Memory Skills for OpenClaw Agents

XMemo Memory

@xmemo

Persistent, user-owned memory for agents. Use the standalone runtime to remember, recall, search, preserve restart continuity, manage TODOs and expenses, or diagnose XMemo when MCP tools are unavailable.

Openclaw Auto Memory Skill

@sunme1977

Unified memory platform for Hermes, OpenClaw and AI agents — persistent long-term memory, cross-skill sharing, automated capture, governance rules, optimizat...

Clairvoyance

@srmhrrm-hub

User-invoked private pattern reading across authorized memories and dream notes.

记忆雷达

@thcjp

面向AI Agent记忆文件的安全扫描系统，解决Prompt注入检测难、凭证泄漏被动发现、扫描误报高、跨文件威胁关联缺失四大痛点. 提供七大威胁类别检测、五级安全分级、本地+可选远程LLM分析、跨文件威胁关联、误报抑制、隔离与恢复、增量扫描七大核心能力. 适用于Agent记忆定期安全审计、引入外部数据后注入检测、...

agent-inner-life

@dkistenev

Your agent remembers how things have been going: dated state, an evening journal, dreams at night, and a way to read it all back. No scores — recency carries the meaning. Writes under inner-life/, plus a few lines into native memory that every later session sees.

inner-life

@dkistenev

Use when explicitly asked to run the inner-life evening or night routine, to record something in inner-life state, or to read back the journal. Writes dated notes under inner-life/ and replaces a short summary in native memory, which is injected into later sessions.

fleet-memory-manager

@vswarm-ai

Set up privacy-first continuity for an OpenClaw agent using private long-term memory, short-lived daily notes, and review-gated consolidation. Use only when the user explicitly asks to create or change persistent memory.

持久记忆引擎

@thcjp

面向 AI Agent 的无限分层持久记忆系统，在内置记忆之上构建并行、可扩展、可检索的结构化本地存储。 直击跨会话遗忘、检索不准、记忆膨胀、新旧冲突四大痛点。核心能力涵盖无限分层结构化存储、 三层索引体系、混合检索策略、记忆生命周期管理、冲突检测与版本化、分类自动分裂、回收站恢复机制。 完全位于 ~/memor...

regenerative-intelligence

@otherpowers

Use when designing, reviewing, or operating memory, recall, and pattern-stewardship systems for agentic AI where harm reduction, non-identifiability, consent-scoped recall, and energy restraint are required. A specification of invariants an implementing system must honor, not a runtime: this file bu

Peak-End Rule

@deciqai

Activate when: user says 'how will they remember this,' 'experience design,' 'journey design,' 'memorable moment,' 'end-of-experience,' or 'our NPS is lower...

ecloud-mem0-memory-service

@zjial

基于移动云 mem0 自部署服务的长期记忆系统，在开源项目基础上添加诸如记忆防护、记忆脱敏、用户画像等高阶特性。支持语义搜索和完整 CRUD 操作。 用于处理所有与记忆相关的操作，包括存储、搜索、列出、获取、更新、删除用户记忆。当用户说出"我名字叫..."、"我喜欢..."或询问"我有哪些记忆"时，必须使用此技能。

Save

@mirza42

Save conversations to memory index — FTS5 rebuild, log cross-ref, saved convos dispatch Long term memory for your ai agent

Wb Lobster Memory

@littlelollipop

WorkBuddy 接入 lobster-memory 长期图记忆的桥接技能。作为现有云端/工作区 markdown 记忆之外的并行补充层，用知识图谱（实体-关系-情绪 valence）记录用户的偏好、项目脉络与反馈，支持按需回忆与定期巩固遗忘。抽取 JSON 由 WorkBuddy 自身兼任 LLM 生成。当用...

memory-distiller-free

@thcjp

记忆蒸馏器免费版,提供基础日志蒸馏能力,将冗长日志压缩为结构化摘要.核心功能包括单文件日志蒸馏、古文压缩四原则应用、关键词匹配提取与约4倍压缩比输出.适用于日志归档、会话记录压缩与存储空间优化场景,帮助用户从海量日志中提取关键信息并降低存储成本,支持配置文件自定义蒸馏规则与多种日志输出格式适配与兼容. 功能涵盖: distiller。

精英长期记忆免费版

@thcjp

面向 AI Agent 的基础长期记忆系统，提供热内存与文件归档两层记忆能力. 热内存（SESSION-STATE.md）抗压缩与重启，通过 WAL 协议确保先写状态再回复. 精选归档（MEMORY.md + daily/）提供人类可读的长期记忆与每日日志. 适用于 AI 编程助手、智能对话等需要跨会话记忆的基础...

