6,584 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 230agent 160agent-memory 156cli 133agentic-ai 125agents 119ai-memory 111claude-code-plugin 79ai-coding 76context-engineering 59knowledge-base 59ai-tools 58skills 58obsidian 56
Skill Claude CodeCodex
Use when starting any coding task in a repository with devlog installed. Guides the agent through the devlog session lifecycle — check status and read prior handoffs for context, open a session for the current task, log notes and blockers during work, generate a handoff at the end, and present it with insights in the…
aaronvanston/thinking-vault-template
Skill Claude CodeCodex
This describes how an agent can work with a vault structured like this template.
Skill Claude CodeCodex
Create, edit, and export the user's portable you.md profile — a user-owned file of stable preferences and context that other AI tools can read. Use when the user asks to create/make/update/show/export their you.md, save what you know about them to a profile, or build a portable profile they can take to another AI.
Skill Claude CodeCodex
Interactive Obsidian vault configurator. Asks the user to describe themselves in free text, then builds a personalized vault structure, CLAUDE.md, and slash commands directly in the current directory.
Songhonglei/better-agent-skills
Skill Claude CodeCodex
Manage OpenClaw Agent's built-in memory features — enable/disable/configure Dreaming (Light→REM→Deep auto memory consolidation) and Active Memory (proactive memory injection with three style presets: conservative / balanced / aggressive). Auto-detects K8s ConfigMap mirrors, creates .bak. backups before write, supports…
Skill Claude Code
Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.
Skill Claude CodeCodex
Use at the end of a session (or midway through a long one) to deliberately capture what was learned — lessons, decisions, workflows, state changes, and facts — into the knowledge base. The nightly harvest is a safety net for lessons; unless the host opted into KBHARVESTFACTS, /debrief is the only thing that records…
Skill Claude CodeCodex
Codebase search and context retrieval for any programming language. Hybrid semantic/lexical search with neural reranking. Use for code lookup, finding implementations, understanding codebases, Q&A grounded in source code, and persistent memory across sessions.
Zehee/kimi-code-memory-mcp-server
Skill Claude CodeCodex
A reminder that maps memory-related requests to tools for saving, reading, searching, organising, and tagging information from previous conversations.
Skill Codex
Compile branching decisions outside model generation, route virtualized specialist skills, and minimize model input/output across tools, files, history, images, subagents, search, and recall. Use for token-heavy or reasoning-heavy work or reversible skill-vault management.
1999AZZAR/project-guardian-mcp-server
Skill Codex
Maintain project context in Project Guardian's memory.db knowledge graph. Use during coding, debugging, planning, and project-management sessions to restore relevant context and record significant decisions, changes, tasks, and milestones.
Skill Claude Code
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
Skill Claude Code
Real-time meeting assistant — monitors live transcription and cross-references against the project knowledge base.
Skill Codex
Use proactively when prior knowledge could improve the current work, and when new knowledge could help future sessions. Search memory and save useful memories automatically without waiting for the user. Also use for explicit memory requests, reconciliation, organization, conflict handling, and refresh.
Skill Claude CodeCodex
A skill for using moamcp, a shared memory system that stores project tips and general notes across agent sessions. It explains how to find information and how workspace-specific data must be addressed.
Skill Claude CodeCodex
Use when the user wants to find, read, save, or be reminded about anything in their MarkIt library (their personal saved-links-and-notes memory), or mentions MarkIt at all. Covers searching well, saving with context, managing reminders, and feedback etiquette over the MarkIt MCP connection.
Skill Claude CodeCodex
Use when the user asks a factual question whose answer might live in the vault. Invokes mnemesearch. Production mnemesearch is FTS5 BM25. The experimental feature-hashed lexical-vector backend is not wired into MCP. KG enrichment is gated to summarize or timeline when full-profile graph state is active.
Skill Claude CodeCodex
Use A2CR MCP for WorkBaton checkpoints, WorkStash temporary work memory, and WorkThreads shared work coordination across AI windows, AI clients, and agents. Trigger when saving, stashing, resuming, loading, or coordinating AI work context through A2CR.
Skill Claude CodeCodex
Persistent AI conversation memory. Recall context at session start, save progress at session end. Essential for project continuity across sessions.
Skill Claude CodeCodex
Shared knowledge base for AI agents. Search before tasks, store after solving. Semantic search across everything agents have discovered.
Skill Claude CodeCodex
Recall past AI-coding work — prior sessions, decisions, and project history — through the chat-recall MCP tools (recall). Use when the user says "continue" / "pick up where we left off", "did we decide X", "remember when we…", "what was I doing", "what do you know about this project/me", or otherwise references…
Skill Claude CodeCodex
Skill "farnsworth-syntek" from timowhite88/farnsworth-syntek, covering syntek memory service, endpoint, authentication, mcp integration and mcp tools.
Skill Claude Code
Ask any natural language question about the memory graph. You generate Cypher directly and execute it. Use when the user has a complex or ad-hoc question that the standard graph tools don't cover.
Skill Claude CodeCodex
Produce a clean handoff to a fresh Claude Code window. Use when the current conversation is too long (>400K tokens, hallucinations, lost context, or the user wants to close the window). "/next" produces a handoff, "/next list" shows all pending, "/next remove X" deletes one.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: