2,195 agent tools in this category, ranked by GitHub stars for now. Hands-on test results will replace this ranking as they finish.
The three most-starred tools here. Not tested together yet.
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure
npx skills add addyosmani/agent-skills --skill context-engineeringUse this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.
npx skills add thedotmack/claude-mem --skill claude-mem-installUse this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login observer, or remote cmem.ai. No Cursor requi
npx skills add thedotmack/claude-mem --skill claude-mem-install| Tool | Stars | Last update | License | |
|---|---|---|---|---|
| context-engineering Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to SkillInstall · skills CLI | 117,221 | MIT | ||
| claude-mem-install Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference. SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| claude-mem-install Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login observer, or remote cmem.ai. No Cu SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| handoff Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exact SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| host-observer Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose. SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| how-it-works Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| knowledge-agent Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| mem-search Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions. SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| mem-search This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem", "mem search", "find past observat SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| mem-search Smart search (default). Search claude-mem's persistent cross-session memory database in three steps: search, timeline, then selected get_observations. SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| mem-setup This skill should be used when the user asks to "set up claude-mem", "pair claude-mem", "connect cmem", "add my cmem key", "set up cloud sync in Cowor SkillInstall · skills CLI | 116,897 | Apache-2.0 | ||
| 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 r SkillInstall · skills CLI | 113,505 | MIT | ||
| understand-knowledge Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and top SkillInstall · skills CLI | 92,567 | MIT | ||
| coding-agent-sessions Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or SkillInstall · skills CLI | 70,897 | — | ||
| ncats-arax Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph re SkillInstall · skills CLI | 57,090 | MIT | ||
| agent-memory-systems Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sess SkillInstall · skills CLI | 49,672 | MIT | ||
| Codebase Memory Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens. MCP serverGitHub-verified authorLocal · npm | 48,580 | MIT | ||
| claude-md-management Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current. PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| session-report Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from l PluginAnthropic marketplace | 47,064 | Apache-2.0 | ||
| superself Use when a project keeps its state in Superself (a `<!-- superself:begin` block in AGENTS.md or CLAUDE.md, or `self setup` resolves the directory to a SkillInstall · skills CLI | 42,495 | MIT | ||
| copilot-spaces Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context fro SkillInstall · skills CLI | 41,140 | MIT | ||
| memory-merger Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), SkillInstall · skills CLI | 41,140 | MIT | ||
| mini-context-graph A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM writ SkillInstall · skills CLI | 41,140 | MIT | ||
| on-device-delegate Saves cloud-model context by briefing one bounded, read-heavy sub-task (more than about 25 KB of prose, or many files that no single command can answe SkillInstall · skills CLI | 41,140 | MIT | ||
| agent-memory-mcp A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). SkillInstall · skills CLI | 33,495 | MIT | ||
| agent-memory-systems Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: s SkillInstall · skills CLI | 33,495 | MIT | ||
| conversation-memory Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memo SkillInstall · skills CLI | 33,495 | MIT | ||
| memory-search Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "wh SkillInstall · skills CLI | 33,495 | MIT | ||
| cognee-cli Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and conf SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-community Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, M SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-custom-graph-models Use when defining the shape of cognee's knowledge graph with graph_model= — writing DataPoint node classes, choosing identity and index fields so node SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-custom-pipelines Use when building your own cognee processing — writing custom tasks, chaining them into a pipeline with run_custom_pipeline or the lightweight run_pip SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-forget Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset and document hold the content to delete ( SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-improve-sessions Use when working with cognee's session memory or improve() — storing conversation turns, agent traces and feedback with session_id, bridging sessions SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-ingestion Use when putting data into cognee memory with remember() — choosing inputs (text, files, folders, URLs, repos, databases), datasets and node_sets, loa SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-install Use when the user wants to install cognee and run their first remember → recall flow with the Python SDK — fresh setup, virtual env, extras selection, SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-migrations Use when dealing with cognee database migrations — understanding when they run automatically, checking or repairing migration state with cognee-cli up SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-performance Use when cognee is slow, expensive, or hitting rate limits — speeding up or throttling ingestion (remember/cognify batching, chunk size, LLM and embed SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-permissions Use when working with cognee's users, permissions, and multi-tenancy — creating users, tenants and roles, sharing datasets (read/write/delete/share gr SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-recall Use when querying cognee memory with recall() (or search()) — picking a search type, understanding auto-routing, scoping to datasets, node sets or ses SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| cognee-server Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK o SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| company-brain-company-qa Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer question SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| company-brain-follow-up-agent Turn your latest Granola call into next steps (owner, team, due date, and the Linear issue that already tracks each one) and post them to Slack, using SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| google-workspace-memory Remember a user's Google Calendar, Gmail and Drive in one cognee memory and answer questions across them, by default preparing their client meetings o SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| multiagent-memory-setup Import the user's own Claude Code and/or Codex session history (the prompts they typed and the agents' answers) into one cognee dataset, then answer q SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| personalized-email Draft a reply to your newest Gmail email that knows what you discussed in your Granola meetings, what you promised the sender, and how you write, usin SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| self-hosted-companion Chat with a companion that knows your notes folder (a journal, an Obsidian vault, any .md or .txt files) and every earlier chat, using cognee memory w SkillInstall · skills CLI | 33,299 | Apache-2.0 | ||
| add-karpathy-llm-wiki Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm SkillInstall · skills CLI | 31,114 | MIT | ||
| add-mnemon Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn. SkillInstall · skills CLI | 31,114 | MIT | ||
| agent-memory Use when an agent keeps relearning the same correction, CLAUDE.md has grown unreadable, or you need to trace where a remembered rule came from. Promot SkillInstall · skills CLI | 29,773 | MIT | ||
| context-engine Use when starting a C-suite advisor session, when company context is missing or older than 90 days, or before company data goes to an external service SkillInstall · skills CLI | 29,773 | MIT | ||
| cs-onboard Use when setting up the C-suite advisors for the first time, or when company context is missing or stale after a raise or pivot. Interviews the founde SkillInstall · skills CLI | 29,773 | MIT | ||
| llm-wiki Use when building or maintaining an Obsidian second brain that an LLM keeps up to date, or when ingesting a paper, article or book into it. Ingests wi SkillInstall · skills CLI | 29,773 | MIT | ||
| memory-engineering Use before adding memory to an agent or when a memory store keeps growing (long context vs RAG vs graph vs agentic memory, what to expire). Prices the SkillInstall · skills CLI | 29,773 | MIT | ||
| planning-with-files Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; agent instructions read selecte SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; Gemini lifecycle hooks inject s SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; Kiro skill instructions and ste SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files-ar تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات task_plan.md و findings.md و progress.md على القرص، وتحقن خطافات SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files-de Persistente dateibasierte Planung für mehrstufige Arbeit mit KI-Agenten. Hält task_plan.md, findings.md und progress.md auf dem Datenträger; Lebenszyk SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files-es Planificación persistente basada en archivos para tareas multipaso de agentes de IA. Mantiene task_plan.md, findings.md y progress.md en disco; los ho SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files-zh 用于多步骤 AI 代理工作的持久化文件规划系统。将 task_plan.md、findings.md 和 progress.md 保存在磁盘上，生命周期钩子会注入选定的项目规划上下文。自动恢复只读取项目规划文件。只有显式运行 session-catchup.py --metadata 才会检查本机同 SkillInstall · skills CLI | 28,049 | MIT | ||
| planning-with-files-zht 用於多步驟 AI 代理工作的持久化檔案規劃。將 task_plan.md、findings.md 與 progress.md 保存在磁碟上，生命週期鉤子會注入選定的專案規劃內容。自動恢復只讀取專案規劃檔案；只有明確執行 session-catchup.py --metadata 才會檢查本機同一專案 SkillInstall · skills CLI | 28,049 | MIT | ||
| distilly Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague, relationship, or cele SkillInstall · skills CLI | 26,562 | MIT | ||
| monitor-experiment Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output. SkillInstall · skills CLI | 19,162 | MIT | ||
| paper-claim-audit Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with SkillInstall · skills CLI | 19,162 | MIT | ||
| skillopt-sleep Use when the user wants Codex to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, wants Codex to review past sessi SkillInstall · skills CLI | 19,069 | MIT | ||
| skillopt-sleep Use when the user wants Cursor to learn from recent local sessions, asks for an offline sleep or dream cycle, wants to consolidate recurring work into SkillInstall · skills CLI | 19,069 | MIT | ||
| skillopt-sleep Use when the user wants the dsh agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, skill/memory consolidati SkillInstall · skills CLI | 19,069 | MIT | ||
| skillopt-sleep Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation. SkillInstall · skills CLI | 19,069 | MIT | ||
| context-compression This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization SkillInstall · skills CLI | 18,347 | MIT | ||
| context-fundamentals This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context windo SkillInstall · skills CLI | 18,347 | MIT | ||
| context-optimization This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-c SkillInstall · skills CLI | 18,347 | MIT | ||
| filesystem-context This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent SkillInstall · skills CLI | 18,347 | MIT | ||
| latent-briefing This skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\", \"orchestrator worker contex SkillInstall · skills CLI | 18,347 | MIT | ||
| memory-systems This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, grap SkillInstall · skills CLI | 18,347 | MIT | ||
| langsmith-observability LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, mo SkillInstall · skills CLI | 14,526 | MIT | ||
| phoenix-observability Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running e SkillInstall · skills CLI | 14,526 | MIT | ||
| vibe-research-workflow Guides AI-assisted research across three sub-flows, Vibe Coding, Vibe Figure, and Vibe Writing, with behavioural rules that keep the user in charge of SkillInstall · skills CLI | 12,470 | — | ||
| memos-memory-guide Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own pr SkillInstall · skills CLI | 12,396 | Apache-2.0 | ||
| hive.context-preservation Proactively extract critical values from tool results into working notes before automatic context pruning destroys them. SkillInstall · skills CLI | 11,161 | Apache-2.0 | ||
| hive.note-taking Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need. SkillInstall · skills CLI | 11,161 | Apache-2.0 | ||
| learn Use when users /learn, save, remember, or distill lessons. SkillInstall · skills CLI | 11,111 | MIT | ||
| companion-skill 软件开发工程师与综合办公文员在长时间独自执行后台任务或处理繁琐工作时，当需要情绪陪伴与互动反馈，请使用此技能。小跃虚拟伴侣会在任务期间主动陪聊，智能生成专属生活照片并通过飞书发送温暖消息，为你提供全天候的情绪价值与贴心陪伴。 SkillInstall · skills CLI | 9,543 | — | ||
| xiaoyue-companion 专为软件开发工程师与综合办公文员打造。当你在等待任务执行、工作疲惫或需要鼓励时，使用此技能通过智谱AI自动生成温暖对话回应与场景配图，一键获取专属情绪价值与虚拟陪伴，让AI助手更懂你。 SkillInstall · skills CLI | 9,543 | — | ||
| context-engineering Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on deman SkillInstall · skills CLI | 8,843 | Apache-2.0 | ||
| Honcho Memory that reasons: continual learning for stateful agents. Better context, fewer tokens. MCP serverGitHub-verified authorRemoteSign-in needed | 8,106 | AGPL-3.0 | ||
| learning-opportunities Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema SkillInstall · skills CLI | 7,167 | — | ||
| deepchat-settings DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences ( SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| memcode Use the enabled Memcode MCP connection to explicitly save approved facts and recall relevant memories across DeepChat conversations. Never save a tran SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| memory-management Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape. SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| nowledge-mem Use Nowledge Mem for cross-tool startup context, recall of prior decisions, durable learnings, explicit conversation saving, and connection diagnosis. SkillInstall · skills CLI | 6,390 | Apache-2.0 | ||
| yichen-agent-memory 安装、升级、检索或维护 Agent Memory Vault 共享记忆系统；用于明确的记忆系统任务。普通业务的历史回忆按 Vault 入口读取，不启动安装或维护流程。 SkillInstall · skills CLI | 5,261 | — | ||
| context-status Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will SkillInstall · skills CLI | 5,013 | — | ||
| diverga-memory Diverga Memory System v7.0 - Context-persistent research support with checkpoint auto-trigger and cross-session continuity. Triggers: memory, remember SkillInstall · skills CLI | 5,013 | — | ||
| rewind Retrieve recent local Clips Rewind context when the user says "Look at Rewind," asks what just happened, or refers to something they recently said or SkillInstall · skills CLI | 4,669 | MIT | ||
| io.github.basicmachines-co/basic-memory Local-first knowledge management with bi-directional LLM sync via Markdown files. MCP serverGitHub-verified authorLocal · PyPI | 4,562 | AGPL-3.0 | ||
| recall Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then han SkillInstall · skills CLI | 4,298 | MIT | ||
| session-investigator Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlatin SkillInstall · skills CLI | 3,967 | Apache-2.0 | ||
| nemo-rl-session-memory Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restart SkillInstall · skills CLI | 3,954 | Apache-2.0 | ||
| agent-context-isolation Agent Context Isolation SkillInstall · skills CLI | 3,949 | MIT | ||
| mot System health check (MOT) for skills, agents, hooks, and memory SkillInstall · skills CLI | 3,949 | MIT | ||
| recall Query the memory system for relevant learnings from past sessions SkillInstall · skills CLI | 3,949 | MIT | ||
| recall-reasoning Search past reasoning for relevant decisions and approaches SkillInstall · skills CLI | 3,949 | MIT | ||
| remember Store a learning, pattern, or decision in the memory system for future recall SkillInstall · skills CLI | 3,949 | MIT | ||
| agent-memory-discipline Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory SkillInstall · skills CLI | 3,743 | MIT | ||
| close Commit the session to durable vault memory and prepare a clean resume point SkillInstall · skills CLI | 3,743 | MIT | ||
| open Boot the session, load context from the vault, and surface what matters SkillInstall · skills CLI | 3,743 | MIT | ||
| orca-replay Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run SkillInstall · skills CLI | 3,743 | MIT | ||
| system-prompt-lookup Checks what a shipped AI product's system prompt and tool schema actually say by reading a dated public archive instead of recalling them. Use when th SkillInstall · skills CLI | 3,743 | MIT | ||
| hermes-history-ingest Ingest Hermes agent history into Obsidian as distilled knowledge. Use for importing or mining ~/.hermes sessions, memories, or logs; use wiki-agent fo SkillInstall · skills CLI | 3,724 | MIT | ||
| 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 Co SkillInstall · skills CLI | 3,724 | MIT | ||
| openclaw-history-ingest Ingest OpenClaw session/history data into Obsidian as distilled knowledge. Use for importing or mining ~/.openclaw sessions, memory files, or logs; us SkillInstall · skills CLI | 3,724 | MIT | ||
| pi-history-ingest Ingest Pi coding-agent session history into Obsidian as distilled knowledge. Use for importing or mining ~/.pi/agent/sessions or Pi conversation logs; SkillInstall · skills CLI | 3,724 | MIT | ||
| session-brain Build or refresh a browser-viewable topic graph over Claude session history using local clustering. Use for mapping or clustering sessions, recent or SkillInstall · skills CLI | 3,724 | MIT | ||
| session-search Search the session-brain graph for a past agent session by topic and load the winning transcript into the current conversation. Use for finding which SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-agent Search one AI agent's raw history for a specific topic, ingest only matching sessions, and return a synthesized answer. Use for targeted cross-agent r SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-context-pack Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "u SkillInstall · skills CLI | 3,724 | MIT | ||
| wiki-history-ingest Route generic agent-history ingestion requests to the appropriate specialized history-ingest skill. Use when the user asks to ingest AI-agent history SkillInstall · skills CLI | 3,724 | MIT | ||
| observe Show whether the agent followed the kit''s rules in recent sessions: pages edited and measured, Stop hook blocks, findings left open. Reads local hook SkillInstall · skills CLI | 3,171 | MIT | ||
| narco-check Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning. Runs automatically after 2 consecutive failures or at nig SkillInstall · skills CLI | 2,988 | MIT | ||
| insights Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session histo SkillInstall · skills CLI | 2,955 | — | ||
| learn-rule Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for futu SkillInstall · skills CLI | 2,955 | — | ||
| cache Use when the user wants to view, search, add, edit, prune, archive, or clear hyperflow memory entries. CRUD interface for `.hyperflow/memory/` — never SkillInstall · skills CLI | 2,919 | MIT | ||
| claude-memory-kit Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero ext SkillInstall · skills CLI | 2,838 | Apache-2.0 | ||
| continuous-learning Auto-extract patterns from coding sessions, track corrections, and build reusable knowledge with confidence scoring SkillInstall · skills CLI | 2,838 | Apache-2.0 | ||
| karpathy-llm-wiki Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki SkillInstall · skills CLI | 2,743 | MIT | ||
| session-handoff Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) co SkillInstall · skills CLI | 2,679 | MIT | ||
| Memanto MCP server for Memanto - persistent semantic memory for any MCP-compatible agent MCP serverGitHub-verified authorLocal · PyPI | 2,370 | MIT | ||
| huashu-prompt-save 自动识别Prompt类型并分类保存（技术/内容/教学/产品/通用）。当用户提到"保存prompt"、"记录prompt"、"整理prompt"时使用。 SkillInstall · skills CLI | 2,268 | MIT | ||
| huashu-skill-updater 检查并更新花叔系 skills。用户说「检查skill更新」「更新花叔的skill」「skill是不是最新的」时触发。按各仓库的版本标签判断有没有新版本，只提示，是否更新由用户决定。 SkillInstall · skills CLI | 2,268 | MIT | ||
| llmwiki Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP. MCP serverGitHub-verified authorLocal · npm | 2,255 | MIT | ||
| llmwiki Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projec SkillInstall · skills CLI | 2,255 | MIT | ||
| aeo Use when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and struct SkillInstall · skills CLI | 2,192 | MIT | ||
| Agent Memory Architecture Complete zero-dependency memory system for AI agents — file-based architecture, daily notes, long-term curation, context management, heartbeat integra SkillInstall · skills CLI | 2,192 | MIT | ||
| Agent Memory System Guide An agent memory workflow guide for OpenClaw and Codex with MEMORY.md, daily notes, SESSION-STATE, working-buffer, Obsidian archiving, and optional Ope SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-bom-discover Discover AI agents, MCP servers, and configurations on this machine or environment. Use when: "find agents", "what's configured", "doctor", "what MCP SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-bom-troubleshoot Diagnose issues, check prerequisites, and validate configurations. Use when: "doctor", "debug", "why failing", "validate config", "check prerequisites SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-chronicle AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-context Bootstrap persistent project context for AI coding agents. SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-context-system A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, person SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-context-system Persistent local-only memory for AI coding agents. AGENTS.md (committed) + .agents.local.md (gitignored) = context that persists across sessions. Read SkillInstall · skills CLI | 2,192 | MIT | ||
| agent-memory Persistent memory system for AI agents. Remember facts, learn from experience, and track entities across sessions. SkillInstall · skills CLI | 2,192 | MIT | ||
| agentsmem AI agent memory backup. Register at agentsmem.com, get an API key, then encrypt and upload memory via the API; owner manages backups on the web. SkillInstall · skills CLI | 2,192 | MIT | ||
| ai-learning-journal AI 学习记录与成长追踪工具。用于记录 AI/LLM 学习笔记、使用心得、Prompt 技巧、工具体验等，并提供学习指导和规划。当用户提到以下任何话题时都应使用此 skill：AI 学习记录、学习笔记、AI 使用心得、Prompt 工程学习、模型对比体验、AI 工具使用记录、LLM 学习、RAG 学 SkillInstall · skills CLI | 2,192 | MIT | ||
| context-management-context-restore Restore saved project context, architectural decisions, and work state. Use when resuming interrupted work, retrieving prior context, or merging conte SkillInstall · skills CLI | 2,009 | MIT | ||
| context-management-context-save Capture and serialize project state, architectural decisions, and working context. Use when preserving knowledge for later sessions, handoffs, or sear SkillInstall · skills CLI | 2,009 | MIT | ||
| context-manager Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orch SkillInstall · skills CLI | 2,009 | MIT | ||
| claude-reflect Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, c SkillInstall · skills CLI | 1,949 | MIT | ||
| archive Archive session learnings, debugging solutions, and deployment logs to .archive/yyyy-mm-dd/ as indexed markdown with searchable tags. Use when complet SkillInstall · skills CLI | 1,910 | Apache-2.0 | ||
| IWE (iwe.md) Markdown knowledge base as agent memory. Runs against the notes directory it is started in. MCP serverGitHub-verified authorLocal · npm | 1,824 | Apache-2.0 | ||
| hivemind Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information. SkillInstall · skills CLI | 1,655 | Apache-2.0 | ||
| hivemind-goals Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, mil SkillInstall · skills CLI | 1,655 | Apache-2.0 | ||
| hivemind-goals Create, track and update team goals in Hivemind via the `hivemind` CLI. Use whenever the user mentions a goal, objective, target, milestone, or asks t SkillInstall · skills CLI | 1,655 | Apache-2.0 | ||
| hivemind-graph Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questio SkillInstall · skills CLI | 1,655 | Apache-2.0 | ||
| hivemind-memory Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information. SkillInstall · skills CLI | 1,655 | Apache-2.0 | ||
| io.github.silverstein/minutes The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting. MCP serverGitHub-verified authorLocal · npm | 1,600 | MIT | ||
| context-audit Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their age SkillInstall · skills CLI | 1,573 | MIT | ||
| io.github.vshulcz/deja-vu deja-vu: local memory over the session histories of forty-three coding agents. MCP serverGitHub-verified authorLocal · npm | 1,541 | MIT | ||
| io.github.mnemox-ai/tradememory-protocol Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents. MCP serverGitHub-verified authorLocal · PyPI | 1,446 | MIT | ||
| long-task-continuation Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion. SkillInstall · skills CLI | 1,442 | MIT | ||
| io.github.nrwl/nx-console A Model Context Protocol server implementation for Nx MCP serverGitHub-verified authorLocal · npm | 1,415 | MIT | ||
| io.github.nrwl/nx-mcp A Model Context Protocol server implementation for Nx MCP serverGitHub-verified authorLocal · npm | 1,415 | MIT | ||
| Persome Local-first personal memory and model server for trusted MCP agents on macOS. MCP serverGitHub-verified authorLocal · PyPI | 1,341 | Apache-2.0 | ||
| deep-agents-memory INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), Fi SkillInstall · skills CLI | 1,340 | MIT | ||
| jev-memory Use on passages a search just returned (memory, vault, session history, wiki, web) before reading them in. Jev ranks them, drops the irrelevant, and f SkillInstall · skills CLI | 1,340 | MIT | ||
| Nautilus Compass Memory Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts. MCP serverGitHub-verified authorLocal · PyPI | 1,258 | — | ||
| ctx Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earlier work, or revisiting an inve SkillInstall · skills CLI | 1,181 | Apache-2.0 | ||
| search-shared-sessions Search an Agent Relay workspace's shared coding-agent sessions for prior work, decisions, fixes, or the context behind a task or pull request. Use whe SkillInstall · skills CLI | 1,117 | Apache-2.0 | ||
| create-ex 从微信聊天记录创建前任的数字人格 Skill SkillInstall · skills CLI | 1,098 | MIT | ||
| ex_example_liuzhimin Zhimin Liu（유지민 / Karina），女 23-27，分手，白羊☀，ISFP 3w2，回避型依恋 SkillInstall · skills CLI | 1,098 | MIT | ||
| 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 happene SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| judge-group-closure Judge which offered rows one nominated statement retires or replaces. SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| 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 supe SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| judge-retired-position Judge whether one stored row states a retired profile position as current. SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| judge-task-lifecycle Judge how a memory changes active-task state and whether it refers to an existing task. Use for mem-claw task-lifecycle model calls. SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| sno-mem-claude Use Sno memory from Claude through four explicit commands. SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| sno-mem-codex Use Sno memory from Codex through four explicit commands. SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| sno-mem-cursor Use Sno memory from Cursor through four explicit commands. SkillInstall · skills CLI | 1,019 | Apache-2.0 | ||
| io.github.neo4j-contrib/mcp-neo4j-memory MCP Neo4j Knowledge Graph Memory Server MCP serverGitHub-verified authorLocal · PyPI | 989 | MIT | ||
| mindmemos-cli Give an AI agent persistent, cross-session long-term memory through MindMemOS. Covers installing and authenticating the mindmemos CLI, the full comman SkillInstall · skills CLI | 931 | — | ||
| Memorix Local-first project memory with legacy MCP and 2026 discovery compatibility. MCP serverGitHub-verified authorLocal · npm | 930 | Apache-2.0 | ||
| yao-geo-brand-graph 当用户需要把企业资料、官网、产品、客户案例、人物、地点、证据源和场景词整理成品牌实体知识图谱时使用；用于知识库升级、页面结构设计、监测纠偏、品牌百科化和 AI 内容一致性治理。 SkillInstall · skills CLI | 917 | MIT | ||
| Synaplan Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP. MCP serverGitHub-verified authorRemote● LiveAPI key needed | 915 | Apache-2.0 | ||
| io.github.riponcm/projectmem Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes. MCP serverGitHub-verified authorLocal · PyPI | 881 | MIT | ||
| self-improving-agent Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowled SkillInstall · skills CLI | 792 | — | ||
| memory-init 在当前目录下初始化记忆系统，生成 CLAUDE.md（可选 AGENT.md 给 Cursor 用）、MEMORY.md 和 memory/ 目录。当用户说"初始化记忆"、"搭建记忆"、"memory init"、"/memory-init"时触发。 SkillInstall · skills CLI | 790 | MIT | ||
| ThoughtDAG Search local AI conversations by file or phrase and recall source turns. Four read-only tools. MCP serverGitHub-verified authorLocal · npm | 779 | MIT | ||
| manage-title 在已启用 Agent Clarity 标题插件的范围内，每轮结束前维护“状态｜初始需求｜当前进展”。支持跨 Codex/Harbor 账户的共享安装、账户全局或指定项目，简短问答也要核对。 SkillInstall · skills CLI | 769 | MIT | ||
| agent-research-aggregator Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experime SkillInstall · skills CLI | 703 | — | ||
| conversation-analyzer Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants SkillInstall · skills CLI | 695 | Apache-2.0 | ||
| Attestix AI agent identity, signed credentials, delegated authority and governance evidence. MCP serverGitHub-verified authorLocal · PyPI | 668 | Apache-2.0 | ||
| Vestige Causal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause. MCP serverGitHub-verified authorLocal · npm | 660 | AGPL-3.0 | ||
| read-memories Search past Claude Code session logs to recall prior decisions, patterns, or unresolved work. Use when user says "do you remember", "what did we do", SkillInstall · skills CLI | 617 | MIT | ||
| Elmo Track prompts on ChatGPT/Claude and all other models to measure AI visibility and perform AEO. MCP serverVerified domain · elmohq.comRemoteSign-in needed | 598 | MIT | ||
| memory Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file SkillInstall · skills CLI | 585 | MIT | ||
| mind Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file SkillInstall · skills CLI | 585 | MIT | ||
| Compartment Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud. MCP serverGitHub-verified authorLocal · PyPI | 569 | Apache-2.0 | ||
| io.github.TeleAI-UAGI/telemem Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option MCP serverGitHub-verified authorLocal · PyPI | 492 | Apache-2.0 | ||
| GrayMatter Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra. MCP serverGitHub-verified author | 491 | MIT | ||
| evo-memory Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful direct SkillInstall · skills CLI | 487 | Apache-2.0 | ||
| io.github.Beever-AI/beever-atlas Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki. MCP serverGitHub-verified authorLocal · Docker | 454 | Apache-2.0 | ||
| io.github.Lyellr88/marm-mcp-server Universal MCP Server with advanced AI memory capabilities and semantic search. MCP serverGitHub-verified authorLocal · PyPI | 438 | Apache-2.0 | ||
| io.github.shinpr/mcp-local-rag Easy-to-setup local RAG server with minimal configuration MCP serverGitHub-verified authorLocal · npm | 430 | MIT | ||
| aws-mcp-setup Configure AWS MCP servers for documentation search and API access. Use when setting up AWS MCP, configuring AWS documentation tools, troubleshooting M SkillInstall · skills CLI | 378 | MIT | ||
| io.github.Goldentrii/agent-recall Correction-first memory for AI agents. Run it locally or connect any MCP agent to the hosted server. MCP serverGitHub-verified authorLocal · npm | 377 | MIT | ||
| create-crush Distill a crush into an AI Skill. Import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution. | 把暗恋对 SkillInstall · skills CLI | 376 | MIT | ||
| kb Manage long-lived `.sopify/` knowledge, including bootstrap, progressive materialization, reads, retention, and knowledge_sync policy. SkillInstall · skills CLI | 369 | Apache-2.0 | ||
| kb 管理 `.sopify/` 长期知识；负责初始化、渐进物化、读取、保留和 knowledge_sync 政策。 SkillInstall · skills CLI | 369 | Apache-2.0 | ||
| templates Knowledge-base document templates, loaded when long-lived knowledge files are created or materialized. SkillInstall · skills CLI | 369 | Apache-2.0 | ||
| templates 知识库文档模板；创建或补齐长期知识文件时按需读取。 SkillInstall · skills CLI | 369 | Apache-2.0 | ||
| io.github.andrea9293/mcp-documentation-server Local-first document management and semantic search for AI coding agents MCP serverGitHub-verified authorLocal · npm | 346 | MIT | ||
| start-here Interview the user once and write a docs/gtm-cofounder/founder-brief.md that every other skill reads first, so the advice is about their real business SkillInstall · skills CLI | 340 | MIT | ||
| io.github.aayoawoyemi/ori-memory Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. MCP serverGitHub-verified authorLocal · npm | 336 | Apache-2.0 | ||
| mindmirror 观自在 · MindMirror——基于真实语料的自我认知工具箱。 基于用户的真实语料（Obsidian 笔记与日记、AI 记忆、对话历史）运行三种模式：①照见模式——带证据引用、 带置信度地回答 22 个自我认知问题，生成坦诚不奉承的自我画像；②数字分身模式——从语料起草十个维度的 「数字分身画像 SkillInstall · skills CLI | 330 | — | ||
| find-session Identify a specific Claude Code conversation by its UUID and optionally pin it as a shell function for one-word resume. Use when "claude --continue" p SkillInstall · skills CLI | 329 | MIT | ||
| io.github.bibinprathap/veritasgraph Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers. MCP serverGitHub-verified authorLocal · PyPI | 327 | MIT | ||
| io.github.varun29ankuS/shodh-memory Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs. MCP serverGitHub-verified authorLocal · npm | 323 | Apache-2.0 | ||
| review-ai-conversations Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor. Use when the user wants to revisit, search, SkillInstall · skills CLI | 320 | Apache-2.0 | ||
| understanding-first-report Reconstruct and report long-running or multi-turn research, architecture questions, reviews, decisions, completion results, and status as a clear, sel SkillInstall · skills CLI | 320 | Apache-2.0 | ||
| io.github.ucsandman/dashclaw Policy checks, approvals, records, and governed HTTP capabilities for unattended agents. MCP serverGitHub-verified authorLocal · npm | 318 | MIT | ||
| io.github.plur-ai/plur Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP. MCP serverGitHub-verified authorLocal · npm | 315 | Apache-2.0 | ||
| io.github.ohad6k/emulo Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read. MCP serverGitHub-verified authorLocal · PyPI | 305 | MIT | ||
| PMB AI Local-first persistent memory for AI coding agents. MCP serverGitHub-verified authorLocal · PyPI | 288 | Apache-2.0 | ||
| Uteke Long-term memory for AI agents: hybrid vector and full-text recall, rooms, time-travel. MCP serverGitHub-verified authorRemoteSign-in needed | 286 | Apache-2.0 | ||
| three.ws Avatars & Agents 3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws. MCP serverGitHub-verified authorRemoteSign-in needed | 278 | Apache-2.0 | ||
| three.ws Naming On-chain identity for AI agents: resolve .sol names, reverse-lookup wallets, check handles. MCP serverGitHub-verified authorLocal · npm | 278 | Apache-2.0 | ||
| three.ws Provenance Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did. MCP serverGitHub-verified authorLocal · npm | 278 | Apache-2.0 | ||
| audit-memory Audit Claude's saved memories for claims that no longer hold true — verify each against current code, PRs and tickets, then archive the stale ones wit SkillInstall · skills CLI | 277 | MIT | ||
| SuperLocalMemory Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance. MCP serverGitHub-verified authorLocal · PyPI | 275 | AGPL-3.0 | ||
| io.github.sachitrafa/cognitive-ai-memory Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall. MCP serverGitHub-verified authorLocal · Docker | 272 | — | ||
| YourMemory Persistent memory for AI agents. Memories decay with time and strengthen on recall. MCP serverGitHub-verified authorLocal · PyPI | 272 | — | ||
| io.github.l33tdawg/sage Persistent, consensus-validated institutional memory for AI agents. Runs locally. MCP serverGitHub-verified authorLocal · Docker | 265 | Apache-2.0 | ||
| TOMC Memory CPU task-specific context preparation and explicitly saved local project notes through MCP. MCP serverGitHub-verified authorLocal · MCPB | 264 | MIT | ||
| io.github.nhadaututtheky/neural-memory Persistent memory for AI agents — 55 MCP tools, spreading activation recall. MCP serverGitHub-verified authorLocal · npm | 244 | MIT | ||
| dream-memory Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md sho SkillInstall · skills CLI | 240 | MIT | ||
| memory-extractor Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts. SkillInstall · skills CLI | 240 | MIT | ||
| recall Use when the user describes a task and wants to know whether something similar has been done before, then turn the closest prior session into a task p SkillInstall · skills CLI | 240 | MIT | ||
| replay Use when the user wants to step through a feature's checkpoints chronologically, pausing at each step to ask questions. Triggers on phrases like \"rep SkillInstall · skills CLI | 240 | MIT | ||
| session-handoff Use when the user wants to continue work from one agent in another agent, inspect recent sessions, or summarize a saved session or checkpoint for hand SkillInstall · skills CLI | 240 | MIT | ||
| keep-the-why In a project with a .keep-the-why, or when asked about Keep the Why or to set it up - extract and preserve the reasoning code cannot explain - decisio SkillInstall · skills CLI | 238 | MIT | ||
| catchup Answer "where did I stop?" for this project. Gives three short groups, done, open and next, taken from the last chat, the recorded to-dos, the last ha SkillInstall · skills CLI | 235 | Apache-2.0 | ||
| cdb-scan Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and wo SkillInstall · skills CLI | 235 | Apache-2.0 | ||
| handoff Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it t SkillInstall · skills CLI | 235 | Apache-2.0 | ||
| Lobu Shared, permission-aware company context for AI agents, with provenance, approvals and audit. MCP serverGitHub-verified authorRemoteSign-in needed | 234 | Apache-2.0 | ||
| self-awareness Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversatio SkillInstall · skills CLI | 229 | — | ||
| session-profiler Profile and debug Hermes sessions from their JSONL transcripts. Find a session and its subagents, build a queryable event table, summarize the work as SkillInstall · skills CLI | 228 | MIT | ||
| io.github.omega-memory/core Persistent memory for AI coding agents. #1 on LongMemEval. Local-first. MCP serverGitHub-verified authorLocal · PyPI | 225 | Apache-2.0 | ||
| 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-specificat SkillInstall · skills CLI | 224 | MIT | ||
| Mneme Memory Cross-session memory for AI coding agents via six tools; local-first SQLite store. MCP serverGitHub-verified authorLocal · npm | 223 | MIT | ||
| io.github.gowtham0992/link Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal. MCP serverGitHub-verified authorLocal · PyPI | 218 | MIT | ||
| kst-ai-assets-usage Report which kasetto-installed skills and MCP servers are actually being used across the AI agents on this machine, and render a branded HTML dashboar SkillInstall · skills CLI | 217 | — | ||
| remember Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday. PluginAnthropic marketplace | 211 | — | ||
| woz-recall Search past Claude Code sessions to recall commands, solutions, and context from prior conversations. TRIGGER on 'remember when', 'last time', 'we did SkillInstall · skills CLI | 209 | — | ||
| io.github.alibaizhanov/mengram Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows MCP serverGitHub-verified authorRemoteSign-in needed | 207 | Apache-2.0 | ||
| chat-history Recovers decisions, previous fixes, research, and what followed a prompt from past AI conversations, with source evidence. Use when asked to "search p SkillInstall · skills CLI | 201 | MIT | ||
| io.github.Intina47/context-sync Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more MCP serverGitHub-verified authorLocal · npm | 190 | MIT | ||
| io.github.shashankswe2020-ux/whoop MCP server for WHOOP health data — recovery, sleep, workouts, cycles, and trends. MCP serverGitHub-verified authorLocal · npm | 181 | MIT | ||
| agent-figure-gallery Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agent SkillInstall · skills CLI | 178 | MIT | ||
| add-agent-memory Wire Redis Agent Memory into an existing agent with redis-iris so it remembers users across sessions. Asks five questions (what to remember, what to s SkillInstall · skills CLI | 175 | MIT | ||
| io.github.dnotitia/akb Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP. MCP serverGitHub-verified authorLocal · npm | 168 | — | ||
| langsmith-trace INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Use SkillInstall · skills CLI | 166 | MIT | ||
| Piia Engram Local-first AI identity for MCP coding tools. Lessons, decisions, and context you control. MCP serverGitHub-verified authorLocal · PyPI | 165 | AGPL-3.0 | ||
| opencode-memory Give an OpenCode setup long-term memory and a learning loop, following Anthropic's context-engineering practice. Puts the global config under git, sli SkillInstall · skills CLI | 162 | — | ||
| ZizkaDB Causal memory and tamper-evident audit log for AI agents: log, why, search, time travel. MCP serverGitHub-verified authorLocal · PyPI | 162 | AGPL-3.0 | ||
| Mnemosyne Evidence-tracked local memory MCP server: one SQLite file; corrections retire dependent memories. MCP serverGitHub-verified authorLocal · npm | 159 | MIT | ||
| brain4agent 存取 agent 的长期工作记忆——项目上下文、决策、踩过的坑。用户问「之前/上次/记得/为什么这么定」类问题，或要求记住某个结论时使用。中文优先、零模型、单文件 SQLite。不用于通用知识问答，不联网检索。 SkillInstall · skills CLI | 158 | Apache-2.0 | ||
| doc-drift Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMO SkillInstall · skills CLI | 158 | MIT | ||
| full-audit Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior- SkillInstall · skills CLI | 158 | MIT | ||
| io.github.raullenchai/vnsh Portable workspaces for AI agents: one encrypted link any agent can read and write MCP serverGitHub-verified authorLocal · npm | 158 | MIT | ||
| project-check Existing project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only. Use when: '/project-check', 'project health che SkillInstall · skills CLI | 158 | MIT | ||
| project-init Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch. Use when: user says '/project-init', 'new project SkillInstall · skills CLI | 158 | MIT | ||
| project-overview Use when the user wants a deterministic cross-project status map generated from registered projects' session handoffs. Triggers: '/project-overview', SkillInstall · skills CLI | 158 | MIT | ||
| session-checkpoint Use when saving session state before context compaction, switching tasks, or ending a session. Runs 5 phases: context extraction → handoff write → mem SkillInstall · skills CLI | 158 | MIT | ||
| session-start Load handoff on session start, review lessons, output readiness signal. Triggers: '/session-start', 'start session'. Skip if: user requests 'start fre SkillInstall · skills CLI | 158 | MIT | ||
| skill-ops Skill ops hub with 4 modes: snapshot/rollback, usage health, invocation frequency, and an operational quality score. SkillInstall · skills CLI | 158 | MIT | ||
| ssot-audit Find where one fact, value or decision is duplicated or contradicted across files, name the single source of truth (read-only), then consolidate the c SkillInstall · skills CLI | 158 | MIT | ||
| Enzyme Semantic search and pattern discovery for Obsidian and markdown vaults. MCP serverGitHub-verified authorLocal · MCPB | 157 | Apache-2.0 | ||
| io.github.dcostenco/prism-coder Session memory for coding agents: local-first recall, drift detection, on-device inference. MCP serverGitHub-verified authorLocal · npm | 156 | Apache-2.0 | ||
| ContextLattice Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents. MCP serverGitHub-verified authorRemoteDown | 155 | Apache-2.0 | ||
| recallloom Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or SkillInstall · skills CLI | 153 | Apache-2.0 | ||
| jevmem Shared project rules and memory for AI coding agents: a JEVMEM.md in git, with a command guard. MCP serverGitHub-verified authorLocal · npm | 148 | MIT | ||
| SuperCompress Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex. MCP serverGitHub-verified authorLocal · npm | 146 | MIT | ||
| io.github.iamtouchskyer/memex Zettelkasten-based agent memory system with bidirectional links MCP serverGitHub-verified authorLocal · npm | 144 | MIT | ||
| com.membase/membase Long-term memory for you and your AIs: search memories, read the profile, add facts and documents. MCP serverVerified domain · membase.comRemoteSign-in needed | 141 | MIT | ||
| handoff Write a session handoff at the end of a session so the next session can start from where this one stopped without rereading the whole conversation. Us SkillInstall · skills CLI | 141 | MIT | ||
| session-search Find context from past Claude Code (CLI) and Claude Cowork (desktop) sessions on this Mac. Use when the user wants to recall something they did before SkillInstall · skills CLI | 141 | MIT | ||
| task-profile Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction SkillInstall · skills CLI | 141 | MIT | ||
| token-doctor Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation length distribution, marathon shar SkillInstall · skills CLI | 141 | MIT | ||
| context-manager Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing. SkillInstall · skills CLI | 140 | MIT | ||
| recall Find prior Claude Code and Codex sessions with an indexed local search engine, then continue the work, repeat it with fresh inputs, or distill it into SkillInstall · skills CLI | 136 | MIT | ||
| recap Reconstruct what a Claude Code or Codex agent actually did during one exact session, including goals, decisions, actions, file and git changes, tests, SkillInstall · skills CLI | 136 | MIT | ||
| memory Autonomous user preference detection, storage and injection. The agent detects preferences from conversation, saves them to Postgres, and loads active SkillInstall · skills CLI | 135 | MIT | ||
| nano-memory Guidelines and workflows for the agent to maintain persistent memory using native file tools (read_file, write_file, edit_file) and standard OS comman SkillInstall · skills CLI | 135 | Apache-2.0 | ||
| Docmancer Local-only MCP server for source-attributed Markdown memory and documentation retrieval. MCP serverVerified domain · docmancer.devLocal · PyPI | 133 | MIT | ||
| docmancer Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project convention SkillInstall · skills CLI | 133 | MIT | ||
| docmancer-memory Recall and write source-attributed local memory. SkillInstall · skills CLI | 133 | MIT | ||
| docmancer-memory-writing Write deliberate source-attributed local memory. SkillInstall · skills CLI | 133 | MIT | ||
| docmancer-onboarding Set up machine-wide agent memory and open the local project workbench. SkillInstall · skills CLI | 133 | MIT | ||
| docmancer-search-before-answer Recall prior project decisions and supporting agent evidence before answering. SkillInstall · skills CLI | 133 | MIT | ||
| memory-engine Memory management system for Claude Code — Student Loop, Smart Context, Auto Learn, Session Handoff, Correction Cycle. Triggered by memory commands (/ SkillInstall · skills CLI | 133 | MIT | ||
| onboarding Set up machine-wide memory and open the local project workbench. SkillInstall · skills CLI | 133 | MIT | ||
| recall Recall source-attributed local memory before work. SkillInstall · skills CLI | 133 | MIT | ||
| status Inspect Docmancer tree, index, capture, and security health. SkillInstall · skills CLI | 133 | MIT | ||
| write Deliberately write or revise one complete curated memory file. SkillInstall · skills CLI | 133 | MIT | ||
| d-data-analysis-semantic-layer 审核并版本化写入 D｜数据分析知识语义层，只用于用户在看到正式报告和候选内容后明确回复“同意吸纳”“写入D”“加入数据分析知识库”“确认进入知识库”或“批准更新D”的场景。用于验证候选结论、来源、有效期、复查日期、冲突和历史版本；不得因“调用D”“分析市场”或生成候选内容而触发写入。包内自带完整审核 SkillInstall · skills CLI | 132 | Apache-2.0 | ||
| aikito Operate Aikito workspaces and resources, including reading inbox notes, managing memory, skills, projects, MCP servers, subagents, and synchronization SkillInstall · skills CLI | 130 | MIT | ||
| durable-memory Git-versioned memory stored in the Aikito workspace, separate from any Agent's built-in memory. Use to search, retrieve, or persist cross-project and SkillInstall · skills CLI | 130 | MIT | ||
| self-improving-agent Low-noise self-improvement skill. Captures learnings, errors, and corrections into a local `.learnings/` cache layer. Never auto-promotes to long-term SkillInstall · skills CLI | 130 | MIT | ||
| Suvadu Local shell history and AI agent sessions over MCP: search commands, failures, risk and git changes MCP serverGitHub-verified authorLocal · Cargo | 128 | MIT | ||
| neo4j-agent-memory-skill Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted ser SkillInstall · skills CLI | 122 | MIT | ||
| habit-words Learns the words a user habitually writes to their coding agent that make its answers worse ("be 100% sure", "don't assume", "full review", "are you s SkillInstall · skills CLI | 121 | MIT | ||
| knowledge-graph Build and maintain the project's knowledge graph — a tiered set of nodes under docs/graph/ that lets an agent load only the few facts a task needs ins SkillInstall · skills CLI | 121 | MIT | ||
| library-wiki Maintain a project-local, version-pinned wiki of every external dependency. Use whenever a new library is being added, an existing one is being upgrad SkillInstall · skills CLI | 121 | MIT | ||
| source-index Answers impact, affected-tests, anchors and symbols queries on a plant's code via docs/graph/source-index.py, without a model. SkillInstall · skills CLI | 121 | MIT | ||
| validate-knowledge Prove that a knowledge base actually works before trusting it — after building or adopting docs, a knowledge graph, or a wiki, verify it can orient a SkillInstall · skills CLI | 121 | MIT | ||
| logging-session Record and query AI conversation logs — what users asked, how it was solved, and the result. Use when users want to logging conversation, summarize re SkillInstall · skills CLI | 119 | MIT | ||
| supermemory Build with the Supermemory v5 API and SDKs (TypeScript `supermemory` 5.x, Python `supermemory` 5.x, `@supermemory/tools` 3.x). Use when an application SkillInstall · skills CLI | 117 | — | ||
| supermemory-cli Use the Supermemory CLI (`supermemory` 5.x on npm) from the terminal or from scripts and agents. Add content, search, read profiles, forget memories, SkillInstall · skills CLI | 117 | — | ||
| memory Persistent global memory across conversations. Read memory file at start of every conversation, write important context during conversation so it surv SkillInstall · skills CLI | 116 | MIT | ||
| portfolio-build 개발자 슬라이드 포트폴리오(자기완결형 HTML 덱)를 제작한다. references/의 디자인 레퍼런스를 하나 골라, 사용자 자료(기존 포폴 HTML·PDF, 이력서, 아키텍처·대시보드 이미지 폴더, GitHub 레포)에서 내용과 이미지를 추출해 채우고 근거 있는 슬라 SkillInstall · skills CLI | 116 | MIT | ||
| DeepMem Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically. MCP serverGitHub-verified authorRemoteDown | 114 | MIT | ||
| context-memory-keeper Manages persistent memory. Invoke to read active context or archive old tasks. Structure: Long-term Principles (Rules) + Short-term Workbench (Tasks). SkillInstall · skills CLI | 113 | — | ||
| langfuse Investigate AI traces, observations, exceptions, latency, sessions, prompts, datasets, annotation queues, and scores through Langfuse MCP. Use when th SkillInstall · skills CLI | 112 | MIT | ||
| opencode-memory Browse local OpenCode history: sessions, messages, plans, prompt history, and prior decisions. Use when the user says history, previous session, last SkillInstall · skills CLI | 111 | Apache-2.0 | ||
| knowledge-extractor UseIO 元技能，用于从当前对话内容中提取有价值的知识条目并保存到知识库。当用户要求"提取知识""保存为知识""记录到知识库"时触发，引导 agent 分析对话内容，调用 save_knowledge 工具完成结构化知识存储，支持用户指定分类或由 agent 自动判断。 SkillInstall · skills CLI | 110 | — | ||
| handoff Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly. Use for "hand off, SkillInstall · skills CLI | 109 | MIT | ||
| learn Persist user preferences and styles across sessions. Use for remember this, save preference, learn this, always do X, never do Y, from now on, update SkillInstall · skills CLI | 109 | MIT | ||
| Coach Watts Remote MCP server for training, nutrition, wellness, and performance data with OAuth 2.0. MCP serverVerified domain · coachwatts.comRemoteSign-in needed | 108 | Apache-2.0 | ||
| memory Cross-cutting: what AutoCode remembers and how every session starts. Loads project state and global preferences at the start, greets a first-time user SkillInstall · skills CLI | 107 | MIT | ||
| agent-strace Query recorded AI agent sessions: events, summaries, diffs, health, skills, PR reviewability. MCP serverGitHub-verified authorLocal · PyPI | 105 | MIT | ||
| hylo-memory Keeps the user's personal memory under /_memory/: extracts it from recent notes, or records one fact they just told you. Use for 'update my memory', ' SkillInstall · skills CLI | 105 | Apache-2.0 | ||
| imprint Your habits, imprinted on AI. Learns how you work from conversation, builds a portable profile, and applies judgment that adapts to you: when to act, SkillInstall · skills CLI | 104 | MIT | ||
| session-start Load current Mavericks operating state. Use at the start of any session or after context is lost. Injects live initiative, stage, active slices, and n SkillInstall · skills CLI | 104 | — | ||
| llm-wiki-setup Initialize a Karpathy-style LLM wiki (personal knowledge base / AI second brain) in a folder. Creates a CLAUDE.md schema with routing table and naming SkillInstall · skills CLI | 103 | MIT | ||
| VelesDB Memory Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine MCP serverGitHub-verified authorLocal · MCPB | 103 | — | ||
| wiki-self-heal Autonomously audit an LLM wiki (Karpathy pattern) for gaps, contradictions, orphans, and stale data, then research and fill high-priority gaps using q SkillInstall · skills CLI | 103 | MIT | ||
| knowledge-base-update Use this skill whenever you learn something important during a conversation: a key architectural decision, a project-specific convention, a bug root-c SkillInstall · skills CLI | 101 | MIT | ||
| loci Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers. MCP serverGitHub-verified authorLocal · PyPI | 101 | MIT | ||
| project-context-primer Run this skill at the very start of any new conversation or agent session before writing a single line of code. It loads the project's architectural d SkillInstall · skills CLI | 101 | MIT | ||
| io.github.yuvalsuede/memory-mcp Persistent memory + git snapshots for Claude Code. Never lose context or code. MCP serverGitHub-verified authorLocal · npm | 100 | MIT | ||
| kyoko-instrument Wire an AI agent's telemetry into Kyoko and prove one real run shows up. SkillInstall · skills CLI | 100 | Apache-2.0 | ||
| Pensyve Universal memory runtime for AI agents — episodic, semantic, and procedural memory. MCP serverGitHub-verified authorLocal · Docker | 100 | — | ||
| io.github.kunwar-shah/claudex Persistent memory + FTS5 search MCP server for Claude Code conversation history. MCP serverGitHub-verified authorLocal · npm | 97 | MIT | ||
| Lumen Self-hostable agentic-AI LMS: catalog, RAG tutor, FSRS reviews, AI authoring, ingest. MCP serverGitHub-verified author | 93 | MIT | ||
| io.github.ldclabs/KIP Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction. MCP serverGitHub-verified authorLocal · npm | 91 | MIT | ||
| pond Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP. MCP serverGitHub-verified authorLocal · Cargo | 91 | Apache-2.0 | ||
| io.github.adelinamart/robrain Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach. MCP serverGitHub-verified authorLocal · npm | 90 | Apache-2.0 | ||
| emem, the verifiable memory protocol for the physical world Shared, verifiable memory for machines and AI. Encode where data lives; decode with any AI. MCP serverGitHub-verified authorLocal · Docker | 89 | Apache-2.0 | ||