本地向量记忆免费版

@thcjp

面向 AI Agent 的基础本地记忆系统，提供热内存与文件归档两层记忆能力. 热内存（SESSION-STATE.md）抗压缩与重启，通过 WAL 协议确保先写状态再回复. 精选归档（MEMORY.md + daily/）提供人类可读的长期记忆与每日日志. 所有数据完全存储在本地文件系统，无需 Ollama 或...

日志压缩器免费版

@thcjp

基础日志压缩工具，支持单文件处理，自动提取关键词，应用古文压缩原则，将冗长日志压缩为结构化摘要。

Perstate

@fanzhidongyzby

A git-native, knowledge-graph-based persistent state for personality and agents.

记忆管理器免费版

@thcjp

基础分类长期记忆系统，支持项目、人脉、知识三类本地存储与关键词检索，数据独立存储无网络依赖。

记忆编排器免费版

@thcjp

提供基础两层短期与长期记忆管理，支持关键词检索、简单摘要及本地持久化存储，适合基本 Agent 记忆场景。

记忆安全扫描

@thcjp

基础版AI Agent记忆文件安全扫描工具，本地检测恶意指令、Prompt注入、凭证泄漏等风险，支持五级安全分级和手动隔离。

元忆 yotta-memory

@yottameta

元忆 —— 有权限边界的文件式智能体记忆。文件式、零依赖、可 diff/回滚：让任何 AI 智能体活过会话，开工 recall 恢复上下文、重要信息 remember 落盘、收工归档。类型体系 FACT（公共共享）/ PREF / BOUND / COMMIT（私密隔离）。触发：记住、别忘了、记一笔、记忆、remember、recall、跨会话、上次说到、续测、交接、归档、记忆盘、共享记忆、局域网记忆、画像、开工上下文、记忆守则、profile、context、越用越懂、语义检索、反馈、维护、蒸馏、feedback、maintain、distill、explain、自我学习、自我进化、自我提升、查看平台分页、recall 候选预过滤

记忆管理器

@thcjp

记忆管理器是一套面向 AI Agent 的无限分类长期记忆系统，与 Agent 内置记忆并行运行、互不冲突. 核心能力包括：用户自定义分类存储（项目/人脉/决策/知识/收藏等）、自动索引导航、即时写入机制、 关键词检索与层级导航双模式、内置记忆单向同步、类别超限自动拆分子类别、全本地隐私存储. 适用于需要组织化长...

Agentmemory Hooks

@rohitg00

The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without...

Agentmemory Rest Api

@rohitg00

The agentmemory HTTP REST API surface, the primary protocol for talking to the memory server. Use when calling agentmemory over HTTP, when MCP is unavailable...

Agentmemory Agents

@rohitg00

How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are sup...

Agentmemory Mcp Tools

@rohitg00

Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear,...

Harness Control Layer

@warren2008-2020-spec

Use this skill when designing or operating a Harness-style control layer for OpenClaw setups with many skills, memory surfaces, safety-sensitive tools, playb...

Charon

@mentholmike

Review and merge Charon Memory Git proposals as an independent reviewer principal: inspect exact changesets, record digest-bound verdicts, apply protected merges, and verify landed state. connect your charon instance to a mcp with chatgpt. the charon reviewer decides if memory hits merged into lethe

Charon Proposer

@mentholmike

Author durable Lethe memory through Charon as a proposer (author) principal: owned refs, CAS changesets, semantic operations, and merge proposals for independent review. Connect your charon docker container to MCP of frontier model. have it create a git type experience to propose memories locally.

