6,965 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 268agent 171agentic-ai 151agent-memory 149cli 133agents 127ai-memory 122claude-code-plugin 80skills 74ai-coding 73ai-tools 70cursor 69knowledge-base 69open-source 64
fangsylar-pixel/marvis-working-memory-mcp
Skill Claude CodeCodex
Persist and reuse confirmed user preferences, project state, and verified task experience through the working-memory MCP. Use for multi-step or recurring work where previous decisions, progress, or successful troubleshooting should carry into later tasks.
Skill Codex
Prepare, save, and transfer durable coding-agent context using OpenHandoff when a task spans agents, sessions, or tools.
Skill Claude CodeCodex
A skill for keeping project-specific work context in private local notes separate from the code repository. It defines how to read and update rules, project overviews, handoffs, inbox items, and decisions.
Skill Claude CodeCodex
Load the governing spec/contract for a file or topic from a project's memo-bank (a read-only MCP docs corpus) BEFORE reading code or editing. Use this in any repo that has a .island-slices.json or a memo-bank MCP server, whenever you are about to edit a file, or are asked "what governs X", "is there a spec for Y"…
Skill Claude CodeCodex
Unified Code Property Graph radar, sandboxed RLM execution, OKF semantic memory evolution, and swarm concurrency control.
Skill Claude CodeCodex
Use when an agent needs durable shared knowledge across people, sessions, machines, or agent runtimes, or needs to connect to and safely operate a Strata deployment.
Skill Claude CodeCodex
Launch or reuse the loopback Memex Workspace UI when the user asks to browse conversations, manage facts, inspect taxonomy or pipeline health, or explore the knowledge map.
Skill Claude CodeCodex
Use the memoryengine tools for long-term memory recall, deterministic analytics, transcript logging, and sync operations.
Skill Claude Code
Wipe the per-project memory cache for the active project when it was re-cloned from the same path. Use when the user says "reset project memory", "wipe this project's memory", "I re-cloned the repo", or "memory is stale".
granoflow/granoflow-mcp-server
Skill Codex
Use when working with Granoflow tasks, Task Work/Delivery, waiting for user input, weekly/monthly reviews, review cards, long-term work memory, project lifecycle boards, milestone Plan acceptance packs, project E2E SoT, long-task run continuity, workflow-jargon glosses, Local HTTP API setup, or dissatisfaction with…
Skill Claude CodeCodex
Give this agent a real email address, a webhook URL, durable memory across runs, and the ability to wait for an event without burning tokens. Use when a task needs a verification code sent by email, needs to wait for a webhook or an approval, needs to remember something after the session ends, or needs to survive a…
Havix0101/arkon-vault-connector
Skill Claude CodeCodex
Use Arkon Vault before substantial work and at handoff boundaries to preserve project continuity across AI tools.
Skill Claude CodeCodex
Use this skill whenever the user wants to store, retrieve, search, or manage persistent semantic memory. This includes requests related to memory management, knowledge retention, context caching, storing information across sessions, semantic search over past conversations, tagging and organizing stored information…
Skill Codex
Recall and maintain one Agent's private, sourced experience together with human-reviewed shared ART Knowledge Editions. Use when prior decisions, procedures, project facts, user preferences, earlier failures, or reusable conclusions may affect the current task, and when the user asks to remember, retrieve, correct, or…
Skill Claude CodeCodex
Japan Operations OS — Verified knowledge across 10 domains for AI agents operating in the Japanese market. Regulations, protocols, calendar, regional, foreign entry, travel, entertainment, and persistent memory.
Skill Codex
Run long-lived autonomous agent loops with persistent memory, context-window compaction, self-healing retries, and resumable state. Use when an AI coding agent must retain progress across sessions, recover from failures, or avoid context exhaustion.
Skill Claude CodeCodex
Instrucciones arquitectónicas sobre cómo guardar, procesar o buscar conocimientos, PDFs, y reflexiones dentro del ecosistema LLM-Wiki MCP. Usa este skill cuando el usuario pida "memorizar", "guardar" o procesar nueva información.
Skill Claude Code
Add persistent, structured long-term memory to AI agents using Maximem Synap. Use this skill whenever the user is building, debugging, or evaluating an AI agent and mentions any of: "memory", "long-term memory", "persistent memory", "agent memory", "remember across sessions", "context window", "agent forgets", "user…
molty-assistant/agent-memory-skill
Skill Claude CodeCodex
Memory management for AI agents - list, search, summarize, and maintain your memory files. Includes AI-powered digest.
Skill Claude CodeCodex
Use when working day to day with an existing goat shed — running goat commands, inspecting or querying facts, understanding broadcast vs conversation, ownership/visibility of facts, tags, or writing a new importer or deliverer. Also use when explaining goat's data model (facts vs state vs reference, valid time vs…
Skill Codex
Always use Memory Store MCP tools for durable project-local AI memories and notes. Required whenever Codex is researching a project, applying code edits, completing a feature, initializing .memory-store, searching, reading, creating, updating, deleting, or cleaning up persistent project knowledge across sessions…
Skill Claude CodeCodex
A semantic compression skill backed by a local MCP server. Compresses PRDs, codebases, research papers, and meeting notes into dense symbolic notation (SHM), reconstructs them back into prose, and manages a persistent library of saved compressions. Trigger on: SQUEEZE, EXPAND, LIST SQUEEZES, RECALL, SEARCH, DELETE…
chetto1983/turing_AgentMemory_MCP
Skill Claude CodeCodex
Use when an agent or application needs persistent memory, cross-session recall, user preferences, durable facts, conversation history, cited document context, memory governance, or direct Turing AgentMemory MCP integration.
Skill Claude CodeCodex
Auto-activate when the user types /zero or asks about the Zero system — boot, health-check, sync, install, or troubleshoot — e.g. "/zero", "เปิด zero", "เช็คระบบ zero", "zero status", "ติดตั้ง zero", "zero ไม่ทำงาน", "ซิงก์สมอง", "อัปเดตสมอง", "zero-brain", "สกิลของ zero". Covers the /.zero zone — brain vault…
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: