jean-claude 0.2.0

Jean Claude CLI - AI-powered development workflows for any codebase

Jean Claude CLI

Universal AI Developer Workflows - Transform any project into an AI-driven development environment

Jean Claude (jc) is a CLI tool that enables programmatic AI agent orchestration for any codebase. Execute prompts, run multi-phase workflows, and monitor agent activity with a unified interface.

Features

• Universal CLI: Single jc command for all operations
• Real-Time Streaming: Watch agent output as it works with --stream mode
• SDK-Based Execution: Claude Agent SDK with Bedrock authentication
• Workflow Composition: Multi-phase SDLC workflows (plan -> implement -> test -> review)
• Git Worktree Isolation: Safe parallel development without conflicts
• Real-Time Telemetry: SQLite event store with live monitoring UI
• Beads Integration: Local SQLite-based issue tracking for offline development

Installation

# Install with uv
uv pip install jean-claude

# Or install globally with uvx
uvx install jean-claude

# Verify installation
jc --version

Quick Start

# Initialize ADW in your project
cd my-project/
jc init

# Run an adhoc prompt
jc prompt "Analyze the codebase structure"

# Run a chore workflow
jc run chore "Add error handling to login"

# Monitor workflow events in real-time
jc watch

Commands

Core Commands

jc init                              # Initialize ADW in current project
jc prompt "your prompt here"         # Execute adhoc prompt
jc prompt "your prompt" --stream     # Stream output in real-time
jc run chore "task description"      # Run chore workflow
jc run feature "feature description" # Run feature workflow
jc watch                             # Real-time monitoring UI

State & Monitoring

jc ps                                # List running workflows
jc state list                        # List all workflow states
jc state show <workflow_id>          # Show workflow details
jc stop <workflow_id>                # Stop running workflow

Streaming Output

Real-time streaming displays output as the agent works:

# Stream output in real-time
jc prompt "Analyze the codebase" --stream

# Show tool uses and thinking process
jc prompt "Refactor authentication" --stream --show-thinking

# Different models with streaming
jc prompt "Quick question" --stream -m haiku
jc prompt "Complex analysis" --stream -m opus

Benefits of streaming:

• See progress in real-time as the agent works
• Better user experience for long-running prompts
• Optional visibility into tool uses and thinking process
• Graceful interrupt handling (Ctrl+C)

Cleanup

jc clean --older-than 7d             # Remove old worktrees
jc clean --zombies                   # Mark dead processes
jc clean --dry-run                   # Preview without deleting

Configuration

jc config show                       # Display current config
jc config set-api-key <key>          # Save Anthropic API key
jc config use-bedrock --profile dev  # Configure AWS Bedrock

Configuration

ADW uses .jc-project.yaml for project-specific configuration:

directories:
  specs: specs/
  agents: agents/
  trees: trees/
  source: src/
  tests: tests/

tooling:
  test_command: uv run pytest
  linter_command: uv run ruff check .

workflows:
  default_model: sonnet
  auto_commit: true

Architecture

project/
├── agents/              # Agent working directories
│   └── {workflow_id}/
│       └── state.json   # Workflow state
├── trees/               # Git worktrees (isolated execution)
├── specs/               # Workflow specifications
├── .jc/                 # Internal state
│   └── events.db        # SQLite telemetry
└── .jc-project.yaml     # Project configuration

Authentication

Anthropic API

export ANTHROPIC_API_KEY="your-api-key"
# Or save to config
jc config set-api-key "your-api-key"

AWS Bedrock

export CLAUDE_CODE_USE_BEDROCK=1
export AWS_PROFILE="your-profile"
# Or save to config
jc config use-bedrock --profile your-profile --region us-west-2

Development

# Clone and install
git clone https://github.com/joshuaoliphant/jean-claude
cd jean-claude
uv sync

# Run tests
uv run pytest

# Run CLI in development
uv run jc --help

License

MIT