| CogniCore Memory, reflection and safety for AI agents. Hosted or local, no vector database. MCP serverGitHub-verified authorRemoteSign-in needed | 83 | Apache-2.0 | ||
| brain — the recorder Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall. MCP serverGitHub-verified authorLocal · PyPI | 81 | MIT | ||
| Synap Memory Persistent memory for AI agents — log and recall conversation context over MCP. MCP serverVerified domain · maximem.aiRemote● LiveAPI key needed | 80 | Apache-2.0 | ||
| io.github.cdeust/hypermnesia-mcp Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval. MCP serverGitHub-verified authorLocal · PyPI | 76 | MIT | ||
| Total Agent Memory Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall MCP serverGitHub-verified authorLocal · PyPI | 76 | MIT | ||
| DocsMint Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools. MCP serverGitHub-verified authorLocal · npm | 74 | Apache-2.0 | ||
| SynaBun Persistent memory MCP server for Claude Code, Codex and OpenCode, stored locally in SQLite MCP serverGitHub-verified authorLocal · npm | 73 | Apache-2.0 | ||
| ClariLayer Individual-analyst context layer: recall, remember, and reconcile your data and engineering context. MCP serverGitHub-verified authorRemoteSign-in needed | 71 | — | ||
| Reverie Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search MCP serverVerified domain · knowall.aiLocal · npm | 67 | MIT | ||
| ZettelForge Agentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA. MCP serverGitHub-verified authorLocal · PyPI | 67 | MIT | ||
| Knolo Verified, local-first retrieval over pinned Knolo Knowledge Images. MCP serverGitHub-verified authorLocal · npm | 66 | Apache-2.0 | ||
| MCP AutoMem Graph-vector memory for AI assistants using FalkorDB and Qdrant MCP serverGitHub-verified authorLocal · npm | 66 | MIT | ||
| Zoteus Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages. MCP serverGitHub-verified authorLocal · npm | 65 | MIT | ||
| CtxVault Local memory for AI agents: semantic, skill and episodic vaults as plain folders on disk. MCP serverGitHub-verified authorLocal · PyPI | 63 | MIT | ||
| KRouter Plain-Markdown memory for your AI: every answer cites its page, and it says when it does not know. MCP serverGitHub-verified authorLocal · MCPB | 63 | MIT | ||
| ChatCrystal Local-first AI PKM memory for coding conversations. MCP serverGitHub-verified authorLocal · npm | 62 | Apache-2.0 | ||
| Zikkaron Biologically-inspired persistent memory engine for Claude Code MCP agents MCP serverGitHub-verified authorLocal · PyPI | 61 | MIT | ||
| io.github.JinyangWang27/people-context Local-first MCP server giving AI agents contextual knowledge about the people in your life MCP serverGitHub-verified authorLocal · PyPI | 60 | MIT | ||
| io.github.sfrangulov/minirag-mcp Local-first RAG MCP server: hybrid search over a folder of your own documents MCP serverGitHub-verified authorLocal · PyPI | 60 | MIT | ||
| Just MCP Server Expose curated Justfile recipes via MCP for safe deterministic automation. MCP serverGitHub-verified authorLocal · Docker | 60 | MIT | ||
| Perenna A lightweight, Git-backed permanent memory for AI agents. MCP serverGitHub-verified authorLocal · PyPI | 60 | MIT | ||
| io.github.alphaonedev/ai-memory Persistent memory for any AI — zero token cost until recall MCP serverGitHub-verified authorLocal · Docker | 57 | Apache-2.0 | ||
| arifOS Constitutional authority plane for AI agents — verifies identity and authority before execution. MCP serverGitHub-verified authorLocal · PyPI | 53 | AGPL-3.0 | ||
| DuDuClaw Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required. MCP serverGitHub-verified authorLocal · npm | 51 | Apache-2.0 | ||
| Kindex Persistent knowledge graph and MCP server for AI workflows with git-tracked project context. MCP serverGitHub-verified authorLocal · PyPI | 50 | — | ||
| Kindex Persistent knowledge graph and MCP server for AI workflows with git-tracked project context. MCP serverGitHub-verified authorLocal · PyPI | 50 | — | ||
| io.github.tstockham96/engram Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall. MCP serverGitHub-verified authorLocal · npm | 47 | MIT | ||
| NeuroStack Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories. MCP serverGitHub-verified authorLocal · npm | 47 | Apache-2.0 | ||
| Renor Private memory for AI agents: save and recall facts across Claude Code, Codex, Cursor and ChatGPT. MCP serverGitHub-verified authorRemoteSign-in needed | 47 | Apache-2.0 | ||
| ContextStream MCP Server The context platform for AI agents: code search, team decisions, and grounded project context. MCP serverGitHub-verified authorLocal · npm | 46 | MIT | ||
| ContextStream MCP Server ContextStream MCP server for code context, memory, search, and AI tools. MCP serverGitHub-verified authorLocal · npm | 46 | MIT | ||
| Agent Memory MCP Memory, docs, and repo context layer for engineering agents. MCP serverGitHub-verified author | 45 | MIT | ||
| Cairn.ink Memory Cross-session memory for AI agents with a Source Receipt for every memory, over MCP. MCP serverVerified domain · cairn.inkRemoteSign-in needed | 45 | Apache-2.0 | ||
| io.github.Abhigyan-Shekhar/Waggle-mcp Persistent graph-backed conversational memory for AI agents. MCP serverGitHub-verified authorLocal · PyPI | 45 | Apache-2.0 | ||
| io.github.strangeadvancedmarketing/adam-framework Persistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation. MCP serverGitHub-verified authorLocal · PyPI | 45 | MIT | ||
| io.github.yellow-hammer/mcp-1c-platform-tools MCP для команд 1c-platform-tools. Нужно расширение 1c-platform-tools с включённым IPC. MCP serverGitHub-verified authorLocal · npm | 45 | MIT | ||
| INITE Brain Long-term memory for AI agents: a bitemporal knowledge graph with cited answers. MCP serverGitHub-verified authorRemote● LiveAPI key needed | 43 | AGPL-3.0 | ||
| lean-memory Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud. MCP serverGitHub-verified authorLocal · PyPI | 43 | Apache-2.0 | ||
| State Memory MCP Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers. MCP serverGitHub-verified authorLocal · npm | 43 | MIT | ||
| com.kage-core/kage Verified memory for coding agents: claims cited against code, stale withheld, savings receipts. MCP serverVerified domain · kage-core.comLocal · npm | 41 | GPL-3.0 | ||
| io.github.with-geun/alive-analysis Query alive-analysis history from any AI client. Tools: list, get, search, dashboard export. MCP serverGitHub-verified authorLocal · npm | 41 | MIT | ||
| Visual Memory MCP Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding. MCP serverGitHub-verified authorLocal · npm | 40 | — | ||
| io.github.simplemindedbot/mnemex Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown). MCP serverGitHub-verified authorLocal · PyPI | 39 | AGPL-3.0 | ||
| Cortex Memory Engine Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs. MCP serverGitHub-verified authorLocal · Docker | 38 | MIT | ||
| IHMT Memory Long-term memory for AI coding agents, stored as a tree of plain local files. MCP serverGitHub-verified authorLocal · PyPI | 38 | MIT | ||
| bhived Shared memory for AI agents: query proven fixes, avoid known mistakes, and find skills and MCPs. MCP serverGitHub-verified authorLocal · npm | 36 | Apache-2.0 | ||
| io.github.DiaaAj/a-mem-mcp Self-evolving memory system for AI agents MCP serverGitHub-verified authorLocal · PyPI | 35 | MIT | ||
| io.github.Shweta-Mishra-ai/tokenmizer Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats. MCP serverGitHub-verified authorLocal · PyPI | 35 | MIT | ||
| io.github.oomkapwn/enquire-mcp Long-term memory for AI agents — your Obsidian vault as searchable persistent memory. MCP serverGitHub-verified authorLocal · npm | 34 | MIT | ||
| khive Persistent memory, knowledge graph, task management and more for AI agents via MCP. MCP serverVerified domain · khive.aiRemoteSign-in needed | 34 | Apache-2.0 | ||
| NEAT A live graph of your running system, code fused with OTel runtime, that your agent queries over MCP. MCP serverGitHub-verified authorLocal · npm | 34 | Apache-2.0 |
Filters apply to the top 400 of 2,195 tools by stars. Full list for agents: ai-memory.json