beads

Persist task memory across AI agent sessions using a graph-based database.

16|1|Updated Jan 2, 2026

Search Tags:#beads #bd #compaction #dependency-graph #task-memory

One-click install

npx skills add https://github.com/michalvavra/agents --skill beads-michalvavra

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: beads
Source: https://github.com/michalvavra/agents/tree/main/skills/beads
Command: npx skills add https://github.com/michalvavra/agents --skill beads-michalvavra

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Beads provides persistent task memory for AI agents by using a graph-based memory that survives conversation compaction and multi-session work.

Core Features & Use Cases

Graph-based memory: Track tasks, context, and decisions with dependencies.
Session continuity: Keeps progress across sessions and tool restarts.
Deterministic workflow & Git sync: Syncs with Git and uses explicit notes to preserve context.

Quick Start

Install the bd CLI, initialize the beads database with bd init in your project, create a task with bd create, start work with bd update --status in_progress, and add progress notes via bd update --notes "..." to survive compaction.