agent-tiered-memoryTwo-tier memory system for OpenClaw agents. Tier 0 = QMD semantic search for recent memories (7-14 days). Tier 1 = SQLite archive for long-term storage. Auto...
Install via ClawdBot CLI:
clawdbot install jpmoregain-eth/agent-tiered-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
Report → https://github.com/jpmoregain-eth/tiered-memory-skill/issuesCalls external URL not in known-safe list
https://ollama.com/downloadAudited Apr 17, 2026 · audit v1.0
Generated May 20, 2026
A customer support AI agent uses tiered memory to remember past interactions from the last 14 days in Tier 0 for rapid retrieval, while archival in Tier 1 stores older conversation summaries. This enables personalized support without losing context, reducing response time and improving satisfaction.
An AI assistant that helps users manage notes, tasks, and research across weeks uses Tier 0 for recent, frequently accessed information and Tier 1 for archived deep-dives. Users can query both tiers seamlessly, ensuring no knowledge is lost over time.
A healthcare AI agent maintains patient interaction logs (symptoms, prescriptions) for the last 14 days in Tier 0 for quick reference, and archives older sessions with summaries in Tier 1. This supports continuity of care and efficient data management.
An e-commerce AI remembers user browsing and purchase history from the recent period via Tier 0, while Tier 1 archives past seasonal trends and long-term preferences. It provides accurate recommendations and personalized marketing.
A legal AI agent uses tiered memory to keep recent case documents and notes in Tier 0 for quick semantic search, with Tier 1 storing summarized archives of older cases. This helps lawyers quickly find relevant precedents and track case evolution.
Offer tiered memory as a feature in a subscription-based AI assistant platform, with pricing tiers based on memory duration and archival capacity. Revenue comes from monthly or annual subscriptions from businesses needing persistent memory.
Provide consulting and development services to build custom tiered-memory agents for enterprise clients in specific industries. Revenue includes project fees and ongoing maintenance contracts.
Release the tiered-memory skill as open-source, generating revenue through premium support, custom integration services, and training for teams. Attracts users while monetizing expertise.
💬 Integration Tip
Ensure QMD is enabled in your OpenClaw config and test with a dry-run before setting up the cron job. The skill requires Python 3 and optionally Ollama for LLM summarization.
Scored May 20, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...