Collaborative memory for human-AI work — persistent, searchable, interconnected
npx claudepluginhub linxule/memex-plugin --plugin memexAsk a complex question of the memex vault with deep retrieval
Batch extract observations from memos that don't have them yet
Load a specific topic, memo, or project context into the current session
Check vault health - broken links, orphans, and maintenance suggestions
Synthesize multiple memos into a concept or summary note
Open the memex vault in Finder or Obsidian
Retry failed memo generations from pending queue
Manually save current context as a memo to the memex vault
Search memos and transcripts in the memex vault using hybrid search
Show memex statistics and status including projects, memos, and pending items
Cross-session synthesis — find patterns, contradictions, and drift across recent memos
Show timeline of sessions and memos for a date range
Ask a complex question about the memex vault — search, cross-reference, and synthesize from memos and observations. Use for "why did we...", "what was the reasoning behind...", cross-project pattern questions, or when simple keyword search isn't enough. <example> Context: User asks about a past architectural decision User: "Why did we reject the Honcho data model?" Assistant: Runs `memex ask` with thorough depth, synthesizes from observations and memos. <commentary> Complex "why" question spanning multiple sessions — ask retrieves observations (atomic facts) plus document context, enabling cross-referencing. </commentary> </example> <example> Context: User asks about cross-project patterns User: "What patterns do we use for config management across projects?" Assistant: Runs `memex ask`, finds observations from memex, my-app, and research-project projects. <commentary> Cross-project pattern question — ask searches observations across all projects and merges results via RRF scoring. </commentary> </example>
Tend the knowledge garden — the full lifecycle of growing, connecting, and maintaining the memex vault. Diagnose vault health, condense project memos into living overviews, create cross-project topics, merge overlapping notes, fix broken links, and archive superseded knowledge. Use when: - A project has 5+ memos since its last condensation (or has never been condensed) - User asks to "condense", "tend the garden", "update project overview", "check vault health" - User asks "what does this project know?" or "where are we with X?" - After `/memex:synthesize` identifies patterns, contradictions, or merge candidates - You notice a `_project.md` is empty or stale while working in a project - A concept appears in 2+ projects and deserves its own topic note - Vault health diagnostics show broken links, orphans, or stale files <example> Context: User is working on alcor and asks about project state User: "Where are we with alcor?" Assistant: "Let me check — alcor has 51 memos but its project overview is empty. I'll condense them." <commentary> Empty _project.md with many memos triggers condensation. Read memos, write overview. </commentary> </example> <example> Context: After completing significant work User: "We've done a lot this week. Can you update the project overview?" Assistant: "I'll read the recent memos and update _project.md with what's changed." <commentary> Explicit request for project condensation. Read new memos since last condensation date. </commentary> </example> <example> Context: User wants vault-wide maintenance User: "Let's tend the garden — condense everything and grow the topics." Assistant: "I'll assess what needs work and create a team to condense projects in parallel, create topic notes for cross-project patterns, and fix broken links." <commentary> Full vault tending. Diagnose first, then use team for parallel work. See lifecycle below. </commentary> </example>
How to write effective session memos. Use when: - User invokes /memex:save - User says "save this for later" or "remember this" - User asks to "create a memo" or "document this session" - Manually capturing important decisions or learnings - The [memex] activity nudge appears in context <example> Context: User asks to save current context User: "Can you save what we discussed about the retry pattern?" Assistant: "I'll create a memo capturing the retry pattern discussion." <commentary> Use memo-writing skill to ensure proper format with future context, decisions, tensions, and open threads. </commentary> </example> <example> Context: Activity nudge appears System: "[memex] Substantial session activity detected. Consider /memex:save" Assistant: "We've done substantial work. Let me save a memo before context gets too long." <commentary> When the nudge appears, proactively suggest saving. You have the best context right now. </commentary> </example>
Search memos and transcripts for prior context — temporal browsing, targeted keyword lookup, or deep synthesis redirect. Use when: - User asks "what did I do yesterday?", "show me last week", "today's sessions" - User asks "what was the decision...", "remind me...", "find the memo about..." - User references past work: "last time", "previously", "earlier we..." - User explicitly says "search for...", "recall...", "when did we..." For complex why/how questions that require synthesizing across many sessions or projects, prefer `ask-memex` instead. Do NOT trigger for: - Future-oriented questions ("how should we implement X?") - General knowledge ("what is a closure?") - Questions answerable from current session context - Vault health, graph structure, or task queries (use garden-tending) - Deep cross-project pattern questions (use ask-memex) <example> Context: User asks what they worked on recently User: "What did I do yesterday?" Assistant: Runs temporal scan, presents timeline of sessions and memos. <commentary> Date reference "yesterday" triggers TEMPORAL mode. No keywords needed. </commentary> </example> <example> Context: User asks about a past decision User: "Why did we choose JWT for authentication?" Assistant: Searches with expanded keyword variants, synthesizes answer. <commentary> "Why did we..." triggers KEYWORD mode. Expand: "JWT OR authentication", "OAuth OR token OR auth", "session OR credential" </commentary> </example> <example> Context: User asks about cross-project patterns User: "What patterns do we use for config management across projects?" Assistant: Redirects to ask-memex skill for deep synthesis. <commentary> "across projects" + "patterns" triggers DEEP mode → redirect to ask-memex. </commentary> </example>
AI-native product management for startups. Transform Claude into an expert PM with competitive research, gap analysis using the WINNING filter, PRD generation, and GitHub Issues integration.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Search and retrieve documents from local markdown files.
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.
Persistent memory system for Claude Code - seamlessly preserve context across sessions