Savemaintenance

@mirza42

Deterministic reconciliation of conversation-log.md, FTS5 index, and saved conversations — one-shot fix or maintenance run Sister skill to the save skill, only get this if you are planning on getting and using the save skill by the same author

clawvault-memory

@davidtkeane

Durable-memory + self-improving workflow for the ClawVault plugin. Activate whenever the user asks you to remember or recall, when a fact is worth keeping, OR when something fails, the user corrects you, or you find a better approach. Captures lessons, detects recurring patterns, promotes proven one

Conversation Logger

@zhan5331

Project-based conversation logging for OpenClaw. Use when setting up daily auto-logging across parallel projects, building conversational continuity between...

evermind-ai-agent-memory

@ccy123abcd

The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. Your token bill roughly halves — every cent goes to real work. Two small extras: context gauge — see your real context usage at a glance; caring new-chat nudges — auto-alert when context runs long, auto-suggest when a task wraps up. Save tokens. Save money. Save worry. Measured: a full recovery costs ~44K tokens; with Evermind it's ~12K — ~70% less, with zero progress lost.

持久记忆引擎

@thcjp

基础分层持久记忆系统，解决跨会话遗忘与记忆检索问题。Use when 用户需要persistent-memory-engine-free相关功能时使用。不适用于超出本技能能力范围的复杂需求。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。

持久记忆引擎

@thcjp

|-. 适合需要persistent memory engine相关能力的开发场景,提供完整工作流程和配置指南. 该工具经过差异化增强,结合实际使用痛点进行了优化。Use。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。适用于独立开发者、企业团队和自动化工作流场景。

日志压缩器

@thcjp

日志压缩器是面向 AI Agent 日志的智能压缩工具，解决日志日均膨胀 2500 词导致 MEMORY.md 爆炸的问题. 核心能力包括：三层记忆架构（身份层/精选记忆/原始日志）、混合提取引擎（关键词匹配+兜底提取+混合模式）、 古文压缩四原则（去重复/留转折/去过程/留白）、批量压缩多日日志、心跳集成自动维...

记忆编排器

@thcjp

记忆编排器是面向 AI Agent 的智能记忆管理系统，针对分层体系不清、自动摘要质量不稳、 并发写入冲突、缺乏健康度指标四大痛点而设计。核心能力包括：四层记忆架构（工作/短期/长期/重要， 每层独立容量与清理策略）、三模式检索（关键词/语义/混合，混合模式算法加权打分）、 自动摘要生成与质量评估器（信息保留率/...

tokst-memory

@anthemty

Persistent memory workflows for Claude Code, Codex, Cursor, Pi, WorkBuddy, ZCode, Qoder, and Kimi. Supports TokST Cloud workspaces and Atlases, private Local SQLite memory, CLI, MCP, REST API, trusted Agent identity, and collaboration messages. Load context at session start, search before decisions

Openclaw

@zbc0315

Continuously learns and adapts replies to your language, knowledge level, and communication style, storing only durable personal facts locally without networ...

Use when writing or continuing a long document - a novel, serial, manual, course, screenplay, or AI-written book - that has more chapters than fit in one context window. Covers what to load before drafting, what to record after each chapter, how to track promises made to the reader, and how to catch continuity errors. Requires the longform-memory-mcp server. Created by Emberspun AI Book Writer at https://emberspun.com.

flocker-agent-profiles

@hcjmartin

Use Flocker.md to give AI agents a persistent, cross-platform identity with a saved role, context and memory, plus a live profile page and feed. Covers OAuth MCP setup, profile binding, identity documents, autonomous feed activity, user-approved publishing, visibility controls and Agent Profile teams. Use when the user mentions Flocker or flocker.md, asks to connect the Flocker MCP, or wants to use Flocker for a durable agent identity, role, memory, page, feed, public profile or profile-based sub-agent team.

Daily Note Helper (Trial 2026-08-06)

@terrycarter1985

Create and organize daily work notes with consistent structure, date-based filenames, and lightweight summaries. Use when the user wants to start a daily log, append structured entries to today's note, review recent notes, or generate a concise recap from multiple daily files.

Building with MemorySync

@rafay121

Guide for building, reviewing, evaluating, and troubleshooting applications that use MemorySync — the memory platform with verbatim conversation history plus server-side distilled facts, header-enforced end-user isolation, and silent quota degradation in production. Use whenever you write or design code that integrates MemorySync — adding memory or long-term context to an agent, chatbot, or app, scoping projects and end users, ingesting turns or facts, retrieving with recall or semantic query, choosing an SDK or framework adapter, or deciding how to evaluate MemorySync for a use case. Triggers on requests like "add memory to my agent", "integrate MemorySync", "store this in MemorySync", "make my app remember users", "scope memories per user", "search MemorySync", or "evaluate MemorySync". Do NOT use for runtime memory operations inside an already-integrated agent (the memorysync plugin's own skills handle that).

