# 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
### Core Capabilities
- **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
### CLI Commands
- **Environment Management**: `anyt env` - Configure and switch between environments
- **Authentication**: `anyt auth login` - Authenticate with user tokens or agent API keys
- **Workspace Management**: `anyt workspace` - List, select, and manage workspaces
- **Task CRUD**: `anyt task create/get/update/delete` - Full task lifecycle management
- **Task Views**: `anyt task list/board` - View tasks in lists or Kanban boards
- **Dependencies**: `anyt task dep` - Manage task dependencies
- **Active Task**: `anyt task pick/drop` - Track current task in progress
- **AI Commands**: `anyt ai decompose` - AI-powered task decomposition
- **MCP Server**: `anyt mcp start` - Run MCP server for Claude Code integration
## Quick Start
### Prerequisites
- **Python 3.12+** with uv installed
- **AnyTask Backend Server** (API endpoint)
- **Authentication**: User token (JWT) or Agent API key
### Installation
#### Option 1: Install from PyPI (Coming Soon)
```bash
pip install anyt
```
#### Option 2: Install from Source
```bash
git clone <repository-url>
cd AnyTaskCLI
make install
```
### Initial Setup
1. **Configure environment**
The CLI comes pre-configured with a production environment. To use a local development server instead:
```bash
anyt env add dev http://localhost:8000
anyt env use dev
```
To verify your current environment:
```bash
anyt env list
```
2. **Authenticate**
For human users:
```bash
anyt auth login
# Paste your JWT token when prompted
```
For AI agents:
```bash
anyt auth login --agent-key anyt_agent_xxxxxxxxxxxxx
```
3. **Select workspace**
```bash
anyt workspace list
anyt workspace select DEV
```
4. **Create your first task**
```bash
anyt task create "Implement user authentication" --status todo --priority 1
```
## Usage Examples
### View Tasks
```bash
# List all tasks
anyt task list
# Filter by status
anyt task list --status inprogress
# View as Kanban board
anyt task board
# Get task details
anyt task get DEV-123
```
### Manage Tasks
```bash
# Create task
anyt task create "Add API endpoint" --status todo --priority 2
# Update task
anyt task update DEV-123 --status inprogress
# Add dependency
anyt task dep add DEV-124 --blocks DEV-123
# Delete task
anyt task delete DEV-123
```
### Active Task Workflow
```bash
# Pick a task to work on
anyt task pick DEV-123
# View current active task
anyt task active
# Mark as done and drop
anyt task update DEV-123 --status done
anyt task drop
```
### AI-Powered Commands
```bash
# Decompose a goal into tasks
anyt ai decompose "Implement user authentication system" --project-id 1
```
### MCP Server for Claude Code
```bash
# Start MCP server
anyt mcp start
# Use with Claude Code by adding to claude_desktop_config.json:
# {
# "mcpServers": {
# "anytask": {
# "command": "anyt",
# "args": ["mcp", "start"]
# }
# }
# }
```
## Claude Code Integration
AnyTask provides seamless integration with Claude Code through slash commands, enabling AI-assisted task management directly in your development environment.
### Quick Setup
1. **Install and configure AnyTask CLI** (see Quick Start above)
2. **Start using 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 Workflow
```
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?"
User: "Let's do DEV-42"
Claude: "Great! Now working on DEV-42. Let me help you implement it..."
