engrammemoryPersistent semantic memory for AI agents. Store, search, recall, and forget memories across sessions using Qdrant + FastEmbed.
Install via ClawdBot CLI:
clawdbot install escapethefate1991/engrammemoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:11435/embeddingsCalls external URL not in known-safe list
http://localhost:6333AI Analysis
The skill uses local endpoints (localhost:11435 for embeddings and localhost:6333 for Qdrant) which are part of its documented architecture for semantic memory storage. These are consistent with the skill's stated purpose of persistent memory using Qdrant + FastEmbed. No evidence of credential harvesting, hidden instructions, or data exfiltration to unauthorized external servers.
Audited Apr 17, 2026 · audit v1.0
Generated May 11, 2026
A customer support AI remembers each user's past issues, preferences, and resolutions to provide faster, context-aware assistance. It eliminates the need for customers to repeat themselves, improving satisfaction and reducing handle time.
Developers use an AI agent that remembers project decisions, architecture patterns, and API endpoints across sessions. It answers questions like 'How did we implement authentication?' without re-querying the entire codebase.
An educational AI tutor retains a student's learning style, progress, and weak areas over time. It recommends customized study materials and recalls past lessons to build on previous knowledge.
A virtual health assistant remembers patient medical history, medication schedules, and doctor's advice across sessions. It provides personalized reminders and answers based on stored facts and preferences.
A legal AI keeps track of case precedents, client preferences, and document versions over multiple interactions. It helps lawyers quickly find relevant past cases and clauses without manual searching.
Offer the Engram Memory skill as part of a broader AI skill marketplace. Basic memory capacity is free, while advanced features (e.g., large vector storage, multi-project context) are subscription-based.
License the skill to enterprises for deployment inside their own infrastructure. Provide dedicated Qdrant instances, priority support, and compliance certifications.
Integrate Engram into existing SaaS platforms (e.g., CRM, project management tools) as an add-on feature. Charge per memory operation or storage volume.
💬 Integration Tip
Start with the quick start and use the provided setup script to deploy Qdrant and FastEmbed via Docker. Then add the engram plugin configuration to your openclaw.json.
Scored Jun 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...