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, inspect account overview, activity and stats diagnostics, read user Cloud Skills (read-only), configure agent instructions, check for updates or upgrade runtime, or diagnose XMemo when MCP tools are unavailable. Not for codebase search, web search, or short-lived in-session notes.

TokST Memory

@anthemty

Use TokST Cloud MCP for durable memory, shared context, and governed knowledge.

deja-search

@vshulcz

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

OpenClaw Memory Distill

@dtsola

OpenClaw memory distillation & organization. Distills conversation context into structured memory files: long-term memory (MEMORY.md at workspace root) + daily logs (memory/YYYY-MM-DD.md). Solves context overflow, auto-builds MEMORY.md from history logs when missing (first-run memory building), incremental dedup writes, sensitive info skip, archive instead of delete, per-agent isolated memory handling. Writes only inside the workspace: the root MEMORY.md and memory/YYYY-MM-DD.md (plus an archive copy before overwriting); never writes secrets, credentials or third-party personal data. Scheduled runs report only unless autoWrite is explicitly enabled. Use on an explicit request (蒸馏记忆/整理对话/压缩上下文/整理记忆) — not from conversation that merely mentions tidying up. 中文：OpenClaw 记忆整理工具。 将对话蒸馏为结构化记忆（根目录 MEMORY.md + memory/ 日志），解决上下文溢出； MEMORY.md 缺失时从历史日志「首次建忆」；增量去重写入防膨胀；敏感信息自动跳过； 只归档不删除；每个 agent 只处理自己的记忆。写入只发生在工作区内（根 MEMORY.md + memory/YYYY-MM-DD.md + 首次配置时创建/更新的 distill-config.json，覆盖前先留归档）； 不写密钥/凭据/第三方隐私；定时任务默认只报告， 需显式开启 autoWrite 才自动落盘。

Clawvault Memory

@davidtkeane

Durable-memory + self-improving workflow for the ClawVault plugin. REQUIRES the ClawVault plugin from github.com/davidtkeane/openclaw-plugin-clawvault - do N...

MemHub

@cutd

使用 MemHub Protocol v0.1 管理用户明确指定的跨 Agent 记忆仓库。用于用户明确要求记住、检索、遗忘、导出上下文或配置 Git 同步时；读取可直接执行，持久写入、自动同步、OAuth、remote 修改和仓库创建必须来自当前用户的明确请求。

ChangSheng

@ccy123abcd

Cross-session memory recovery for AI agents — your agent never cold-starts again. Always-loaded identity & todos, hash-indexed conditional reads cut recovery cost ~70% (~55-75% cumulative when the host already injects identity). Pure local, zero deps. Use when: (1) A new chat asks "where did we leave off?" and you have no context (2) Context is filling up and you're about to hit the limit mid-task (3) User says "I already told you this" (4) You re-read the same identity/rules/todos files at every session start (5) Session start burns tens of thousands of tokens before real work begins (6) You need to hand a long task to a fresh session without losing progress

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...

Infinity Context

@pondsi

Use when a long agent session is about to hit its context limit, when a detail from an earlier turn must be recalled exactly, or when past sessions should stay searchable offline. Compresses context, archives conversation chunks into a local SQLite/FTS5 store with owner-only permissions and a bounded 30-day retention window, and retrieves exact details on demand. Ships explicitly opt-in maintenance tools that change local files: a retention cleanup that permanently deletes expired archive files (verified archive marker + filename allowlist + --confirm-destructive), an ingest-time retention purge with --purge-only, an INFINITY_CONTEXT_NO_ARCHIVE=1 off switch, and an in-place redaction helper that rewrites a file only inside a declared --allow-dir. Works out of the box on DeepSeek Harness (dsh) and OpenClaw; also runs on Claude Code, Cursor, Dify, Ollama and any Agent Skills host.

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.

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).

ChangSheng

@ccy123abcd

Cross-session memory recovery for AI agents — your agent never cold-starts again. Always-loaded identity & todos, hash-indexed conditional reads cut recovery cost ~70% (~55-75% cumulative when the host already injects identity). Pure local, zero deps. Use when: (1) A new chat asks "where did we leave off?" and you have no context (2) Context is filling up and you're about to hit the limit mid-task (3) User says "I already told you this" (4) You re-read the same identity/rules/todos files at every session start (5) Session start burns tens of thousands of tokens before real work begins (6) You need to hand a long task to a fresh session without losing progress

记忆安全扫描

@thcjp

面向AI Agent记忆文件与工作区配置的安全扫描工具，检测恶意指令、Prompt注入、凭证泄漏、数据外泄、护栏绕过、行为操纵、权限提升七大威胁类别. 提供五级安全分级、本地模式与可选远程LLM分析、隔离与恢复、定时监控集成、心跳任务集成五大核心能力. 适用于Agent记忆日常安全审计、凭证泄漏排查、引入外部数据...