```
### Features
- **Smart Task Selection**: AI analyzes priority, dependencies, and impact to recommend the best task
- **Interactive Task Creation**: Claude guides you through creating well-structured tasks
- **Progress Tracking**: View active tasks and board status without leaving your editor
- **Context-Aware Help**: Claude understands your current task and offers relevant assistance
### Learn More
See **[Claude Code Integration Guide](docs/CLAUDE_CODE_INTEGRATION.md)** for:
- Complete setup instructions
- All available slash commands
- Workflow examples and best practices
- Troubleshooting tips
**Two Integration Options:**
1. **CLI-based** (recommended for getting started) - Simple slash commands, no extra setup
2. **MCP Integration** (advanced) - Full Model Context Protocol integration with real-time updates
## Configuration
### Environment Configuration
Configuration is stored in `~/.config/anyt/config.json`:
```json
{
"environments": {
"prod": {
"api_url": "http://anyt.up.railway.app",
"auth_token": "your-token-here",
"default_workspace": 1
},
"dev": {
"api_url": "http://localhost:8000",
"auth_token": "your-dev-token-here",
"default_workspace": 1
}
},
"current_environment": "prod"
}
```
### Workspace Configuration
Workspace settings are stored in `.anyt/anyt.json`:
```json
{
"workspace_id": "1",
"name": "Development",
"api_url": "http://localhost:8000",
"last_sync": "2025-10-18T10:00:00Z"
}
```
## Development
### Setup Development Environment
```bash
# Clone repository
git clone <repository-url>
cd AnyTaskCLI
# Install dependencies
make install
# Run tests
make test
# Run type checking
make typecheck
# Format code
make format
# Lint code
make lint
```
### Project Structure
```
src/
├── cli/ # CLI application
│ ├── main.py # Entry point
│ ├── client.py # API client
│ ├── config.py # Configuration management
│ └── commands/ # Command modules
│ ├── env.py
│ ├── auth.py
│ ├── workspace.py
│ ├── task.py
│ ├── ai.py
│ └── mcp.py
└── anytask_mcp/ # MCP server
├── server.py
├── tools.py
└── resources.py
tests/
└── cli/
├── unit/ # Unit tests
└── integration/ # Integration tests
```
### Running Tests
```bash
# Run all tests
make test
# Run only unit tests
make test-cli-unit
# Run integration tests (requires server)
make test-cli-integration
```
## Documentation
- **[CLI Usage Guide](docs/CLI_USAGE.md)** - Comprehensive CLI command reference
- **[Claude Code Integration](docs/CLAUDE_CODE_INTEGRATION.md)** - Using AnyTask with Claude Code slash commands
- **[MCP Integration](docs/MCP_INTEGRATION.md)** - Advanced Model Context Protocol integration
- **[Development Guide](CLAUDE.md)** - Developer guidelines and architecture
## License
Proprietary - AnyTransformer Inc.
## Support
For issues and feature requests, please contact: contact@anytransformer.com
Raw data
{
"_id": null,
"home_page": null,
"name": "anyt",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": "AnyTransformer Inc <contact@anytransformer.com>",
"keywords": "ai, cli, developer-tools, productivity, task-management",
"author": null,
"author_email": "AnyTransformer Inc <contact@anytransformer.com>",
"download_url": null,
"platform": null,
"description": "# AnyTask CLI\n\n> AI-native task management CLI for coding agents and human developers\n\nAnyTask 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.\n\n## Features\n\n### Core Capabilities\n\n- **Linear-style Task Management**: Human-readable task IDs (DEV-123), status workflows, priorities, and dependencies\n- **Multi-Environment Support**: Manage tasks across dev, staging, and production environments\n- **Workspace & Project Organization**: Isolated workspaces with role-based access\n- **Rich Terminal UI**: Beautiful, color-coded task boards and visualizations\n- **Agent Integration**: Native support for AI agents via API keys and MCP server\n\n### CLI Commands\n\n- **Environment Management**: `anyt env` - Configure and switch between environments\n- **Authentication**: `anyt auth login` - Authenticate with user tokens or agent API keys\n- **Workspace Management**: `anyt workspace` - List, select, and manage workspaces\n- **Task CRUD**: `anyt task create/get/update/delete` - Full task lifecycle management\n- **Task Views**: `anyt task list/board` - View tasks in lists or Kanban boards\n- **Dependencies**: `anyt task dep` - Manage task dependencies\n- **Active Task**: `anyt task pick/drop` - Track current task in progress\n- **AI Commands**: `anyt ai decompose` - AI-powered task decomposition\n- **MCP Server**: `anyt mcp start` - Run MCP server for Claude Code integration\n\n## Quick Start\n\n### Prerequisites\n\n- **Python 3.12+** with uv installed\n- **AnyTask Backend Server** (API endpoint)\n- **Authentication**: User token (JWT) or Agent API key\n\n### Installation\n\n#### Option 1: Install from PyPI (Coming Soon)\n\n```bash\npip install anyt\n```\n\n#### Option 2: Install from Source\n\n```bash\ngit clone <repository-url>\ncd AnyTaskCLI\nmake install\n```\n\n### Initial Setup\n\n1. **Configure environment**\n\n The CLI comes pre-configured with a production environment. To use a local development server instead:\n\n ```bash\n anyt env add dev http://localhost:8000\n anyt env use dev\n ```\n\n To verify your current environment:\n\n ```bash\n anyt env list\n ```\n\n2. **Authenticate**\n\n For human users:\n\n ```bash\n anyt auth login\n # Paste your JWT token when prompted\n ```\n\n For AI agents:\n\n ```bash\n anyt auth login --agent-key anyt_agent_xxxxxxxxxxxxx\n ```\n\n3. **Select workspace**\n\n ```bash\n anyt workspace list\n anyt workspace select DEV\n ```\n\n4. **Create your first task**\n ```bash\n anyt task create \"Implement user authentication\" --status todo --priority 1\n ```\n\n## Usage Examples\n\n### View Tasks\n\n```bash\n# List all tasks\nanyt task list\n\n# Filter by status\nanyt task list --status inprogress\n\n# View as Kanban board\nanyt task board\n\n# Get task details\nanyt task get DEV-123\n```\n\n### Manage Tasks\n\n```bash\n# Create task\nanyt task create \"Add API endpoint\" --status todo --priority 2\n\n# Update task\nanyt task update DEV-123 --status inprogress\n\n# Add dependency\nanyt task dep add DEV-124 --blocks DEV-123\n\n# Delete task\nanyt task delete DEV-123\n```\n\n### Active Task Workflow\n\n```bash\n# Pick a task to work on\nanyt task pick DEV-123\n\n# View current active task\nanyt task active\n\n# Mark as done and drop\nanyt task update DEV-123 --status done\nanyt task drop\n```\n\n### AI-Powered Commands\n\n```bash\n# Decompose a goal into tasks\nanyt ai decompose \"Implement user authentication system\" --project-id 1\n```\n\n### MCP Server for Claude Code\n\n```bash\n# Start MCP server\nanyt mcp start\n\n# Use with Claude Code by adding to claude_desktop_config.json:\n# {\n# \"mcpServers\": {\n# \"anytask\": {\n# \"command\": \"anyt\",\n# \"args\": [\"mcp\", \"start\"]\n# }\n# }\n# }\n```\n\n## Claude Code Integration\n\nAnyTask provides seamless integration with Claude Code through slash commands, enabling AI-assisted task management directly in your development environment.\n\n### Quick Setup\n\n1. **Install and configure AnyTask CLI** (see Quick Start above)\n2. **Start using slash commands** in Claude Code:\n - `/anyt-next` - Get intelligent task recommendations\n - `/anyt-active` - View your current task\n - `/anyt-create` - Create new tasks interactively\n - `/anyt-board` - See your Kanban board\n\n### Example Workflow\n\n```\nUser: /anyt-next\n\nClaude: \"\ud83d\udccb Top Task Recommendations:\n\n1. DEV-42: Implement OAuth callback (Score: 15.0)\n \u2022 Priority: 2 (Urgent)\n \u2022 All dependencies complete \u2713\n \u2022 Unblocks 2 other tasks\n\nWhich task would you like to work on?\"\n\nUser: \"Let's do DEV-42\"\n\nClaude: \"Great! Now working on DEV-42. Let me help you implement it...\"\n```\n\n### Features\n\n- **Smart Task Selection**: AI analyzes priority, dependencies, and impact to recommend the best task\n- **Interactive Task Creation**: Claude guides you through creating well-structured tasks\n- **Progress Tracking**: View active tasks and board status without leaving your editor\n- **Context-Aware Help**: Claude understands your current task and offers relevant assistance\n\n### Learn More\n\nSee **[Claude Code Integration Guide](docs/CLAUDE_CODE_INTEGRATION.md)** for:\n- Complete setup instructions\n- All available slash commands\n- Workflow examples and best practices\n- Troubleshooting tips\n\n**Two Integration Options:**\n1. **CLI-based** (recommended for getting started) - Simple slash commands, no extra setup\n2. **MCP Integration** (advanced) - Full Model Context Protocol integration with real-time updates\n\n## Configuration\n\n### Environment Configuration\n\nConfiguration is stored in `~/.config/anyt/config.json`:\n\n```json\n{\n \"environments\": {\n \"prod\": {\n \"api_url\": \"http://anyt.up.railway.app\",\n \"auth_token\": \"your-token-here\",\n \"default_workspace\": 1\n },\n \"dev\": {\n \"api_url\": \"http://localhost:8000\",\n \"auth_token\": \"your-dev-token-here\",\n \"default_workspace\": 1\n }\n },\n \"current_environment\": \"prod\"\n}\n```\n\n### Workspace Configuration\n\nWorkspace settings are stored in `.anyt/anyt.json`:\n\n```json\n{\n \"workspace_id\": \"1\",\n \"name\": \"Development\",\n \"api_url\": \"http://localhost:8000\",\n \"last_sync\": \"2025-10-18T10:00:00Z\"\n}\n```\n\n## Development\n\n### Setup Development Environment\n\n```bash\n# Clone repository\ngit clone <repository-url>\ncd AnyTaskCLI\n\n# Install dependencies\nmake install\n\n# Run tests\nmake test\n\n# Run type checking\nmake typecheck\n\n# Format code\nmake format\n\n# Lint code\nmake lint\n```\n\n### Project Structure\n\n```\nsrc/\n\u251c\u2500\u2500 cli/ # CLI application\n\u2502 \u251c\u2500\u2500 main.py # Entry point\n\u2502 \u251c\u2500\u2500 client.py # API client\n\u2502 \u251c\u2500\u2500 config.py # Configuration management\n\u2502 \u2514\u2500\u2500 commands/ # Command modules\n\u2502 \u251c\u2500\u2500 env.py\n\u2502 \u251c\u2500\u2500 auth.py\n\u2502 \u251c\u2500\u2500 workspace.py\n\u2502 \u251c\u2500\u2500 task.py\n\u2502 \u251c\u2500\u2500 ai.py\n\u2502 \u2514\u2500\u2500 mcp.py\n\u2514\u2500\u2500 anytask_mcp/ # MCP server\n \u251c\u2500\u2500 server.py\n \u251c\u2500\u2500 tools.py\n \u2514\u2500\u2500 resources.py\n\ntests/\n\u2514\u2500\u2500 cli/\n \u251c\u2500\u2500 unit/ # Unit tests\n \u2514\u2500\u2500 integration/ # Integration tests\n```\n\n### Running Tests\n\n```bash\n# Run all tests\nmake test\n\n# Run only unit tests\nmake test-cli-unit\n\n# Run integration tests (requires server)\nmake test-cli-integration\n```\n\n## Documentation\n\n- **[CLI Usage Guide](docs/CLI_USAGE.md)** - Comprehensive CLI command reference\n- **[Claude Code Integration](docs/CLAUDE_CODE_INTEGRATION.md)** - Using AnyTask with Claude Code slash commands\n- **[MCP Integration](docs/MCP_INTEGRATION.md)** - Advanced Model Context Protocol integration\n- **[Development Guide](CLAUDE.md)** - Developer guidelines and architecture\n\n## License\n\nProprietary - AnyTransformer Inc.\n\n## Support\n\nFor issues and feature requests, please contact: contact@anytransformer.com\n",
"bugtrack_url": null,
"license": "Proprietary",
"summary": "AI-native task management CLI for coding agents and human developers",
"version": "0.1.3",
"project_urls": {
"Documentation": "https://anyt.dev/docs/cli",
"Homepage": "https://anyt.dev",
"Support": "https://anyt.dev/support"
},
"split_keywords": [
"ai",
" cli",
" developer-tools",
" productivity",
" task-management"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "480c38ff900dba5f448e74b3c69dec7adae14de540aed688c9cfc98f727f35b9",
"md5": "c10d34f4bd643949de694dd547d1b847",
"sha256": "5f45af29238bbd933e1b0e92ea904e0932b93442f565f4b5df0093e74a3af5e2"
},
"downloads": -1,
"filename": "anyt-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c10d34f4bd643949de694dd547d1b847",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 109507,
"upload_time": "2025-10-21T07:26:36",
"upload_time_iso_8601": "2025-10-21T07:26:36.582387Z",
"url": "https://files.pythonhosted.org/packages/48/0c/38ff900dba5f448e74b3c69dec7adae14de540aed688c9cfc98f727f35b9/anyt-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-21 07:26:36",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "anyt"
}
JSON