Claude skills for memory

The 50 strongest of 739 memory skills on GitHub. Skills built for memory come first; no repository gets more than 3 spots. Each links to its folder; copy it into ~/.claude/skills/ to use it.

  1. para memory files

    Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions. Trigger on saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory.

    paperclipai/paperclip★ 109kMITFolder: para-memory-files

  2. agent memory mcp

    A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

    sickn33/agentic-awesome-skills★ 49kMITFolder: agent-memory-mcp

  3. agent memory discipline

    Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.

    sickn33/agentic-awesome-skills★ 49kMITFolder: agent-memory-discipline

  4. agent memory

    A hybrid memory system that provides persistent, searchable knowledge management for AI agents.

    sickn33/agentic-awesome-skills★ 49kMITFolder: agent-memory

  5. spark memory thermal ops

    Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

    wshobson/agents★ 42kMITFolder: spark-memory-thermal-ops

  6. codebase memory mcp

    Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip…

    github/awesome-copilot★ 41kMITFolder: codebase-memory-mcp

  7. migrate memory

    Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run after an update reports the shared-memory breaking change, or when a group still has .seed.md, legacy CLAUDE.md/CLAUDE.local.md,…

    nanocoai/nanoclaw★ 31kMITFolder: migrate-memory

  8. memory management

    Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.

    ThinkInAIXYZ/deepchat★ 6.4kApache-2.0Folder: memory-management

  9. remember

    Store a learning, pattern, or decision in the memory system for future recall

    parcadei/Continuous-Claude-v3★ 3.9kMITFolder: remember

  10. memory bridge

    Browse or compare wiki knowledge by originating AI tool. Use for cross-tool memory questions, tool-specific knowledge, or gap/diff analysis between Codex, Claude, Hermes, and other agents.

    Ar9av/obsidian-wiki★ 3.6kMITFolder: memory-bridge

  11. session memory

    Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.

    a5c-ai/babysitter★ 1.9kMITFolder: session-memory

  12. persistent memory

    Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.

    a5c-ai/babysitter★ 1.9kMITFolder: persistent-memory

  13. vector memory

    HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.

    a5c-ai/babysitter★ 1.9kMITFolder: vector-memory

  14. promote memory

    Review candidate learnings in Claude Code's native auto memory (`~/.claude/projects/<project>/memory/`, machine-local) and run them through a five-critic council in parallel: generality, staleness, redundancy, evidence, format. Majority vote (3+ of 5)…

    pedrohcgs/claude-code-my-workflow★ 1.7kMITFolder: promote-memory

  15. memory

    AI DevKit · Use the memory CLI as a durable knowledge layer. Search before non-trivial work, store verified reusable knowledge, update stale entries, and avoid saving transcripts, secrets, or one-off task progress.

    codeaholicguy/ai-devkit★ 1.7kApache-2.0Folder: memory

  16. hivemind memory

    Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

    activeloopai/hivemind★ 1.6kApache-2.0Folder: hivemind-memory

  17. memory ticketing

    Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.

    agentlas-ai/Agentlas-OS★ 1.6kApache-2.0Folder: memory-ticketing

  18. memory file maintenance

    Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting you right. Use when asked review my memory file, my AI context is outdated,…

    mohitagw15856/pm-claude-skills★ 1.5kMITFolder: memory-file-maintenance

  19. memory hygiene

    Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries

    huytieu/COG-second-brain★ 1.3kMITFolder: memory-hygiene

  20. run memory

    Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run…

    gooseworks-ai/goose-skills★ 1.3kMITFolder: run-memory

  21. matlab optimize memory

    Guides the 7-step MATLAB memory optimization workflow: baseline, profile, identify, optimize, measure, verify, report. Use when asked to reduce MATLAB memory usage, find memory bottlenecks, fix out-of-memory errors, or optimize memory-intensive code.

    matlab/matlab-agentic-toolkit★ 1.2kLicence: see repoFolder: matlab-optimize-memory

