AI-native task management CLI for coding agents and human developers
Project description
AnyTask CLI
AI-native task management CLI for coding agents and human developers
AnyTask CLI is a command-line interface for managing tasks and projects, designed specifically for AI agents and developers working together. It provides Linear-style task management with agent-aware features, MCP (Model Context Protocol) integration, and powerful AI-assisted commands.
Features
- Linear-style Task Management: Human-readable task IDs (DEV-123), status workflows, priorities, and dependencies
- Multi-Environment Support: Manage tasks across dev, staging, and production environments
- Workspace & Project Organization: Isolated workspaces with role-based access
- Rich Terminal UI: Beautiful, color-coded task boards and visualizations
- Agent Integration: Native support for AI agents via API keys and MCP server
- Worker System: Automated task execution using declarative YAML workflows
- AI-Powered Commands: Task decomposition, smart suggestions, and context-aware assistance
Installation
Recommended: Install with uvx or pipx
For the best experience, install using uvx (recommended) or pipx:
# Using uvx (recommended - no installation needed)
uvx anyt --help
# Or using pipx (install once, use everywhere)
pipx install anyt
anyt --help
Alternative: Install with pip
pip install anyt
Quick Start
1. Configure Environment
The CLI comes pre-configured with a production environment. To use a local development server:
anyt env add dev http://localhost:8000
anyt env use dev
View your environments:
anyt env list
2. Authenticate
For human users:
anyt auth login
# Paste your JWT token when prompted
For AI agents:
anyt auth login --agent-key anyt_agent_xxxxxxxxxxxxx
3. Select Workspace
anyt workspace list
anyt workspace select DEV
4. Create Your First Task
anyt task create "Implement user authentication" --status todo --priority 1
Core Commands
Environment Management
anyt env add <name> <api-url> # Add new environment
anyt env list # List all environments
anyt env use <name> # Switch environment
anyt env remove <name> # Remove environment
Authentication
anyt auth login # Login with user token
anyt auth login --agent-key KEY # Login with agent API key
anyt auth whoami # Show current user info
anyt auth logout # Logout
Workspace Management
anyt workspace list # List workspaces
anyt workspace select <identifier> # Select workspace
anyt workspace create <name> # Create new workspace
Task Management
Create and update tasks:
anyt task create <title> # Create new task
--status <todo|inprogress|done>
--priority <1-5>
--assignee <user-id>
--project-id <id>
anyt task update <identifier> # Update task
--status <status>
--priority <priority>
--title <new-title>
anyt task delete <identifier> # Delete task
View tasks:
anyt task list # List all tasks
--status <status> # Filter by status
--priority <priority> # Filter by priority
--assignee <user-id> # Filter by assignee
anyt task get <identifier> # Get task details
anyt task board # View Kanban board
Task dependencies:
anyt task dep add <task> --blocks <other-task>
anyt task dep remove <task> --blocks <other-task>
anyt task dep list <task>
Active task tracking:
anyt task pick <identifier> # Pick task to work on
anyt task active # Show current task
anyt task drop # Drop current task
AI-Powered Commands
anyt ai decompose <goal> # Decompose goal into tasks
--project-id <id>
anyt ai suggest # Get task suggestions
--limit <number>
Worker System
Automated task execution using YAML workflows:
anyt worker start # Start worker daemon
anyt worker stop # Stop worker
anyt worker status # Check worker status
Create a workflow file in .anyt/workflows/:
name: Feature Development
on:
task_created:
labels: ["feature"]
jobs:
develop:
steps:
- uses: anyt/checkout@v1
- uses: anyt/claude-code@v1
with:
prompt: "Implement: ${{ task.description }}"
- run: make test
- uses: anyt/git-commit@v1
- uses: anyt/task-update@v1
with:
status: done
Usage Examples
Daily Workflow
# View your board
anyt task board
# Pick a task
anyt task pick DEV-42
# Update progress
anyt task update DEV-42 --status inprogress
# Complete the task
anyt task update DEV-42 --status done
anyt task drop
Team Collaboration
# List all tasks
anyt task list
# Filter by status
anyt task list --status inprogress
# View task details
anyt task get DEV-123
# Add dependencies
anyt task dep add DEV-124 --blocks DEV-123
AI-Assisted Development
# Get task recommendations
anyt ai suggest --limit 5
# Decompose a complex goal
anyt ai decompose "Build authentication system" --project-id 1
Claude Code Integration
AnyTask provides seamless integration with Claude Code through slash commands.
Quick Setup
- Install and configure AnyTask CLI
- Use slash commands in Claude Code:
/anyt-next- Get intelligent task recommendations/anyt-active- View your current task/anyt-create- Create new tasks interactively/anyt-board- See your Kanban board
Example
User: /anyt-next
Claude: "📋 Top Task Recommendations:
1. DEV-42: Implement OAuth callback (Score: 15.0)
• Priority: 2 (Urgent)
• All dependencies complete ✓
• Unblocks 2 other tasks
Which task would you like to work on?"
See Claude Code Integration Guide for details.
Configuration
Environment Configuration
Configuration is stored in ~/.config/anyt/config.json:
{
"environments": {
"prod": {
"api_url": "http://api.anyt.dev",
"auth_token": "your-token-here"
}
},
"current_environment": "prod"
}
Workspace Configuration
Workspace settings in .anyt/anyt.json:
{
"workspace_id": "1",
"name": "Development",
"api_url": "http://api.anyt.dev",
}
Documentation
User Guides
- CLI Usage Guide - Complete command reference
- CLI Complete Reference - Generated documentation
- Worker Quick Start - Automated task execution
- Claude Code Integration - AI-assisted development
Developer Documentation
For internal development, see DEVELOPER_GUIDE.md.
Environment Variables
Optional configuration via environment variables:
ANYT_ENV- Current environment (dev/staging/prod)ANYT_AUTH_TOKEN- Authentication tokenANYT_AGENT_KEY- Agent API keyANYT_CONFIG_DIR- Override config directory (default: ~/.config/anyt)
Support
For issues and questions, contact: contact@anytransformer.com
License
Proprietary - AnyTransformer Inc.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
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 anyt-0.2.0-py3-none-any.whl.
File metadata
- Download URL: anyt-0.2.0-py3-none-any.whl
- Upload date:
- Size: 315.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e6f91f9a6d338054f5e9ef43887e57f77962aedfc9be470cb1e6c406eaf7c85b
|
|
| MD5 |
a750a70cdbfeea53964bebe8ef8b112d
|
|
| BLAKE2b-256 |
f8858576c61cc6599f223086d9ec58fe10d9e9a0fd712bbc1c5bedfb5d5ba25b
|