beads

Stores issues and dependencies in a git-backed store for persistent cross-session memory.

5|Updated Dec 9, 2025
One-click install
npx skills add https://github.com/arisng/github-copilot-fc --skill beads-arisng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: beads
Source: https://github.com/arisng/github-copilot-fc/tree/main/skills/beads
Command: npx skills add https://github.com/arisng/github-copilot-fc --skill beads-arisng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Beads provides a persistent memory layer for multi-session work by capturing issues, notes, and dependencies in a git-backed bead store, ensuring context survives compaction and session gaps.

Core Features & Use Cases

  • Persistent, cross-session memory: Track work that spans days or weeks with full history and context.
  • Dependency graph awareness: Model blockers, related work, epic/subtasks, and discoveries to guide execution order.
  • Session handoff & compaction resilience: Read notes to resume work after interruptions and rebuild context from bead notes.

Quick Start

Quick Start: Create a beads issue for a multi-session task, then resume across sessions by checking the notes field and continuing work with the standard workflow commands.

Frequently Asked Questions about beads

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I preserve context across coding sessions when the previous session is compacted?

To preserve context across sessions, you can use a persistent memory layer that captures issues and dependencies in a git-backed store. This ensures your work context survives compaction events and session gaps.

What is the best way to track complex task dependencies over multiple work sessions?

The best way to track complex task dependencies is by using a dependency graph that models blockers, related work, and subtasks. This approach guides execution order and maintains context across multi-session workflows.

Do I need external infrastructure or databases to maintain persistent memory for AI agents?

No external infrastructure is required to maintain persistent memory. The system uses a git-backed store, operating entirely within your existing workspace without needing additional databases or servers.

How do I resume an interrupted software engineering task and rebuild lost context?

To resume an interrupted task and rebuild context, read the notes field stored in the persistent memory layer. This allows you to pick up exactly where the previous session left off.

Can I manage multi-session work with full history tracking using a standard git repository?

Yes, you can manage multi-session work with full history by using a git-backed bead store. It tracks work spanning days or weeks, ensuring durable context and clear dependency tracking.