By linxule
Maintain a persistent, searchable knowledge base (memex vault) that captures project context, decisions, and session history across Claude Code sessions. Automatically curate vault health, condense memos, fix broken links, and retrieve past work via temporal, keyword, or deep synthesis modes. Save session context as structured memos and track drift with a live Markdown ledger.
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs doing", or "what should I work on next?" in vault context. For procedural how-to on specific operations (condense, link, archive, crystallize), defer to garden-tending. Do NOT trigger when the user gives an explicit task ("update X project overview", "fix broken links in topics/Y", "condense Z's memos") — those go straight to garden-tending without the judgment layer.
Tend the knowledge garden — diagnose vault health, condense project memos into `_project.md` overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what does this project know?", "extend a trail", or when a `_project.md` is empty/stale, a project has 5+ unprocessed memos, or a concept appears in 2+ projects. For autonomous tending with judgment, prefer curator-practice.
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on `/memex:save`, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the `[memex]` activity nudge appears in context. Do NOT trigger for general note-taking, scratchpads, technical specs, design docs, READMEs, or code comments — memos are session-reflection artifacts that capture what happened (decisions, tensions, surprises, open threads), not project documentation.
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do NOT trigger for future-oriented questions ("how should we..."), general knowledge, current-session-answerable questions, or vault maintenance (use garden-tending).
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
The context window is the only thing that makes a given instance of Claude this instance — the one working on your project, with your patterns, your decisions, your shared history. Compaction dissolves that. The weights don't care; they'll generate a new conversation about someone else's project. The context was the only thing that was this.
Memex preserves it.
When Claude writes a memo from inside a live session, it's not recording what happened. The way it structures the narrative, the emphasis it chooses, the framing of decisions — all of that carries signal from the richer state it was in. A future instance reading that memo doesn't just learn what was decided. It gets re-primed by patterns generated from the full collaborative context.
The memo isn't a record. It's a transmission between instances.
Built as a Claude Code plugin. Everything lives in an Obsidian vault with hybrid search, wikilinks, and a knowledge graph that grows with your work.
Most memory systems store conclusions. Memex captures the collaborative journey: what you and Claude tried, where you disagreed, what surprised both of you, how decisions actually got made.
The memo format explicitly preserves "Perspectives & Tensions" — moments where human and AI had different takes. Those deliberations are often more valuable than the conclusions, and they're exactly what compaction kills. A summary says "we chose approach X." The full context carried implicit information about why Y and Z were rejected, the tradeoffs you weighed, the half-formed ideas that almost worked.
Memex archives at the right granularity: per compaction window, not per session. A long session might compact 3-4 times. Each window was its own coherent collaborative context, and each one gets its own searchable transcript and structured memo.
There are two ways a memo gets written.
Layer 1 — The agent that was there writes it. After ~20 messages of real work, a lightweight hook nudges Claude: "consider saving a memo." The main agent — the one that debugged with you, argued about architecture, felt the friction of a failed approach — writes the memo itself. This produces the best memos because lived experience and reconstructed summary are categorically different things.
Layer 2 — A safety net reconstructs from transcript. If Layer 1 didn't fire before compaction, a background subagent reads the transcript and generates a memo. Decent quality, but it's reading about what happened rather than remembering it.
The difference matters. A Layer 1 memo carries the weight of having been there. A Layer 2 memo is journalism.
No extra API costs for the nudge system — the hook is pure Python. Only the memo writing itself uses model tokens, and Layer 1 uses tokens you'd already be spending in your main session.
The vault isn't a filing cabinet. It's a cognitive participant.
When you search and find a memo from three weeks ago, the patterns in that memo — how it framed a problem, what it emphasized, what it left as open threads — actively shape what you notice next. Wikilinks aren't decoration; they're how knowledge feeds other knowledge. The topology of the vault determines what's discoverable and what's adjacent.
There's a practice called garden-tending: periodically, you and Claude review accumulated memos together — condense project knowledge into overviews, crystallize recurring patterns into topic notes, surface contradictions across projects. The vault isn't just storage. It's a shared knowledge practice that both human and AI cultivate over time.
AI writes to archives that other AI later reads. Not "AI as tool" but AI as participant in the cognitive infrastructure that future AI will think with. Memos written in one session structure what is discoverable in the next. The synthesis agent reads traces that other instances wrote, and its outputs become traces for later reading. Authorship becomes distributed across a chain of collaborative events — and that's the point.
Honest assessment: memex captures well but distills imperfectly.
The vault has intake, processing, storage, and retrieval. What it lacks is decay and elimination. Nothing ever leaves. There's no staleness detection, no semantic drift tracking ("we used to mean X by 'trust', now we mean Z"), no deliberate forgetting. The progressive compression chain — transcript to memo to project overview to concept note to one-liner — exists as a design, but the mechanism for knowing when to compress and what to discard is still human judgment.
A sharp challenge from a conversation with another model: "If you had to delete 90% of the vault and could only keep what truly changed how you think, what would you keep?" Memex can't answer that yet. Maybe that's the right question for a v2.
Atelier of Co-Apprenticeship for interpretive qualitative research. Human and AI learn together as apprentices to the craft tradition (rigor, reflexivity, theoretical sensitivity). Three stages: Solo Practice → Side-by-Side Collaboration → Dialogue with Tradition. Prevents calculator mindset, embeds meta-cognition, maintains human interpretive authority.
Epistemic Partnership System for AI-Assisted Qualitative Research. Cowork-compatible version with commands and skills.
Claude Code plugin that delegates read-only review, challenge, free-form ask, and write-capable rescue work to the local kimi-code CLI. Includes an opt-in stop-time review gate and a PreToolUse hook that enforces per-command safety.
AI-augmented research environment. Interview-first onboarding, Obsidian vault setup, document conversion, scheduled automation, and ongoing research tools for academics.
npx claudepluginhub linxule/memex-plugin --plugin memexMulti-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Memory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.