engramPersistent semantic memory layer for AI agents. Local-first storage (SQLite+LanceDB) with Ollama embeddings. Store and recall facts, decisions, preferences, events, relationships across sessions. Supports memory decay, deduplication, typed memories (5 types), memory relationships (7 graph relation types), agent/user scoping, semantic search, context-aware recall, auto-extraction from text (rules/LLM/hybrid), import/export, REST API, MCP protocol. Solves context window and compaction amnesia. Server at localhost:3400, dashboard at /dashboard. Install via npm (engram-memory), requires Ollama with nomic-embed-text model.
Install via ClawdBot CLI:
clawdbot install dannydvm/engramGrade 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:3400/api/memoriesPotentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
http://localhost:3400/api/memoriesAI Analysis
The skill interacts with a local server (localhost:3400) for its stated purpose of persistent memory storage, which is consistent with its design and does not constitute unauthorized external data exfiltration. The 'UNSAFE_SHELL' signal appears to be a misinterpretation of example setup commands, not actual skill execution. The primary risk is local data persistence, not external transmission.
Generated Mar 22, 2026
Track client interactions, preferences, and churn risks across sessions. Store facts like contract terms, decisions on support strategies, and events such as onboarding milestones. Use semantic search to quickly recall client history before meetings.
Maintain a persistent memory of technical decisions, codebase facts, and team preferences. Store events like deployment dates and relationships between team members. Recall context-aware memories to avoid re-discussing past decisions during sprint planning.
Securely store patient preferences, treatment decisions, and appointment events in a local-first setup. Use agent scoping to isolate memories per healthcare provider while allowing global access to critical facts. Semantic search helps retrieve patient history efficiently.
Document case facts, legal decisions, and client relationships across long-term engagements. Apply memory decay to prioritize recent developments while archiving older details. Auto-extract memories from legal documents to streamline data entry.
Store research findings, hypotheses, and literature references as typed memories. Use memory relationships to link supporting or contradictory evidence. Semantic search aids in recalling relevant studies during paper writing or team discussions.
Offer tiered subscriptions for teams, with features like advanced memory relationships, higher storage limits, and priority support. Target businesses needing persistent memory for customer-facing agents or internal knowledge bases.
Provide custom setup, training, and integration with existing AI agent workflows or MCP protocols. Help clients optimize memory types and decay settings for specific use cases like healthcare or legal.
Distribute the core tool as open source (e.g., via npm) to build a community. Monetize through premium extensions like cloud sync, advanced analytics dashboards, or specialized embedding models.
💬 Integration Tip
Start by integrating the boot sequence command into agent startup scripts to load relevant memories automatically, and use the REST API for seamless embedding into existing applications.
Scored Apr 19, 2026
Audited Apr 17, 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
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
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.