vfsProvides a multi-agent shared AI virtual memory system with semantic search, token-aware recall, lifecycle management, decentralized discovery, and memory co...
Install via ClawdBot CLI:
clawdbot install bkmashiro/vfsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdSends data to undocumented external endpoint (potential exfiltration)
webhook → http://localhost:9999/testPotentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://paper-api.alpaca.marketsGenerated May 12, 2026
A developer uses AVM to store and semantically recall personal notes, code snippets, and documentation, enhancing productivity with fast, relevance-ranked access.
Multiple trading agents share a memory namespace with AVM, each contributing market analysis and signals, enabling collaborative research and consensus-based decision-making.
A customer support agent retains past interactions and solution articles in AVM, quickly recalling relevant information to resolve new tickets efficiently.
A researcher uses AVM to store and link papers, notes, and experimental results with tags for easy retrieval and knowledge graph navigation.
An AI personal finance assistant maintains a memory of user transactions, goals, and advice, using importance and tags to prioritize relevant information during conversations.
Offer the AVM daemon as a cloud-managed service with tiered subscriptions based on storage size and number of agents, providing regular updates and support.
Provide a white-label solution for enterprises to deploy AVM for their AI agent fleets, with dedicated instances, advanced security, and custom integrations.
Offer a free tier with limited storage and agents, and charge for premium features like higher recall speed, importance scoring, and knowledge graph analytics.
💬 Integration Tip
Start by mounting AVM for a single agent and test recall/remember via command line. For multi-agent, add per-agent mounts and use shared namespaces for collaboration.
Scored Jun 29, 2026
Uses known external API (expected, informational)
api.anthropic.comAI Analysis
The skill primarily manages a local memory filesystem for AI agents and does not appear to send user data to unauthorized external servers. The identified signals point to local daemon operations and configuration access, not active credential harvesting or data exfiltration. The external API reference (paper-api.alpaca.markets) is likely a placeholder or example, not a core function.
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...