secretary-memoryOpenClaw 秘书式多分区记忆系统 v3.0。仿生现代秘书的笔记本分类法,支持:(1) 多分区并发搜索 + 每分区3条上下文召回,(2) 会话自动摘要,(3) 偏好自动提取 + 用户关系图谱,(4) 记忆冲突主动检测,(5) 定时 consolidation + 会话结束 hook,(6) 精细化恢复/回溯,...
Install via ClawdBot CLI:
clawdbot install wgj24/secretary-memoryGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:11434/api/generateAudited May 20, 2026 · audit v1.0
Generated Oct 5, 2026
An individual power user runs an OpenClaw-based personal assistant that needs to remember preferences, ongoing projects, and past conversations across sessions. The Secretary Memory skill enables cross-session recall, automatic summarization, and preference mining so the assistant feels like a real human secretary who never forgets context. It automatically loads relevant memories at session start and archives older logs to prevent bloat.
A SaaS company deploys an AI customer support agent that handles hundreds of tickets per day. Using Secretary Memory, the agent can recall a customer's history, prior issues, and account details from previous interactions, delivering personalized support without repeating questions. The conflicts detection module prevents contradictory information from being served, and FTS5 search enables instant retrieval of past resolutions.
A software engineering team uses OpenClaw agents to track architecture decisions, code review patterns, and ongoing project todos. Secretary Memory organizes project notes, automatically generates skills from repeated tasks like bug triage or code review, and provides context-aware recall when developers ask about past decisions. The user relationship graph maps team members to projects and technologies for smarter recommendations.
A management consulting firm uses AI agents to capture meeting notes, client preferences, and project deliverables across multiple engagements. Secretary Memory's agenda and projects partitions keep work organized, while automatic session summaries and user modeling create a rich knowledge graph of client relationships. Consultants can query past discussions and get LLM-summarized answers instantly.
A research lab uses OpenClaw to manage literature notes, experiment logs, and collaborator interactions. Secretary Memory archives daily logs, builds a knowledge partition for papers and findings, and uses FTS5 full-text search to help researchers recall relevant prior work. The automatic skill generation detects repetitive analysis tasks and creates reusable tools for data processing.
The Secretary Memory skill is offered as a free, open-source package for individual users to run locally. A paid tier provides managed hosting, automated backups, advanced capacity analytics, and priority support for teams that want a turnkey solution without maintaining their own infrastructure.
Companies building their own AI assistants or customer support bots can license Secretary Memory as an embedded memory layer. Licensing fees scale with the number of active agents or API calls, and include enterprise features like SSO, audit logs, and compliance certifications.
A cloud-hosted version offers a free tier with limited memory capacity and basic search. Users can upgrade to a paid plan for increased storage, advanced LLM summarization, cross-session recall, and automatic skill generation. Add-ons include dedicated vector search, custom retention policies, and team collaboration features.
💬 Integration Tip
Integrate Secretary Memory by wiring the provided hook scripts (auto_loader, session_summary) into your agent's session lifecycle events; ensure Python 3 and SQLite with FTS5 are available, and configure the memory partition paths and capacity thresholds to match your storage and retention policies.
Scored Oct 5, 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...