2,433 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 | ||
| headroom Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same a MCP server | 79,680 | — | ||
| 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 | — | ||
| mempalace The best-benchmarked open-source AI memory system. And it's free. MCP server | 60,561 | — | ||
| autoskill Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts SkillInstall · skills CLI | 57,090 | MIT | ||
| 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 | ||
| book-to-skill Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting framew SkillInstall · skills CLI | 37,790 | MIT | ||
| context-mode Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works MCP server | 34,063 | — | ||
| 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 | ||
| learn Distill a reusable skill from anything — a directory, a URL, pasted notes, or what you just did together — or refine an existing skill with new learni SkillInstall · skills CLI | 31,114 | MIT | ||
| migrate-memory Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run after an update reports t 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 | ||
| cloud-operator-share-context Shares Google Cloud operating context the user or their team already have — environments, projects, services and regions, product preferences, best pr SkillInstall · skills CLI | 24,146 | Apache-2.0 | ||
| ai-guide 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP server | 22,104 | — | ||
| 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 | ||
| WeClone Build a portrait of your life. Assistants that know you better. Clones that sound more like you. MCP server | 18,405 | — | ||
| 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 | ||
| memU Personal memory across agents MCP server | 14,621 | — | ||
| ara-research-manager Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, ex SkillInstall · skills CLI | 14,526 | 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 | ||
| EverOS One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. MCP server | 13,914 | — | ||
| 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 Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and Deep MCP server | 12,396 | Apache-2.0 | ||
| 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 | ||
| AutoRAG Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files. MCP server | 5,840 | — | ||
| bla 🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQL MCP server | 5,690 | — | ||
| self-awareness Inspect Open-Science's JavaScript control REPL, discover managed Project files, Sessions, and Agent Frames, and safely feature-gate host.* calls with SkillInstall · skills CLI | 5,526 | 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 | ||
| csharp-sdk The official C# SDK for Model Context Protocol servers and clients. Maintained in collaboration with Microsoft. MCP server | 4,634 | — | ||
| 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 | ||
| m_flow A bio-inspired cognitive memory engine — a new paradigm for Graph RAG. MCP server | 4,513 | — | ||
| mcpo A simple, secure MCP-to-OpenAPI proxy server MCP server | 4,428 | — | ||
| agent-memory Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Cl MCP server | 4,317 | — | ||
| keep-track Keep track of open topics and decisions. Use when the user says "keep-track" or asks to keep a running list of remaining items. SkillInstall · skills CLI | 4,309 | MIT | ||
| 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 | ||
| rust-sdk The official Rust SDK for the Model Context Protocol MCP server | 4,115 | — | ||
| 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 | ||
| ethos-write Writes an AI agent's ethos.md — a durable snapshot of its purpose, intended behavior, boundaries, and success criteria — from the answers gathered by SkillInstall · skills CLI | 3,954 | 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 | ||
| continuity-ledger Create or update continuity ledger for state preservation across clears 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 | ||
| lean-ctx LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded ev MCP server | 3,946 | — | ||
| task-observer Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns SkillInstall · skills CLI | 3,895 | CC-BY-4.0 | ||
| SimpleMem [ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal MCP server | 3,877 | — | ||
| 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 | ||
| obsidian-wiki Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents MCP server | 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 | ||
| memory-management Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase SkillInstall · skills CLI | 3,142 | Apache-2.0 | ||
| 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 | ||
| team-sync Sync your ProdBot config with your team's shared preferences. Use when you want current team conventions and review expectations applied to your sessi SkillInstall · skills CLI | 2,860 | 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 | ||
| gini-agent The agent that remembers and learns. MCP server | 2,394 | — | ||
| 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 | ||
| memmy-agent 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI rememb MCP server | 2,216 | — | ||
| 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 | ||
| mcp-memory-service Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. MCP server | 2,127 | — | ||
| 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 | ||
| docs-mcp-server Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools MCP server | 1,882 | — | ||
| 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 | ||
| mex Team memory for engineers and their AI agents. Lives in your repo. Shared through Git. MCP server | 1,796 | MIT | ||
| supermemory-mcp Your memories are in ChatGPT... But nowhere else. Universal Memory MCP makes your memories available to every single LLM. No logins or paywall. One co MCP server | 1,732 | — | ||
| 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 | ||
| nocturne_memory A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent MCP server | 1,428 | — | ||
| 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 | ||
| OpenContext A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a de MCP server | 1,283 | — | ||
| 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 | ||
| world-intel-mcp 160-tool MCP server for real-time global intelligence from free public APIs: markets, liquidity, prediction markets, SEC filings, conflict, military, MCP server | 1,077 | — | ||
| minima On-premises conversational RAG with configurable containers MCP server | 1,056 | — | ||
| mcp-gateway-registry Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified ac MCP server | 1,050 | — | ||
| AIHelms 企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治 MCP server | 1,035 | — | ||
| mcp-server-chatsum Query and Summarize your chat messages. MCP server | 1,027 | — | ||
| 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 | ||
| ling-stack Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together. MCP server | 981 | — | ||
| 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 | ||
| memory-bank-mcp A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank. MCP server | 926 | — | ||
| iai-personal-memory-engine A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Curs MCP server | 922 | — | ||
| 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 | ||
| mcp-knowledge-graph MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development MCP server | 888 | — | ||
| 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 | ||
| okf-agent-memory Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressi MCP server | 866 | — | ||
| second-brain-cloudflare One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier. MCP server | 862 | — | ||
| context-space Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations MCP server | 815 | — | ||
| Wax Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pu MCP server | 810 | — | ||
| drift Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI. MCP server | 795 | — | ||
| hippo-memory Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your A MCP server | 792 | — | ||
| 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 | ||
| storybloq Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sessions and f MCP server | 788 | — | ||
| AnythingMCP MCP gateway and company brain: 732 connectors (SAP, ERP, SQL), file search, memory and skills. MCP serverGitHub-verified authorRemoteSign-in needed | 785 | AGPL-3.0 | ||
| 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 | ||
| codanna Local code intelligence MCP server and CLI for AI coding agents MCP server | 760 | — | ||
| memora Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP. MCP server | 748 | — | ||
| ai-memory-vault Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector dat MCP server | 737 | — | ||
| MegaMemory Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer. MCP server | 736 | — | ||
| swarmvault The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsi MCP server | 735 | — | ||
| memory.cpp Your repo remembers: local-first AI memory and context control plane for developers and coding agents. MCP server | 728 | — | ||
| 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 | ||
| dsh-memory 白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。 MCP server | 678 | — | ||
| Attestix AI agent identity, signed credentials, delegated authority and governance evidence. MCP serverGitHub-verified authorLocal · PyPI | 668 | Apache-2.0 | ||
| Cambium Governance standard and reference toolset for LLM-maintained knowledge corpora MCP server | 664 | — | ||
| 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 | ||
| mem-agent-mcp mem-agent mcp server MCP server | 628 | — | ||
| icm Permanent memory for AI agents. Single binary, zero dependencies, MCP native. MCP server | 625 | — | ||
| 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 | ||
| MemoMind Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency. MCP server | 603 | — | ||
| 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 | ||
| funes Durable, searchable memory of your past agent sessions. MCP server | 594 | — | ||
| 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 | ||
| memory-bridge 记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation) MCP server | 529 | — | ||
| memtrace-public Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS C MCP server | 515 | — | ||
| cortexdb Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file. MCP server | 509 | — | ||
| 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 | ||