  22. memory review

    Review the file-based memory store via the Agent Monitor Config Explorer API: the user and project CLAUDE.md plus per-project auto-memory files under ~/.claude/projects/<slug>/memory/*.md. Groups by project, shows the index (MEMORY.md) vs per-fact files,…

    hoangsonww/Claude-Code-Agent-Monitor★ 1.1kMITFolder: memory-review

  23. extract atomic memory

    Read one conversation window and return every independently mutable claim it states, one record each, with who or what it is about, whether it happened or stands, and the words that carry its time. Used by the memory extraction model on every conversation…

    sno-ai/sno-station★ 1kApache-2.0Folder: extract-atomic-memory

  24. judge rem memory updates

    Judge REM memory relations, rewrites, verification, and clause carry by meaning. Use for REM update model calls that decide which older facts are superseded, which facts remain current, and whether a proposed rewrite preserves all surviving facts.

    sno-ai/sno-station★ 1kApache-2.0Folder: judge-rem-memory-updates

  25. memory detective

    根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件,并在用户确认后生成可追溯的回忆故事。

    LC044/TrailSnap★ 849AGPL-3.0Folder: memory-detective

  26. light memory pm

    Light 项目运行时记忆与项目管理常驻技能:把"项目做到哪/定了啥/出到哪版/术语怎么统一/上次断哪" 落到每个项目自己的 .light/ 目录(项目卡 + 决策日志 + 版本史 + 受控术语表 + 跨会话交接卡), 复用 passport.py 引擎管 DAG 台账(不重造)。它是 consistency 事实源的归属方,定义一改即变更广播 回扫所有材料;是总控"会话开头自动汇报上次断哪"的记忆底座。何时用:长期/跨会话项目、需记住背景/进展/…

    Light0305/Light-skills★ 824MITFolder: light-memory-pm

  27. media memory

    Use when the user sends or generates an image, screenshot, video, audio or file and wants it saved, or asks to find past media (that diagram, the mockup from last week). Ingests and searches with local ChromaDB embeddings.

    coco-research/coco★ 795Licence: see repoFolder: media-memory

  28. video memory

    The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a question that spans several videos. Use this to search and…

    oxbshw/watch-skill★ 534MITFolder: video-memory

  29. windbg user virtual memory exhaustion

    Use when a native app, service, or user-mode driver host allocation fails; distinguish VA exhaustion, fragmentation, and commit pressure. Not for managed .NET heap growth, proving a leak from one snapshot, or corruption.

    microsoft/win-dev-skills★ 490MITFolder: windbg-user-virtual-memory-exhaustion

  30. memory bank

    Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.

    aiskillstore/marketplace★ 446No licence statedFolder: memory-bank

  31. project memory

    Generates project instruction files (AGENTS.md or CLAUDE.md) that transfer institutional knowledge. Use when setting up projects or onboarding. For lessons from a finished project or investigation, use project-retrospective.

    jamditis/claude-skills-journalism★ 439MITFolder: project-memory

  32. AgentDB Memory Patterns

    Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

    Microck/ordinary-claude-skills★ 408Licence: see repoFolder: agentdb-memory-patterns

  33. engagement memory

    Use when recalling prior techniques at recon/weaponize, or recording a confirmed finding at report — cross-engagement pattern memory ranked by impact

    hypnguyen1209/offensive-claude★ 403MITFolder: engagement-memory

  34. V3 Memory Unification

    Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

    spencermarx/open-code-review★ 382Apache-2.0Folder: v3-memory-unification

  35. memory md management

    Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files.…

    giuseppe-trisciuoglio/developer-kit★ 366MITFolder: memory-md-management

  36. night market collective memory

    Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for settled battles; see failure-archaeology.

    athola/claude-night-market★ 343MITFolder: night-market-collective-memory

  37. memory palace architect

    Designs memory palace structures with spatial layouts and domain organization. Use when creating a new palace or planning knowledge architecture by hand.

    athola/claude-night-market★ 343MITFolder: memory-palace-architect

  38. memory clarity probe

    Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.

    athola/claude-night-market★ 343MITFolder: memory-clarity-probe

  39. agent memory testing

    Use this skill when you need evidence-bounded memory write/read/update/delete, retention, contamination, isolation, provenance, and forgetting behavior; triggers include Agent 记忆 and Agent memory.

    naodeng/awesome-qa-skills★ 288Licence: see repoFolder: agent-memory-testing

  40. memory forensics triage

    Triages supplied Windows, Linux, or other volatile-memory images while preserving acquisition provenance, image integrity, process and region evidence, network and object correlations, extracted-artifact custody, timeline limits, and claim confidence. Use…

    zero-lab-ai/skills★ 284Apache-2.0Folder: memory-forensics-triage

  41. qdrant memory usage optimization

    Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match…

    qdrant/skills★ 266Apache-2.0Folder: memory-usage-optimization

  42. debug memory

    Query and manage the executable feedback debug memory

    jmagly/aiwg★ 226MITFolder: debug-memory

  43. ralph memory

    Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations

    jmagly/aiwg★ 226MITFolder: ralph-memory

  44. harness memory maintenance

    Audit and maintain harness memory through reviewed aiwg memory plans, with owner receipts, verification and recovery.

    jmagly/aiwg★ 226MITFolder: harness-memory-maintenance

  45. rag and memory

    Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.

    DevelopersGlobal/ai-agent-skills★ 216MITFolder: rag-and-memory

  46. oma memory

    Manage project memory with MEMORY.md index + modular rule packs.

    Joonghyun-Lee-Frieren/oh-my-antigravity★ 215Licence: see repoFolder: oma-memory

  47. memory system

    当需要为 AI 设计记忆存储、检索、应用和更新机制时调用此 skill。典型场景包括:设计持久化记忆架构(用户偏好、历史上下文、项目知识)、定义记忆的创建/读取/更新/删除生命周期、实现静默记忆应用(不在回复中透露记忆内容)、管理敏感记忆边界。 不适用于:定义工具接口(tool-specification)、定义安全规则(safety-guardrails)、定义人格风格(personality-system)。 关键 trigger 信号:AI…

    kangarooking/system-prompt-skills★ 214MITFolder: memory-system

  48. compact memory implementation

    Developer implementation guide for adding compact memory to an Agent — covers fork agent pattern for compaction, trigger strategy, summary format design, and memory restoration in subsequent sessions. Use when a developer asks how to implement compact…

    simbajigege/book2skills★ 198MITFolder: compact-memory-implementation

  49. agent memory implementation

    Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system organizes memory — a lightweight pointer index (always loaded) and topic files (loaded on demand). Stale or superseded memories are…

    simbajigege/book2skills★ 198MITFolder: agent-memory-implementation

  50. folded memory implementation

    Developer implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when…

    simbajigege/book2skills★ 198MITFolder: folded-memory-implementation

Claude skills for memory: common questions

What's the best Claude skill for memory?

Yes: 739 public skills from 340 GitHub repositories mention memory. The best-known ones named for it are para memory files (paperclipai/paperclip, ★ 109k), agent memory mcp (sickn33/agentic-awesome-skills, ★ 49k) and agent memory discipline (sickn33/agentic-awesome-skills, ★ 49k). Stars belong to the whole repository, not to one skill.

How do I add para memory files to Claude?

For memory, copy the para-memory-files folder from paperclipai/paperclip (the folder that holds SKILL.md) into ~/.claude/skills/ to use it in every Claude Code project, or into .claude/skills/ for one project. For the Claude apps, upload the zipped folder as a custom skill instead.

Skill or MCP server for memory: which do I need?

A skill teaches Claude a way of working; an MCP server gives it new tools, like access to memory itself. We list 729 MCP servers for memory if you need the connection.

Are there memory skills in other languages?

No: 3 of those listed, such as memory detective and light memory pm, are written mainly in Chinese, Japanese, Korean or Russian rather than English, though the memory task is the same. Claude can follow them either way, but read them before you install.

How recently were memory skills updated?

527 of the 739 memory skills sit in repositories that changed in the 30 days before 31 Oct 2026.

More topics: every “Claude skills for…” page.