memory-toolsAgent-controlled memory plugin for OpenClaw with confidence scoring, decay, and semantic search. The agent decides WHEN to store/retrieve memories — no auto-...
Install via ClawdBot CLI:
clawdbot install gianni-dalerta/memory-toolsGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAICalls external URL not in known-safe list
https://github.com/Purple-Horizons/openclaw-memory-toolsUses known external API (expected, informational)
arxiv.orgAI Analysis
The skill's external API usage (OpenAI for embeddings) is consistent with its stated purpose of semantic search and requires a user-provided API key. The GitHub reference is for documentation/installation, not runtime data exfiltration. No hidden instructions, credential harvesting, or obfuscation were found in the provided definition.
Generated Mar 21, 2026
An AI support agent uses memory tools to remember customer preferences, past issues, and specific instructions across interactions. It stores facts like product preferences and updates them as customers provide new information, ensuring consistent and tailored responses without manual context review.
A healthcare assistant AI stores patient preferences, medical history events, and treatment decisions. It retrieves critical instructions during consultations, avoids contradictions by updating records, and summarizes patient contexts for quick reviews by medical staff.
An AI project manager tracks team decisions, entity details like project names, and contextual information such as deadlines. It uses semantic search to find related memories during meetings and lists important instructions to ensure alignment without flooding chat logs.
A tutoring AI remembers student learning preferences, past lesson events, and key facts about subjects. It updates confidence scores as students progress, searches for relevant instructional memories, and summarizes topics to adapt teaching strategies dynamically.
An AI financial advisor stores client risk preferences, investment decisions, and temporal events like market changes. It uses importance scoring to prioritize critical advice, forgets outdated information, and lists instructions to comply with regulatory guidelines.
Offer the memory tools as a cloud-hosted API with tiered pricing based on usage volume and features like advanced search or decay settings. Revenue comes from monthly subscriptions, targeting businesses needing scalable, persistent memory for their AI agents without infrastructure management.
Sell on-premise licenses to large organizations in regulated industries like healthcare or finance, with added support for custom integrations and security compliance. Revenue includes one-time license fees and annual support contracts, ensuring high reliability and data control.
Distribute the skill for free via platforms like ClawHub, with premium features such as enhanced analytics or priority updates available for purchase. Revenue is generated through in-app purchases or donations, appealing to developers and small teams experimenting with AI memory.
💬 Integration Tip
Ensure the OPENAI_API_KEY is set for embeddings, and test the plugin with a gateway restart after installation to avoid connection issues.
Scored Jun 3, 2026
Audited Apr 18, 2026 · audit v1.0
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...