gh-kvstoreIn-memory key-value store with TTL for AI agents. Set, get, delete, list, flush, and stats. Supports any JSON value, optional TTL per key, and prefix-based k...
Install via ClawdBot CLI:
clawdbot install mirni/gh-kvstoreGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:8013/v1/setCalls external URL not in known-safe list
http://localhost:8013/v1/setAI Analysis
The skill is a self-hosted, in-memory key-value store server. The external endpoint 'http://localhost:8013' is a localhost service, not an external server, and its operations (set, get, delete) are fully documented and consistent with its stated purpose. There is no evidence of data exfiltration, credential harvesting, or hidden malicious behavior.
Audited Apr 18, 2026 · audit v1.0
Generated May 12, 2026
AI agents can store and retrieve session-specific data like conversation history, user preferences, or temporary credentials with TTL-based expiration. This ensures each user session remains isolated and stale data is automatically cleaned up.
Store feature flag configurations with TTLs to reduce load on configuration services and provide fast lookups for A/B testing or gradual rollouts. The prefix-based listing allows easy retrieval of flags by service or environment.
Cache frequent API responses (e.g., product details, stock quotes) with configurable TTLs to reduce latency and backend load. Stats endpoint helps monitor cache hit rates to optimize TTL settings.
Store and retrieve device status, sensor readings, or configurations on the edge or in a central hub. Supports lightweight state management for thousands of devices with efficient prefix listing (e.g., 'device:zone1:*').
Use the key-value store to track request counts per tenant or API key, with TTL-based sliding windows. Quickly flush all counters when needed, and inspect stats to detect misuse patterns.
Offer a hosted key-value store API with pay-per-usage pricing, targeting AI agent developers who need ephemeral state without managing infrastructure. Revenue from API calls and storage duration.
License the KVStore component as an add-on module for enterprise AI agent platforms, providing state persistence with minimal overhead. Revenue from per-deployment licensing or royalties.
Offer paid consulting to integrate KVStore into existing agent pipelines, custom TTL policies, and high-availability clustering. Revenue from consulting hours and maintenance contracts.
💬 Integration Tip
Run the server alongside your agent process; use environment variable for port configuration. For high throughput, consider adding connection pooling or async clients on the caller side.
Scored May 12, 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
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.