e4fba408f3
Add lightweight example script for converting markdown planning docs to bd JSONL format. This addresses #9 without adding complexity to bd core. Features: - YAML frontmatter parsing (priority, type, assignee) - Headings converted to issues - Task lists extracted as sub-issues - Dependency parsing (blocks: bd-10, etc.) - Fully customizable by users This demonstrates the "lightweight extension pattern" - keeping bd core minimal while providing examples users can adapt for their needs. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Beads Examples
This directory contains examples of how to integrate bd with AI agents and workflows.
Examples
- python-agent/ - Simple Python agent that discovers ready work and completes tasks
- bash-agent/ - Bash script showing the full agent workflow
- markdown-to-jsonl/ - Convert markdown planning docs to bd issues
- git-hooks/ - Pre-configured git hooks for automatic export/import
- branch-merge/ - Branch merge workflow with collision resolution
- claude-desktop-mcp/ - MCP server for Claude Desktop integration
Quick Start
# Try the Python agent example
cd python-agent
python agent.py
# Try the bash agent example
cd bash-agent
./agent.sh
# Install git hooks
cd git-hooks
./install.sh
# Try branch merge collision resolution
cd branch-merge
./demo.sh
Creating Your Own Agent
The basic agent workflow:
- Find ready work:
bd ready --json --limit 1 - Claim the task:
bd update <id> --status in_progress --json - Do the work: Execute the task
- Discover new issues:
bd create "Found bug" --json - Link discoveries:
bd dep add <new-id> <parent-id> --type discovered-from - Complete the task:
bd close <id> --reason "Done" --json
All commands support --json for easy parsing.