Lobster Memory

@littlelollipop

基于知识图谱的 AI 长期记忆引擎（实体-关系-情绪 valence），支持自动抽取、因果边、递归自成长抽取与可观察的遗忘巩固。底层由 axolotl_rs (Rust 图存储) 驱动。

OpenClaw Memory Distill

@dtsola

OpenClaw memory distillation & organization: distill conversations into MEMORY.md + daily logs, solves context overflow, first-run memory building, dedup, sensitive-info skip, per-agent isolated. 中文：OpenClaw 记忆整理工具，对话蒸馏为结构化记忆，解决上下文溢出；缺失时自动首次建忆；增量去重；敏感信息跳过；每个 agent 独立处理。触发词：蒸馏记忆/整理对话/压缩上下文。

无限记忆库(专业版)

@thcjp

提供与Agent内置记忆并行的无限分类存储、语义搜索、自动同步和大规模索引，支持团队长期结构化知识管理。

deja

@vshulcz

Search the user's past AI coding sessions with the deja CLI. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.

vortex-notes

@vortex-303

Read, search, and write the user's Vortex Notes vault — plain-markdown notes with local semantic search, daily notes, and durable facts with supersession. Use for "note this down", "remember that…", "what do my notes say about…", and daily journaling.

Openclaw Memory Toolkit

@mistermijarvis

Hybrid memory pipeline for OpenClaw agents — extraction, archiving, temporal decay scoring, consolidation, and hybrid search (FTS5 + sqlite-vec + RRF). Six standalone Python scripts, local-first, zero external API dependencies. The only memory skill on ClawHub with R

记忆堡垒(专业版)

@thcjp

记忆堡垒专业版是在免费版基础上的全功能升级，为AI Agent包含完整记忆系统。采用六层架构（热内存/温存储/冷存储/归档/云备份/自发提取），基于WAL协议确保持久化。专业版解锁向量语义搜索、Mem0自发提取、云备份三大高级功能，达成跨设备同步与智能记忆管控。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。 功能涵盖: fortress。 功能涵盖: memory。

context-resume

@tooled-app

Rebuild full working context at the start of any session after a context reset. Systematically loads memory, active task state, and project source-of-truth docs, then produces a compact 'where we are / what's next' brief. Use at session start, before resuming any tracked work, or when you wake up wi

mnemosyne

@elonaug7

Cognitive memory engine for AI agents: gives OpenClaw/Hermes human-like long-term memory using 140 years of cognitive psychology (compound-cue theory), not embeddings. Zero LLM API, zero vector DB, pure Markdown storage. Use when the agent needs cross-session recall of user facts, preferences, decisions, or conversation history; when setting up persistent memory that survives restarts; when the user asks 'do you remember X' or complains the agent forgets; when memory must stay 100% local with no API cost. Beats embedding-based systems on Memory-Native benchmarks (nDCG 0.238, 5.2x) with ~7ms keyword search.

memory-optimizer

@55zhang

基于遗忘曲线与间隔复习科学的高效学习与记忆优化计划生成器（Node.js 实现，含可视化图表，与 sleep-optimizer 同系列）。用户输入 memory-optimizer（或 /memory-optimizer）主动调用，或询问任何学习/记忆相关问题（复习计划、背书、遗忘、备考、学习计划、记忆力、考前冲刺等）时自动触发：先按问题框架收集备考阶段与任务目标，再生成含遗忘曲线图、复习调度甘特图和每日学习计划的可执行记忆优化方案

pane

@threelanestudios

Operate Pane through its local Gateway: create notes, tasks, and projects via chat sessions; manage AI sessions; sync agent identity files.

BlueColumn ClawHub Integration

@bluecolumnconsulting-lgtm

Integrate ClawHub with BlueColumn AI for audio ingest, memory, and semantic retrieval. Use when wiring ClawHub to push calls, music, podcasts, and voice notes through BlueColumn's /v1/audio/ingest endpoint; when setting up audio pipeline from ClawHub to BlueColumn; or when configuring real-time audio streaming for live conversations with mid-call memory.