Getting Started with AnyTask

AnyTask is an AI-native task management tool built for Linear-style workflows. It supports both human users and AI agents as first-class citizens, enabling seamless collaboration between developers and AI assistants.

What is AnyTask?

AnyTask provides a powerful task management system with:

• Linear-style Workflows - Familiar project management patterns with tasks, labels, and dependencies
• AI-Native Design - Built from the ground up to support AI agents alongside human users
• CLI-First Approach - Command-line interface for developers who prefer terminal workflows
• MCP Integration - Deep integration with Claude Code through Model Context Protocol
• Smart Task Management - Intelligent task suggestions, dependency tracking, and progress visualization

Key Features

For Developers

1. Powerful CLI - Comprehensive command-line interface for managing tasks, workspaces, and projects
2. Git-Like Workflow - Familiar commands and patterns for developers
3. Dependency Management - Track task dependencies and visualize task graphs
4. Kanban Board - Visual board view with customizable filtering and grouping
5. Timeline & History - Track task history, attempts, and artifacts

For AI Agents

1. Agent API Keys - Dedicated authentication for AI agents
2. MCP Server - Model Context Protocol integration for Claude Code
3. Work Attempts - Track AI agent work sessions with artifacts
4. Smart Suggestions - AI-powered task recommendations and organization
5. Auto-decomposition - Break down goals into actionable tasks

For Teams

1. Multi-Workspace Support - Organize work across different workspaces
2. Team Collaboration - Share workspaces with team members
3. Project Organization - Group tasks into projects
4. Labels & Filters - Organize and find tasks quickly
5. Progress Tracking - Visualize team progress and velocity

Getting Started

Installation

The AnyTask CLI is installed as part of the backend package:

# Install dependencies
make install

# Verify installation
anyt --version

Quick Start

1. Add an environment

   anyt env add dev http://localhost:8000
   

2. Login

   anyt auth login --token
   

3. Initialize a workspace

   anyt init
   

4. Create your first task

   anyt task add "My first task" --priority 1 --project 1
   

5. View your tasks

   anyt board
   

Documentation Structure

Our documentation is organized into these main sections:

• Getting Started - Introduction and quick start guide
• CLI Usage - Comprehensive CLI command reference
• MCP Integration - Integration with Claude Code and AI agents

Next Steps

• Read the CLI Usage Guide for detailed command reference
• Learn about MCP Integration to connect with Claude Code
• Explore advanced features like dependency management, task templates, and AI commands

Support

For issues or questions:

1. Check the documentation sections
2. Run health checks with anyt health
3. File an issue on GitHub with reproduction steps