kb-memory

Captures facts, decisions, corrections and pitfalls in a persistent append-only ledger for recall and validation.

Updated May 30, 2026
One-click install
npx skills add https://github.com/InnerScopeHearing/otchealth-claude-tools --skill kb-memory-innerscopehearing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kb-memory
Source: https://github.com/InnerScopeHearing/otchealth-claude-tools/tree/main/skills/kb-memory
Command: npx skills add https://github.com/InnerScopeHearing/otchealth-claude-tools --skill kb-memory-innerscopehearing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a durable, append-only working memory for agents, enabling persistent context capture and recall for improved AI decision-making and collaboration.

Core Features & Use Cases

  • Persistent Context Capture: Capture and store facts, decisions, corrections, and pitfalls into a persistent ledger.
  • Ledger-based Recall: Retrieve stored information directly from the ledger for accurate recall and validation.
  • Shared Team Memory: Enable agents to share relevant information with the team and access a collective knowledge base.
  • Use Case: Consider an executive team working on a project. This Skill can help them keep track of all the decisions, changes, and lessons learned throughout the project's lifecycle, ensuring that all team members have access to the same information.

Quick Start

Run the command 'kb-memory use <role>' to claim your identity for the working memory ledger.

Frequently Asked Questions about kb-memory

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

FAQPage Schema
How do I maintain persistent working memory for AI agents across sessions?

You can maintain persistent working memory by using an append-only ledger that captures facts, decisions, and corrections. This ensures accurate recall and validation of information for AI agents across different sessions.

What is the best way to enable team collaboration on shared AI knowledge management?

The best way to enable team collaboration is through a shared memory ledger. This allows agents and team members to access a collective knowledge base and share relevant project information directly.

How do I capture project decisions and lessons learned for executive-level knowledge management?

You capture project decisions by logging facts, corrections, and pitfalls into a durable, append-only ledger. This provides a persistent record for executive teams to track changes and validate information throughout the project lifecycle.

Can I correct or delete inaccurate facts in a persistent context ledger?

You cannot delete entries because the ledger is strictly append-only. However, you can capture corrections and pitfalls as new entries to ensure accurate recall and maintain a valid history of changes.

How do I set up a working memory ledger for my role?

You set up the working memory ledger by running the command 'kb-memory use <role>'. This claims your identity and initializes the persistent context capture environment for your agent.

Does this knowledge management approach require external dependencies to store context?

No external dependencies are required to store context. The skill operates independently using its internal scripts and references to manage the append-only ledger and validate recalled information.