# Aexagon

> Open-source publisher. Listings imported from github.com/Aexagon — credited to the original author with their license.

- **Listings:** 3
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/aexagon
- **Website:** https://github.com/Aexagon

## Published listings

- [Mneme Wiki](https://agentstack.voostack.com/l/skill-aexagon-mneme-mneme-wiki) — Skill · Free · security-reviewed — `agentstack add skill-aexagon-mneme-mneme-wiki`
  The Mneme knowledge tier (Tier 2) — a per-corpus wiki built from documents, read on demand and never injected into a chat. Use when ingesting a source into a wiki, querying a wiki, or auditing one. Distinct from the lean cache (Tier 1).
- [New Skill](https://agentstack.voostack.com/l/skill-aexagon-mneme-new-skill) — Skill · Free · security-reviewed — `agentstack add skill-aexagon-mneme-new-skill`
  Scaffold a new skill for the Mneme bay (or for personal use) with skill-creator, then wire it to read/write the Mneme cache. Use when the user wants to add a skill to Mneme, build a new capability for the engine, or create a skill that learns into the cache.
- [Mneme Engine](https://agentstack.voostack.com/l/skill-aexagon-mneme-mneme-engine) — Skill · Free · security-reviewed — `agentstack add skill-aexagon-mneme-mneme-engine`
  The Mneme self-improving cache protocol — how to read the cache, when to save a learning (the relevance gate), the note schema, the lean-index and dedupe rules, and how skills read/write the cache. Use when capturing a learning to Mneme, writing a cache note by hand, pruning the cache, or building a skill that reads or writes Mneme.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.
