layered-memory-managerMulti-tier (L1/L2) memory management skill for OpenClaw agents. Use when: (1) reading, writing, organizing, or searching memories, (2) deciding what to remem...
Install via ClawdBot CLI:
clawdbot install chyern/layered-memory-managerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/chyern/Agent-SkillsAudited Apr 23, 2026 · audit v1.0
Generated Oct 2, 2026
An always-on OpenClaw agent that serves one user across months of daily sessions, remembering preferences, decisions, and project context. The L1/L2 architecture keeps hot facts (user name, core preferences) instantly available while detailed history stays in cold storage. Hygiene cycles automatically promote frequently accessed memories and archive stale ones.
A corporate agent deployed to a team of analysts that must retain decision rationale, project state, and institutional preferences across many users and sessions. L2 layer files per domain (decisions.md, context.md) act as an auditable knowledge base, while L1 provides fast recall during active work. Explicit forget-by-tag supports compliance-driven data hygiene.
A developer assistant working on a large codebase over weeks, needing to remember architectural decisions, conventions, and previously resolved bugs. The pre-decision self-check rule ensures the agent greps memory before running shell commands or edits, preventing it from violating established project preferences. Daily session logs provide a chronological debugging trail.
An agent handling recurring customer interactions that must recall prior tickets, escalation decisions, and account-specific preferences. The 3-session promotion trigger surfaces high-frequency issues to L1 for rapid response, while full ticket histories remain in L2. Forget-by-keyword supports right-to-be-forgotten requests.
An agent conducting long-horizon research projects that needs to track evolving hypotheses, sources, and conclusions across many sessions. L2 knowledge.md and decisions.md preserve full reasoning context, while L1 keeps the most-cited facts at hand. Hygiene monitoring flags memory drift or contradictions between layers.
Released as a free, self-hosted skill package for the OpenClaw agent community, with optional paid support and hygiene tooling. Adoption drives ecosystem lock-in around the L1/L2 memory convention. Monetization comes from enterprise support contracts and managed sync services.
A hosted backend that persists L1/L2 memory, runs scheduled hygiene jobs, and provides cross-device sync for agent users. Teams pay per active memory namespace or per stored gigabyte. Premium tiers add audit logs, compliance-grade forget workflows, and analytics on memory health.
A licensed platform sold to companies deploying fleets of OpenClaw agents, bundling role-based access control, centralized hygiene policy, and memory analytics dashboards. Integration includes SSO and audit export for regulated industries. Annual per-seat licensing with volume discounts.
💬 Integration Tip
Start by mapping your existing workspace files to the L1/L2 convention, then enable hygiene.json tracking before adding promotion automation. Test the pre-decision self-check rule early, since it fundamentally changes how the agent interacts with tools.
Scored Oct 2, 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...