
- Analyze Complexity: Assess task complexity using AI and generate a report with recommendations.
- Dependency Management: Validate and automatically fix dependency issues such as missing references and simple cycles.
Tools
parse_inputs
Generates initial tasks from configured spec files.
update_tasks
Updates tasks from a given ID based on a prompt.
generate_task_files
Creates individual phase_XX_task_YYY.txt files.
expand_task
Expands a single task into subtasks, supporting research=True for STORM.
analyze_complexity
Analyzes task complexity and saves a report.
