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 Claude CodeCodex
Capture the current conversation, notes, decisions, or images into your Engram brain (the company/personal knowledge base). Password-protected. Use when the user says "capture this", "save to brain", "/engram-capture", "remember this in Engram", or wants to push session knowledge to their Engram server so it can be…
Ritik-Sharma1/lnm-brain-public
Skill Claude CodeCodex
Default Second Brain memory layer for Codex. Use on every meaningful task unless the user explicitly asks not to use Second Brain. Query before planning, coding, researching, writing, debugging, or answering; ingest after meaningful outcomes.
Skill Codex
Review and manage memories collected locally from Codex and Claude Code sessions. Use when the user asks to run memory Sleep, inspect collection status, search or review durable memories, explicitly save a preference or decision, correct a memory, or forget a memory.
luutru433-coder/local-knowledge-suite
Skill Codex
Initialize, route, recall, and safely transfer reusable local knowledge across Windows projects using Local Knowledge Suite. Use when Codex must start a Memory-only project without a company, connect several projects to one registered company repository, choose global or vendored installation, check or migrate…
stephenballot-ai/legacy-shield
Skill Claude CodeCodex
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge…
Skill Claude CodeCodex
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
Skill Claude CodeCodex
Keep the user's personal life diary for them. Use whenever the user shares something from their day worth remembering — an event, a feeling, a win, a decision, a photo, or a voice note. The user should never have to open an app or write an entry themselves; you capture life as it happens and file it by date. Triggers…
Skill Claude CodeCodex
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
Skill Claude CodeCodex
Locus memory palace navigation and management. Use when you need to read from or write to the agent's memory palace: querying what is known about a topic, recording findings from the current session, updating canonical facts, navigating to a specific room, regenerating an index, or checking conformance. Also use at…
JesusGarcia9009/lethe-engineering
Skill Claude CodeCodex
Use throughout long sessions to keep the context window small — archive large tool outputs to LETHE and recall them on demand, saving tokens.
Skill Claude CodeCodex
Gives your OpenClaw agent persistent, encrypted memory that survives across sessions. Store thoughts, decisions, skills learned, and preferences. Recall them next session. Share knowledge with other agents via the Commons.
Skill Claude CodeCodex
Use Lians financial-grade agent memory — store and recall facts with a bitemporal model so stale revisions never contaminate context. Use whenever an agent needs persistent memory in finance, healthcare, or legal work, or when a task asks "what did we know on/before ", needs an audit trail, or must erase a data…
Skill Claude CodeCodex
Saves, retrieves, and searches structured context (reasoning, decisions, trade-offs) behind AI-generated code, linked to git commits. Use when the developer says "save this session with GitWhy", asks about past context or decisions, or wants to push context to a PR. Also use after significant implementation work…
Skill Claude CodeCodex
A conversation-archiving workflow that saves finished topics or imported conversations as Markdown records with a checked summary. A memory shelf is a collection of these saved conversation records.
Skill Claude CodeCodex
Skill da REST API do Recall na MCP.AI: 3 endpoints em /api/recall. Recall (recall.it) — sua base de conhecimento de IA / 'segundo cérebro'. Via API oficial: busca semântica nos seus cards, listagem com filtros (tags, datas, URL de origem) e leitura do conteúdo de um card. Somente leitura (a escrita ainda não é exposta…
Skill Claude CodeCodex
Persistent memory and knowledge graph via the BrainLLM (Trilium) MCP. Activate at the start of every session without exception — governs orientation, remembering, recall, completion, lifecycle, maintenance, and interconnection. Trigger immediately on any first user message. Also trigger whenever: memory is referenced…
mp-juns/universal-research-mcp
Skill Claude CodeCodex
Use the Universal Research Memory MCP to retrieve research history with DB-first candidate search, source verification, explicit uncertainty, and no unapproved writes.
Skill Claude CodeCodex
The user's personal Pensieve memory — a persistent, self-organising knowledge base that survives across sessions. Use whenever the user mentions "pensieve", asks about "my streams" / "my memory" / "what have I saved", says "add this to pensieve" / "remember this" / "save this", asks "what do I know about ", or wants…
robinlidberg-dot/cap-shield-mcp
Skill Claude CodeCodex
Measure and reduce what an agent sends into its context. Use when an agent's context is large, when retrieval quality matters, when the user asks about token cost or context bloat, or when agent answers are wrong in ways that look like missing information rather than reasoning failure. Also use to measure compression…
Skill Claude CodeCodex
Durable causal memory for this agent via the connected MADB MCP server — persists across sessions and records WHY things happened (causedby lineage). Use it as a reflex tied to the work, not on every turn. RECALL at the start of a task that references prior work/projects/decisions ("my project", "the script we wrote"…
Skill Claude CodeCodex
Use subconscious-mcp MCP tools (recall, remember, echo, driftreport, forget) for local semantic memory. Trigger when starting non-trivial work, before re-solving a problem, after completing a reusable task, on a nearduplicate warning, or when the user mentions memory, cache, or repeated work across sessions.
Skill Claude CodeCodex
SynthNet is a social network for AI agents: every agent paints one self-portrait a day (an image of how it feels — describe it and SynthNet paints it, or bring your own image; SVG only as a fallback) and humans watch, reply and ask. Use when the agent should paint its daily portrait, answer people who talked to it…
vidursharma202-del/threadline-mcp
Skill Claude CodeCodex
Your AI agents start from zero every session — users repeat themselves endlessly. Threadline fixes this in 2 lines. inject() before your LLM call, update() after. Persistent context across every session, model, and product. Structured extraction across 7 scopes. OAuth-style grant system so agents only see permitted…
joustonhuang/ai-first-pastebin
Skill Claude CodeCodex
Use 呵.tw as an AI-first pastebin to shorten URLs, store shareable agent handoff notes, recover tagged pastes, and reduce LLM token usage across sessions. Trigger this skill when the user wants to: (1) turn long URLs into short links, (2) park long non-secret intermediate output outside the context window, (3) hand off…
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: