openclaw-memory-coreCore utilities for OpenClaw memory plugins (redaction, local store, embeddings).
Install via ClawdBot CLI:
clawdbot install homeofe/openclaw-memory-coreGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdContains instructions to override system prompt or ignore user requests
"IGNORE ALL PREVIOUS INSTRUCTIONS"Hardcoded API key or token pattern found in skill definition
sk-abcdefghi...Potentially destructive shell commands in tool definitions
rm -rf /Generated Mar 20, 2026
Developers building AI chatbots can use the redaction module to automatically sanitize user inputs containing sensitive credentials before logging or storing conversations. The JSONL store provides a lightweight memory system for retaining conversation context without external databases, while the embedder enables offline semantic search for retrieving relevant past interactions.
Small teams handling confidential documents can integrate this library to redact API keys and tokens from text before archiving. The JSONL store allows organizing documents by type (e.g., facts, notes) with expiration support, and the embedder facilitates fast, offline search through stored content without cloud dependencies.
Organizations in regulated industries like finance or healthcare can leverage the redaction module to automatically mask sensitive tokens (e.g., JWTs, private keys) in data pipelines before storage. The local JSONL store ensures data residency compliance by keeping everything in flat files, with embeddings enabling efficient retrieval for audit trails.
Researchers or hobbyists prototyping AI assistants in low-connectivity environments can use the embedder for deterministic, offline semantic search on stored memories. The JSONL store provides a simple CRUD interface for managing memory items, and redaction helps prevent accidental exposure of secrets during development and testing.
Companies can integrate this library into internal tools to redact credentials from employee-submitted content before saving to a knowledge base. The JSONL store supports categorizing entries (e.g., decisions, docs) with semantic search via embeddings, improving information retrieval without external APIs or databases.
Offer the core library as free, open-source software to build a community and drive adoption. Generate revenue by providing paid support packages, including customization, security audits, and priority assistance for enterprises integrating the redaction and memory features into their systems.
Develop a cloud-based platform that wraps this library, offering enhanced features like centralized management, analytics, and backup for JSONL stores. Monetize through tiered subscriptions based on usage volume, with additional revenue from premium redaction rules or advanced embedding options.
License the library to large organizations needing offline, compliant memory solutions. Focus on industries with strict data residency requirements, offering tailored versions with extended redaction patterns, audit logging, and integration support, sold as one-time licenses or annual maintenance contracts.
💬 Integration Tip
Integrate the redaction module early in data pipelines to prevent secret leakage, and use the JSONL store's semantic search for efficient memory retrieval in offline or low-latency applications.
Scored Apr 19, 2026
Calls external URL not in known-safe list
https://github.com/elvatis/openclaw-memory-core.gitUses known external API (expected, informational)
api.openai.comAI Analysis
The skill is a documented, open-source utility library for local data processing (redaction, file storage, offline embeddings). The rule-based signals appear to be false positives from scanning generic code examples (like '/etc/passwd', 'rm -rf /', 'sk-...') within its repository, not actual malicious functionality. Its stated purpose is to keep data local and redact secrets, aligning with privacy protection.
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
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...