6,603 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 231agent 160agent-memory 156cli 133agentic-ai 125agents 119ai-memory 111claude-code-plugin 79ai-coding 76context-engineering 61ai-tools 58knowledge-base 58skills 58open-source 56
Skill Claude Code
Read-only gap analysis comparing an Obsidian vault's current quality setup against the 7-dimension methodology. Use when user says "audit vault", "check vault quality", "what's missing", "vault gaps", or wants to see how their vault measures up before running setup.
Skill Claude CodeCodex
Comprehensive guide for using the Memory, Hybrid RAG Knowledge Engine & MCP Helper tools (remember, recall, getfact, forget, updatefact, memoryinfo, linkknowledge, linkprojectmemory, unlinkprojectmemory, relinkprojectmemory, ingestdocument, queryknowledgebase, manageknowledgebase, reindexknowledgebase, list-mcp-tools…
mariusSil/chat-history-search-plugin
Skill Claude CodeCodex
Search through Claude Code local chat history JSONL files to find information from past conversations. Use when the user asks "did we discuss X before", "what did we decide about Y", "how did we solve Z", or when context from a previous session would be useful. Searches all local session files efficiently via grep +…
Skill Claude CodeCodex
Use when explicitly maintaining Project Knowledge Base: user asks to ingest/refresh/repair memory, a task is at final handoff/commit/PR/merge, or the KB needs bootstrap or full-refresh.
Skill Claude CodeCodex
Use when an agent should pick work up from Engram quickly and leave behind a clean structured handoff for the next session. Best for multi-step coding, investigations, releases, debugging, and any task where recent decisions and open loops matter.
Skill Claude CodeCodex
Memoria persistente CORTEX v3.2 (local-first). Cold start automático inyecta contexto del proyecto + perfil del operador. Hook post-turno obligatorio con quickobserve. 22 tools.
dwightpeaster/littlebird-obsidian-mcp
Skill Codex
Use when the user asks to check global knowledge, global directory, Obsidian memory, project history, company context, people notes, decisions, tasks, open loops, or anything that should be searched in the configured Obsidian vault.
Skill Claude CodeCodex
A shared team memory skill using ChromaDB, a database for storing and searching information. It is intended for team knowledge, decisions, and shared memories.
Skill Claude CodeCodex
Run health diagnostics on the amem memory database. Use when the user wants to check memory health, embedding coverage, stale memories, or diagnose issues.
iamsupersocks/grokbot-obsidian-bridge
Skill Claude CodeCodex
Search and read the user's self-hosted Obsidian vault through the bundled OAuth MCP bridge. Use when the user asks about notes, vault search, or recent documents.
Skill Claude CodeCodex
Use this procedure when a task is completed, paused, blocked, or handed to another device.
Skill Claude CodeCodex
A local-first memory and knowledge service that an AI client can access through MCP or HTTP. It stores long-term facts and preferences, indexes documents and web pages, and supports retrieval while offline.
Skill Claude CodeCodex
Use when substantive project work, structural code questions, research, planning, debugging, architecture, decisions, document ingest, incident recovery, or verified context and results should survive future sessions; also when the user invokes $using-lwc or asks to search, update, repair, configure, or maintain an…
Skill Claude CodeCodex
Event Pod gives your agent a persistent world model — structured context that survives across sessions, models, and tools. Not a transcript. A causal model with certainty scores that gets sharper over time.
Skill Claude CodeCodex
Use when managing tasks, projects, multi-agent workflows, or knowledge persistence in an Obsidian vault via MCP. This skill should be used when creating tasks, claiming work, updating progress, completing deliverables, decomposing projects into sub-tasks, monitoring project status, logging decisions or discoveries, or…
Skill Claude CodeCodex
Set up, re-authenticate, repair, or switch the Kumiho Memory backend for Codex. Use when the user invokes $kumiho-onboard, installs Kumiho Memory, has missing memory tools or authentication errors, or wants Kumiho Cloud versus self-hosted CE configuration.
Skill Claude CodeCodex
Use when maintaining project state, decisions, evidence, or a handoff that must survive a new session.
Skill Claude CodeCodex
Use when Codex should recall or store durable project context with MemoryLayer, preserve decisions across sessions, use MemoryLayer MCP tools, or troubleshoot MemoryLayer setup.
alrcatraz/astra-knowledge-base-mcp
Skill Claude CodeCodex needs its repo
Two-layer knowledge architecture — curate in LLM Wiki, search in Astra KB. Covers input classification, source-to-wiki ingestion, wiki-to-KB export (batch + realtime), semantic chunking, SAG extraction, health checks, and multi-format export.
Skill Claude CodeCodex
Master context engineering principles for building production-grade AI agent systems with effective context management, multi-agent architectures, and memory systems.
Skill Claude CodeCodex
Manage what goes into the AI agent context window for maximum quality and minimum waste.
Skill Claude CodeCodex
Search, read, and lightly organize the user's Trilium notes via hybrid lexical+semantic query over note content. On-demand: find a note, check what's in the journal, add a label, link two notes.
Skill Claude CodeCodex
Connect an agent to the Tulimoa MCP gateway — one EU-hosted endpoint that federates your connected SaaS tools and carries a persistent memory layer, so context (facts, IDs, goals, plans) survives across turns and sessions and the agent stops re-fetching and re-asking.
AINative-Studio/ainative-zerodb-memory-mcp
Skill Claude CodeCodex
Use ZeroDB persistent memory to store and recall facts, decisions, and context across agent sessions. Invoke when storing user preferences, project context, implementation decisions, or searching prior conversation history.
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: