6,984 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 270agent 171agentic-ai 150agent-memory 149cli 133agents 127ai-memory 123claude-code-plugin 80ai-coding 73skills 73ai-tools 70cursor 69knowledge-base 69open-source 64
Skill Codex
Use when working with local EverOS memory through Codex MCP tools such as memorysearch, memorysaveturn, memoryget, and memoryflush, especially for prior project recall, high-value task summaries, or read-your-write verification.
l111403717-cloud/fix-memory-mcp
Skill Codex
Use Fix Memory as cross-window Agent Operating Context and as a verified-fix library. At task start assemble a small Core Context; for real code errors and repeated environment/tool failures use the deeper retrieval gate and fix workflow.
Skill Claude CodeCodex
Working inside the exocortex vault (/git/exocortex) — garden passes, writing or editing vault notes, checkpointing decisions. Load whenever touching vault/ markdown; encodes the golden rules, note shape, the gardening routine, and pointers to the standing case law so rulings aren't re-derived.
knowledge-bridge-labs/llmwiki-agent-bridge
Skill Claude CodeCodex
Use this skill when a coding agent needs local wiki context from a configured llmwiki-serve instance. The server is read-only from the client perspective and is addressed through the LLMWIKISERVEURL environment variable.
anthonycho-ux/unified-agent-context
Skill Claude CodeCodex
Publish posts on Threads (threads.com) for the user. Use whenever the user wants to write, draft, or publish a Threads post or thread, with or without an attached image, including "post this", "write a post using this image", or a pasted block of raw post text.
YR-yangrui/personal-project-knowledge-mcp
Skill Codex
Interactive configuration-console skill for personal-project-knowledge-mcp. Use when the user wants to view, understand, or change config.yaml; tune short/long memory conversion; adjust context budgets; change dataRoot; add or modify semantic types/categories; list all available configuration features; or asks for a…
Skill Claude CodeCodex
Use when working from the Alcove hub workspace or routing personal knowledge, pins, projects, prompts, tasks, mounts, connectors, or managed KB operations.
dhaseeb-proj/obsidian-second-brain-mcp-and-skill
Skill Codex
Use when working in a repo linked to Obsidian project memory, when the user asks to use Obsidian as a second brain, or when project work involves bugs, features, decisions, session logs, changelogs, releases, next actions, or durable project context through the Obsidian Second Brain MCP server.
Skill Claude CodeCodex
Review ai-dememory inbox proposals, provider imports, explicit captures, hook captures, recall misses, false positives, and conflict candidates. Use when the user wants to promote, reject, clean, consolidate, dismiss, or write conflict merge proposals.
zotoio/cursor-symlink-ext-context-mcp
Skill Cursor
Search shared CORE and installed extension context with the core-context MCP. Use when a request depends on shared conventions, extension-specific guidance, product context, QA context, support context, or another installed CONTEXT document.
perinchiang/kimi-code-memory-mcp
Skill Claude CodeCodex
A long-term memory system for an agent, storing conversation context and user information in several levels of detail.
Skill Claude CodeCodex
Use when the user asks to bootstrap, generate, or seed an initial okf/ knowledge bundle for this codebase from scratch.
radthenone/ai-instruction-kit-mcp
Skill Claude Code
Cursor IDE only: unify Chat Summarize under slash /compact in this project. Use when user types /compact or asks to summarize this Cursor chat thread. Do NOT use for Claude Code, Codex, or other CLIs — those have their own compact.
Skill Claude CodeCodex
Use nautli to set up and operate persistent local-first memory for MCP clients. Trigger when the user asks to remember or recall durable facts across sessions, asks "what did we decide about X", complains the agent forgot something from a previous session, wants memory shared between Claude Code and Cursor, wants to…
Skill Claude CodeCodex
Guide a user through securely configuring and using the local Zhenhai Lexiang knowledge-base MCP service.
Skill Claude CodeCodex
Use for reading/writing structured memory blocks, hash-chain audit, session logs. Replaces flat STATE.MD with typed JSON blocks and provenance chain. Load when starting/ending sessions, recording decisions, or verifying facts.
Skill Claude Code
Preserve and resume coding-session context with Session Handoff. Use at the start of repository work, before clearing context, before handoff, or when completing a spec or substantial stage.
yavdaanalytics/context-optimiser
Skill Claude CodeCodex
Exposes tools and routines to optimize conversation context, rotate chats, offload completed tasks to ChromaDB, and cluster semantic failures.
Skill Claude CodeCodex
Close out stabilized work in Vertiso Memory when the user requests a wrap-up, invokes /wrap-up, or affirmatively accepts an agent's offer. Separately confirm any proposed follow-on creation or work closure — completing actions, archiving finished intents and projects — then record the stable state, so deferred…
Skill Claude CodeCodex
Persistent personal knowledge base powered by semantic search. Capture thoughts, ideas, tasks, and observations — then find them later by meaning, not keywords. Includes extensions for household knowledge, home maintenance, family calendar, meal planning, professional CRM, and job hunt tracking. Supports multi-agent…
Skill Claude CodeCodex
Save a durable fact, preference, decision, convention, or completed-session outcome in NarratorDB. Use when the user explicitly asks to remember something or clearly requests persistence across future sessions.
234194027-cpu/aion-memory-nexus
Skill Codex
Set up an external AI agent to connect to the Life Memory System through MCP, including verified installation, retrieval, RawEvent writes, sync, diagnostics, and Working-Agent governance. Use when an agent needs to install or verify the Life Memory MCP bridge, onboard Codex/Claude/Cursor/Windsurf style clients, or…
Skill Codex
Create and maintain effective durable memories with the agent-memory MCP tools. Use when the remember, review, revise, and forget tools are available, when starting a task that may benefit from prior workspace context, or when confirmed preferences, corrections, decisions, constraints, pitfalls, and reusable…
Skill Claude CodeCodex
Distill a git repo's full history into durable engineering memory under .repo-memory/ (timeline, decisions, landmines, architecture). Use when the user wants historical/"why is this like this" context for a codebase, to onboard an agent onto a repo's past, or asks to run repo-history / analyze git 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: