Task Researcher
by tejpalvirk
Task Researcher is a Python task management system designed for AI-driven development. It features integrated, in-depth research capabilities using the `knowledge-storm` library to break down complex projects, generate tasks, and leverage automated research to inform implementation details.
Last updated: N/A
What is Task Researcher?
Task Researcher is a Python-based task management system that integrates AI-driven task generation, expansion, and research capabilities. It provides both a command-line interface (CLI) and a Model Context Protocol (MCP) Server for interacting with AI models and managing tasks.
How to use Task Researcher?
The Task Researcher can be used via the command line or as an MCP server. The CLI allows for parsing input files, expanding tasks with or without research, updating tasks, analyzing complexity, managing dependencies, and generating files. The MCP server exposes these functionalities as tools and resources for MCP clients like Claude Desktop or custom applications.
Key features of Task Researcher
Parse Inputs from project specification files
Expand Tasks using AI and STORM-powered research
Update Tasks based on new prompts
Analyze Complexity using AI
Dependency Management (validation and fixing)
Generate Files for each task and subtask
Standalone Research using
knowledge-stormMCP Server functionality for integration with AI clients
Use cases of Task Researcher
Breaking down large software projects into manageable tasks
Automating research for complex tasks to inform implementation
Integrating task management with AI development workflows
Using AI to analyze task complexity and suggest improvements
FAQ from Task Researcher
What is the difference between --research and --research-hint?
What is the difference between --research and --research-hint?
--research triggers the full STORM-based workflow, performing web searches and synthesizing reports. --research-hint modifies the prompt for the primary LLM to leverage its internal knowledge base more deeply.
What API keys are required?
What API keys are required?
You need an API key for at least one supported LLM provider (e.g., Anthropic, Google Gemini, OpenAI) and an API key for a search engine supported by knowledge-storm (e.g., Bing Search, You.com, Tavily).
How do I install Task Researcher?
How do I install Task Researcher?
Clone the repository, install dependencies using Poetry (recommended) or pip, and configure your environment variables in a .env file.
How do I run the MCP server?
How do I run the MCP server?
Use the command poetry run task-researcher serve-mcp or poetry run python -m task_researcher.mcp.server.
What are the exposed MCP tools?
What are the exposed MCP tools?
The exposed MCP tools include parse_inputs, update_tasks, generate_task_files, expand_task, expand_all_tasks, analyze_complexity, validate_dependencies, fix_dependencies, and research_topic.