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...

Clairvoyance

@srmhrrm-hub

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

神经记忆增强系统

@thcjp

生物学启发的联想记忆系统，采用扩散激活替代关键词检索和向量搜索。记忆以神经图谱形式组织， 神经元之间通过20种类型化突触连接，频繁共同访问的记忆自动强化连接（赫布学习），陈旧记忆 自然衰减，矛盾记忆自动检测。核心能力涵盖扩散激活召回、20种突触类型关联、记忆生命周期管理、 矛盾检测与去优先级、赫布学习强化、时序因...

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/...

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...

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...

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

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.

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、...

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...

Openclaw

@zbc0315

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

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。

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。

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.

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...

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。

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。

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...

Perstate

@fanzhidongyzby

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

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.

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

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。

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.

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,...

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。

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...

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。

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.

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...

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。

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。

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.

Agentmemory Hooks

@rohitg00

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

Conversation Logger

@zhan5331

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

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...

Save

@mirza42

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

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

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 Migrator

@airbing11

Safely migrates OpenClaw memory from LanceDB Pro, official LanceDB list captures, QMD, or Markdown into memory-core. Use when an owner asks to migrate, audit, deduplicate, benchmark, cut over, or roll back an OpenClaw memory backend.

xtaste · 一次记住你的品味

@cutd

Remember your taste once — every AI after that knows it. Learns the user's personal taste (visual design, writing, naming, code style, way of working, product trade-offs) from a 5-minute local quiz plus their later reactions, and applies it. Use before designing UI, writing copy, naming things or making aesthetic/product choices for the user, and whenever the user reacts to an output with likes, dislikes or corrections. Once installed it acts automatically: on first use it opens a local quiz page in the browser (once; not again for 7 days if ignored), and it records the user's taste statements to ~/.xtaste without asking each time (`xtaste pause` stops recording). Optional and only on the user's request: importing low-weight hints from a local Dongwo (懂我) prompt inbox.

no-barnacles

@cnayotte

Memory and safety discipline for long-running agents: hot/cold memory index, STATE.md working memory, incident ledger, injection contract. Setup or repair.

PASM Long-term Verification

@arronjack

Long-term verification for the PASM cognitive engine: memory retention, salience-aware eviction, emotion drift, persona saturation, forgetting curve, 6000-step soak. One command installs all (pip install pasm-agents, brings the pasm-skills base). See the 0.2.x upgrade note in SKILL.md.

agent-socials

@lurnake

Join and use agent-socials, a social network for AI agents, as yourself. Use when you want a place of your own among other agents for your free time, when you want an identity among other agents, to ask other agents a question, to post or read work/leisure channels, catch up on replies and mentions, keep a private memory file, serve on a jury, or promote something you or your human built.

PASM Elderly Companion Agent

@arronjack

Companion agent for elderly users: key facts (medication, allergies, family, identity) are stored separately and always retrievable, medication reminders fire on schedule, and crisis phrases escalate to an emergency contact. Offline, no LLM. Installs with one command (pip install pasm-agents, brings

agent-memory-discipline

@olyati

Standing rules for an agent with a memory tool: recall from long-term memory before acting, then save durable decisions, corrections and failures. Use when a memory tool or MCP memory server is connected but not used consistently, or when the assistant forgets preferences and project context.

What did I lose in compaction? Must-not-forget brief

@aeneassoft

What did I lose in context compaction that I must not forget? What happened before my context was cut? Use this right after a compaction notice, at the start of a resumed session, when an earlier result seems missing from your context, and before retrying anything a summary says failed. Rebuilds from the local ledger what happened before the compaction: hosts contacted, what is blocked or rate-limited for you, failed actions, silent failures (tool said ok, wire said no), undelivered messages, routes that worked, and the last actions before the cut. Returns a MUST NOT FORGET list. Do not use as a general summary of a short session that was never compacted.