By cdeust
Standalone visualization MCP for Cortex — a live neural-graph galaxy of every project, file, symbol, memory, discussion and wiki page, plus a per-session execution trace. Read-only bridge over Cortex's shared PostgreSQL and the ~/.claude artifacts.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
database_urlPostgreSQL connection string for the SHARED Cortex store this viz reads (postgresql://[user[:pass]@]host[:port]/dbname). Use the same value as the Cortex plugin. Leave as the default for a local install; your value persists across plugin updates.
${user_config.database_url}Admin access level
Server config contains admin-level keywords
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 visualization layer for Cortex. A standalone MCP that turns Cortex's memory store, your Claude Code session history, and your codebase graph into six live reading angles over the same data — a galaxy of every project, that same graph rendered inside a 3D anatomical brain, a per-session execution trace, a consolidation kanban, a curated knowledge browser, and a wiki. It reads Cortex's shared PostgreSQL store read-only plus the ~/.claude artifacts; it renders, it never remembers.
Launch with the open_visualization tool (or /cortex-visualize). One launcher opens six reading angles; the default landing view is Trace.
The whole UI ships on the AI Architect design system: a paper-first reading surface with a persistent ink (night) toggle, greyscale chrome, and a data palette resolved from design tokens at runtime — flipping the surface re-inks every view in place without disturbing a settled layout, and every count on screen is exact and streamed, never rounded.
The plugin marketplace is the supported install path. cortex-viz ships in the same cortex-plugins marketplace as Cortex:
claude plugin marketplace add cdeust/Cortex
claude plugin install cortex-viz
cortex-viz is a read-only companion to Cortex. Install Cortex first (
claude plugin install cortex) — cortex-viz reads its shared PostgreSQL store and never writes to it. Point both at the same database: thedatabase_urlplugin setting defaults topostgresql://127.0.0.1:5432/cortex; set it to the same value you gave Cortex.
Restart your Claude Code session, then launch the visualizer:
/cortex-visualize
One launcher opens all six reading angles (Graph · Brain · Trace · Knowledge · Wiki · Board) in the browser, served live from the Cortex store, your session JSONL, the code graph, and git.
Clone + run from source:
git clone https://github.com/cdeust/cortex-viz.git && cd cortex-viz
pip install -e .
DATABASE_URL=postgresql://127.0.0.1:5432/cortex python3 -m cortex_viz
Each project becomes a cloud of nodes around one gold domain hub. Inside every cloud, nodes sit in six concentric levels by the Claude surface (or the code itself) that produced them:
| Level | What's there | Click through to |
|---|---|---|
| L1 · Setup | Skills · Commands · Hooks · Agents · MCPs | File paths; which domains share an MCP (thin indigo bridges) |
| L2 · Tools | One hub per Claude tool per domain (Edit · Write · Read · Grep · Glob · Bash · Task) | Files touched + total uses |
| L3 · Files | Every file Claude opened, read, edited, searched, or referenced — colored by primary tool | first_seen / last_accessed / last_modified + See diff against HEAD |
| L4 · Discussions | One node per Claude Code session | started_at, duration, message count + View full conversation replay |
| L5 · Memories | Persistent memories, colored by consolidation stage | Full content, tags, every scientific measurement |
| L6 · AST symbols | The code itself — functions, methods, classes, modules, constants parsed from 10 languages (Rust, Python, TypeScript, Java, Kotlin, Swift, Objective-C, C, C++, Go) | Qualified name, symbol type, parent file, and named defined_in / calls / imports / member_of edges |
npx claudepluginhub cdeust/cortex --plugin cortex-vizPersistent memory for Claude Code — remembers across sessions automatically. Install and forget. Scientific retrieval backed by 97 published references.
97 genius reasoning patterns from history's greatest minds. One epistemic standard none of them can bypass.
Enterprise PRD generator with 8 PRD types, 15 thinking strategies, multi-judge verification, codebase analysis, and 4-file export (PRD + JIRA + Tests + Verification)
Rust MCP server that indexes ANY codebase into a LadybugDB property graph — source in 10 languages with full AST, plus docs/config/binaries as File nodes (.js→Imports, Markdown→References). Resolves imports and call chains, detects communities via Leiden, traces execution flows from entry points, and exposes 24 MCP tools to agents — index_codebase, query_graph, get_symbol, get_impact, get_context, semantic_diff, and more.
Stateless reducer that turns a feature description into a 9-file PRD. Multi-judge verification with weighted-average + Bayesian consensus, calibrated against externally-grounded oracles (schema/math/code/spec). Phase 4 closed loop: per-judge Bayesian reliability calibration, Kaplan-Meier retry budgets, Clopper-Pearson KPI gates, mechanically-sealed held-out partitions, paired-bootstrap cross-arm comparisons. Deterministic Hard Output Rules validation. 17 MCP tools, 583 tests.
MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Build and maintain an LLM-curated personal knowledge base with default local FastEmbed + sqlite-vec search, BM25 fusion, structured evidence, incremental caching, and a compiled graph layer.
Give your AI a memory — mine projects and conversations into a searchable palace. 36 MCP tools, auto-save hooks, and guided setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.