rockdawayne-ship-it

Akm — AI skill for Claude Code

AI community

AKM — universal Agent Knowledge Management.

How to install Akm

This entry records only its repository, not the path inside it, so there is no exact command to give. Open rockdawayne-ship-it/akm and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Akm does

AKM — universal Agent Knowledge Management. A tool-agnostic Markdown knowledge OS for AI agents: memory / brain / vault over seven layers, with a Learn Back loop. Works with Claude Code, Codex, OpenClaw, and any agent.

Alternatives in AI

README

AKM — Agent Knowledge Management

A universal, tool-agnostic knowledge system for AI agents. Plain Markdown, no database or server required. Works with **Claude Code**, **Codex**, **OpenClaw**, and any agent that can read files; optional zero-dependency scripts provide linting, operational enforcement, and export.

An LLM wiki gives an agent a *map* of knowledge. AKM gives it an *operating system* for knowledge: what to learn, where to store it, how to act on it, how to verify results, and where failures go so the next run is better.

Why

Agents forget. Plain RAG re-interprets the same documents every session, good syntheses evaporate when the session ends, and the same mistakes repeat. Compiled Markdown wikis (e.g. Karpathy's LLM Wiki pattern) fix the *knowledge* half — but knowing is not operating. AKM keeps the wiki pattern as its knowledge layer and adds operational memory, context, procedures, selective action logging, and an evaluation loop, so agents don't just know more — they work better over time.

The core idea is **separation of stores**. Long external knowledge, short operating rules, repeatable procedures, execution records, and verification criteria each fail differently when mixed. AKM stores them apart and reconnects them with wikilinks and frontmatter.

The seven layers

# Layer Folder One-line rule
1 Source 10-sources/ Originals, never modified. Provenance tracked
2 Knowledge 20-knowledge/ Compiled, reusable knowledge — true for anyone
3 Context 30-context/ True only for this user / org / project / domain
4 Operational Memory 40-memory/ Short, stable pointers the agent must know every session
5 Procedural 50-procedures/ How to execute — skills, workflows, checklists
6 Action 60-actions/ Selected execution records — only what's needed for reproduction, verification, handoff
7 Evaluation 70-evaluation/ Failure