cass-memory

Transform scattered agent sessions into persistent cross-agent procedural memory.

2|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/build000r/skillbox --skill cass-memory-build000r
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cass-memory
Source: https://github.com/build000r/skillbox/tree/main/skills/cass-memory
Command: npx skills add https://github.com/build000r/skillbox --skill cass-memory-build000r

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transforms scattered agent sessions into a durable cross-agent procedural memory, enabling teams to learn from past work and avoid repeating mistakes.

Core Features & Use Cases

Core features include cross-agent memory, historical session integration, starter playbooks, and context hydration to guide future tasks across multiple agents and projects. Use cases include building resilient playbooks from prior sessions and reducing repetitive debugging by leveraging past learnings.

Quick Start

Initialize a starter memory graph with cm init, then seed your first task context using cm context.

Frequently Asked Questions about cass-memory

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

FAQPage Schema
How do I build persistent procedural memory from scattered agent sessions?

To build persistent procedural memory from scattered agent sessions, you can initialize a starter memory graph and seed task context to retain learnings and avoid repeating mistakes. This converts episodic memory into structured playbooks.

How does cross-session memory work for multi-agent workflows?

Cross-session memory for multi-agent workflows works by transforming historical sessions into durable procedural memory. This context hydration guides future tasks across multiple agents, reducing repetitive debugging by leveraging past learnings.

What is the best way to reduce repeated mistakes in long-running agent tasks?

The best way to reduce repeated mistakes in long-running agent tasks is to apply cross-agent procedural memory. Converting episodic memory into structured playbooks ensures future sessions learn from past work and avoid similar errors.

How do I create a starter playbook for proactive task planning?

To create a starter playbook for proactive task planning, initialize a memory graph and seed your first task context. This process hydrates the context needed to guide future sessions and build resilient playbooks from prior work.

Can I use cross-agent memory across different projects?

Yes, you can use cross-agent memory across different projects. The system integrates historical session data to build durable procedural memory, enabling teams to apply retained learnings and guide future tasks across multiple agents and projects.

When do I need context hydration for agent tasks?

You need context hydration for agent tasks when you want to proactively guide future sessions and reduce repetitive debugging. It converts episodic memory into structured playbooks, ensuring past learnings hydrate the context for upcoming work.