jmiaie

Ompa — AI skill for Claude Code

AI community

Universal AI agent memory layer — vault + palace + temporal knowledge graph.

How to install Ompa

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

What Ompa does

Universal AI agent memory layer — vault + palace + temporal knowledge graph.

Alternatives in AI

Wiki Graph — Build the LLM Wiki knowledge graph 2.3k ★
Memtrace Public — Structural memory for AI coding agents 466 ★
Mnem — Git for AI Agent Knowledge 144 ★

README

OMPA

Universal AI Agent Memory Layer

Vault · Palace · Temporal Knowledge Graph

**Obsidian-MemPalace-Agnostic** — Give any AI agent persistent memory in one `pip install`. Works with Claude Code, OpenClaw, Codex, Gemini CLI, LangChain, or any custom agent.

pip install ompa
ao init && ao session-start

**96.6% R@5 on LongMemEval** using verbatim storage — no summarization loss, no API cost for search.

Why OMPA?

Every AI agent starts empty every session. Important decisions get lost. Context grows expensive. Summaries lose nuance.

OMPA solves all three:

Problem	OMPA's Answer
Lost decisions	Vault — every significant event persisted as markdown
Expensive context	5 lifecycle hooks with token budgets (~2K at start, ~100 per message)
Summarization loss	Verbatim storage — proven 96.6% R@5 on LongMemEval
Framework lock-in	Works with any Python agen