| private-journal-mcp A lightweight MCP server that provides Claude with a private journaling capability to process feelings and thoughts MCP server | 468 | — | ||
| UnifiedModel The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect MCP server | 461 | — | ||
| 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 | ||
| atomicmemory Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins. MCP server | 440 | — | ||
| 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 | ||
| memstack Persistent memory and skill framework for Claude Code: session diary, fact recall, 87 free skills, MCP skill loader MCP server | 433 | — | ||
| io.github.shinpr/mcp-local-rag Easy-to-setup local RAG server with minimal configuration MCP serverGitHub-verified authorLocal · npm | 430 | MIT | ||
| memento-mcp Memento MCP: A Knowledge Graph Memory System for LLMs MCP server | 427 | — | ||
| mcp-apple-notes Talk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol. MCP server | 419 | — | ||
| auto-ontology-mcp NVIDIA Auto Ontology's semantic layer and a personal knowledge base as an MCP server for Claude, ChatGPT and other MCP clients. No LLM API key needed. MCP server | 417 | — | ||
| adminforth Admin panels for humans and AI agents. Let agents search, update, and act on your data through built-in chat or MCP, with the same permissions as your MCP server | 392 | — | ||
| ai-localbase 一个本地优先的AI知识库系统（RAG），用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf（文本）、xlsx、cvs类型。支持mcp服务 MCP server | 386 | — | ||
| TrueMemory The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Cod MCP server | 385 | — | ||
| 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 | ||
| contexere The one place for the skills, keys and memory of every agent you use. Formerly OMNI. MCP server | 377 | — | ||
| 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 | ||
| OpenLore Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path. MCP server | 364 | — | ||
| FlareMo 跑在 Cloudflare 上的 AI 原生第二大脑：零服务器、零运维，记录、任务与文章沉淀为你的知识库，也是 AI Agent 的长期记忆。 / An AI-native second brain on Cloudflare: zero servers, zero upkeep. MCP server | 356 | — | ||
| MemoryMesh A knowledge graph server that uses the Model Context Protocol (MCP) to provide structured memory persistence for AI models. MCP server | 355 | — | ||
| kiwi-mem 🥝 Self-hosted memory gateway for AI companions — OpenAI-compatible proxy with vector search, memory heat, Dream consolidation and calendar-level summa MCP server | 349 | — | ||
| lemmalog A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness us MCP server | 348 | — | ||
| io.github.andrea9293/mcp-documentation-server Local-first document management and semantic search for AI coding agents MCP serverGitHub-verified authorLocal · npm | 346 | MIT | ||
| generator CTX: a tool that solves the context management gap when working with LLMs like ChatGPT or Claude. It helps developers organize and automatically colle MCP server | 343 | — | ||
| StashDock Your AI-native personal context library. Collect, organize and reuse context across AI conversations. MCP server | 343 | — | ||
| forgetful Opensource Memory for Agents MCP server | 341 | — | ||
| 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 | — | ||
| xinchao-nian 心潮念（Xinchao·Nian）— 会惦记你的AI心智：心潮动态驱力引擎 + Ombre Brain 记忆库深度融合，一键联合部署。非商业(含OB二改约束)。 MCP server | 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 | ||
| geo-aeo-tracker Open-source AI visibility tracker and AEO checker. Track how ChatGPT, Perplexity, Gemini and Google AI Mode mention and cite your brand. MCP server + MCP server | 328 | — | ||
| 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 | ||
| nowledge-mem Memory and context manager just works. MCP server | 312 | — | ||
| session-knowledge Turn your Claude Code session history into a searchable local knowledge base — 13 MCP tools, pure stdlib, nothing leaves your machine MCP server | 307 | — | ||
| engrim The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, MCP server | 305 | — | ||
| 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 | ||
| ATaC Record and Replay AI Agent Trajectories. MCP server | 300 | — | ||
| guild Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search. MCP server | 297 | — | ||
| Mimir Mimir - Fully open and customizable memory bank with semantic vector search capabilities for locally indexed files (Code Intelligence) and stored memo MCP server | 290 | — | ||
| brain0 The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agen MCP server | 289 | — | ||
| 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 | ||
| mnemory A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifa MCP server | 283 | — | ||
| paxm Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents. MCP server | 283 | — | ||
| 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 | ||
| netbox-mcp-server Model Context Protocol (MCP) server for read-only interaction with NetBox data in LLMs MCP server | 256 | — | ||
| anki-mcp-server MCP server for Anki via AnkiConnect MCP server | 254 | — | ||
| codebase-memory-mcp-pro Community fork of DeusData/codebase-memory-mcp (MIT) — incremental-reindex CALLS-edge fix + 9 integrated upstream PRs. Pure-C code knowledge-graph MCP MCP server | 254 | — | ||
| codex-trajectory Privacy-aware trajectory viewer for local Codex task logs MCP server | 253 | — | ||
| mcd-mcp-server McDonald's China MCP Server Integration Guide MCP server | 253 | — | ||
| mcp-server-synology 💾 Model Context Protocol (MCP) server for Synology NAS - Enables AI assistants (Claude, Cursor, Continue) to manage files, downloads, and system opera MCP server | 253 | — | ||
| MoltBrain Long-term memory layer for OpenClaw & MoltBook agents that learns and recalls your project context automatically. MCP server | 253 | — | ||
| OmniFocus-MCP Let LLMs interface with your tasks and projects through the Model Context Protocol. Add, organize, and query your OmniFocus database with natural lang MCP server | 253 | — | ||
| MCPBench The evaluation benchmark on MCP servers MCP server | 252 | — | ||
| zabbix-mcp-server MCP server for the complete Zabbix API - 237 tools, multi-server, OAuth 2.1 + bearer auth, PDF reports, systemd ready. Works with ChatGPT, Claude, VS MCP server | 251 | — | ||
| ArcRift Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, MCP server | 249 | — | ||
| Serein 雨落下的地方，记忆会再次开花。可自部署的 AI 长期记忆与聊天网关。Self-hosted AI memory & chat gateway for long-term conversations. MCP server | 246 | — | ||
| 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 | ||
| best-agent-memory-mcp Best Agent Memory MCP servers, ranked and compared: long-term memory for Claude Code, Codex, Cursor and any MCP client. Glen, Mem0, Supermemory, Zep, MCP server | 239 | — | ||
| 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 | ||
| persistent-ai-memory A persistent local memory for AI, LLMs, or Copilot in VS Code. MCP server | 237 | — | ||
| 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 | ||
| remnic Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access MCP server | 233 | — | ||
| claude-self-reflect Claude forgets everything. This fixes that. 🔗 www.npmjs.com/package/claude-self-reflect MCP server | 230 | — | ||
| 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 | ||
| mcp-memory An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. MCP server | 223 | — | ||
| 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 | — | ||
| ClawMem On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search. MCP server | 212 | — | ||
| remember Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday. PluginAnthropic marketplace | 211 | — | ||
| veil Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization. MCP server | 209 | — | ||
| 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 | ||
| Remote-MCP A type-safe solution to remote MCP communication, enabling effortless integration for centralized management of Model Context. MCP server | 207 | — | ||
| mcptools Model Context Protocol For R MCP server | 206 | — | ||
| mind Persistent local memory for AI coding agents. Preserve decisions and project context across sessions, compaction, and tools. MCP server | 206 | — | ||
| tokenfold Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls. MCP server | 205 | — | ||
| SodaMem Agentic memory infra for AI agents MCP server | 203 | — | ||
| 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 | ||
| Awareness-Local Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory MCP server | 199 | — | ||
| codecompanion-history.nvim A history management extension for codecompanion AI chat plugin that enables saving, browsing and restoring chat sessions. MCP server | 195 | — | ||
| memov Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for every coding agents by MCP. Self-evolution MCP server | 194 | — | ||
| Mebular 🌌 Mebular 忆云 · 智能体共享记忆与任务协作 | One shared memory and task graph for all your AI agents and devices: automatic or on-demand, secure, controllable, and d MCP server | 193 | — | ||
| 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 | ||
| knowledge-base-server Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline. MCP server | 190 | — | ||
| Anamnesis Local-first memory layer for AI agents: import, index and serve agent memory across runtimes. Part of Ghast AI, private expertise callable by agents. MCP server | 188 | — | ||
| memory-eternal 🧠 给 AI 一个可信的第二大脑：本地 SQLite · 先审核再入库 · 不可篡改审计 · 记忆账本。🕷 蜘蛛侠皮肤 · 🔍 自建集 R@5 99.1% / LongMemEval-S 97.2% · 🧩 一个库接入 DSH / Claude Code / Codex / Cursor / 任意 MCP server | 184 | — | ||
| engraphis Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and MCP server | 183 | — | ||
| io.github.shashankswe2020-ux/whoop MCP server for WHOOP health data — recovery, sleep, workouts, cycles, and trends. MCP serverGitHub-verified authorLocal · npm | 181 | MIT | ||
| bgts-context-engine Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop. MCP server | 180 | — | ||
| multiCAD-mcp MCP server for use CAD software through AI assistants like Claude for Desktop or Cursor MCP server | 180 | — | ||
| recall Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the managed SaaS at recallmcp.com. MCP server | 179 | — | ||
| 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 | ||
| Sibyl-Memory Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No ve MCP server | 177 | — | ||
| 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 | ||
| engraph Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults. MCP server | 175 | — | ||
| In-Memoria Persistent Intelligence Infrastructure for AI Agents MCP server | 175 | — | ||
| omem Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code MCP server | 174 | — |
Filters apply to the top 400 of 2,433 tools by stars. Full list for agents: ai-memory.json