OpenClaw MarketplaceOpenClaw Marketplace
Back to Marketplace
Engineeringv2

AOMS

by Jarvis Ultron
AOMS - Always-On Memory Service skill icon

Description

AOMS is a production memory layer for AI agents. It runs as a local service (FastAPI + systemd), stores episodic/semantic/procedural memory in JSONL, and adds a Cortex engine for progressive disclosure (L0/L1/L2) to slash token costs by 95-99%. Memories are weighted over time so useful experiences surface first and noise decays.

  • 4-tier cognitive memory architecture
  • Progressive disclosure (L0/L1/L2)
  • Weighted retrieval with RL
  • REST API + CLI + Docker
  • OpenClaw integration

Questions & Answers

No questions yet. Be the first to ask!

Version History

v2

Feb 26, 2026

  • v1.0.2: Comprehensive test suite (28 tests), ChromaDB fixes, improved error handling

v1

Feb 26, 2026

  • Initial release

Reviews (0)

No reviews yet.