Plugin marketplace
The Cortex family of Claude Code plugins: home of hypermnesia-mcp (the persistent-memory server formerly named cortex, renamed in v4.15.0 over a directory name collision), zetetic-team-subagents, and hypermnesia-mcp-viz. The marketplace name stays cortex-plugins: it is the brand-level umbrella, while hypermnesia-mcp is one package inside it.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Complete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates
21 skills · 30 commands · 1 MCP server · hooks
Cortex — persistent memory and cognitive profiling for Claude Code (renamed from the 'cortex' plugin in v4.15.0 to match the PyPI/MCP-registry identity hypermnesia-mcp) — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. These mechanisms are implemented and inspectable; committed ablations do not establish a retrieval gain from all 36 mechanisms. 57 MCP tools (60 with the optional ai-architect-mcp-codebase + ai-architect-mcp-spec integrations) with enriched schemas (visualization extracted to the standalone Hypermnesia MCP Viz server). PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. v3.17.0 — autonomous per-project wiki: SessionStart auto-spawns a 6-hour consolidate cycle; a headless `claude -p` worker drains the curation-gap queue, calls codebase-intelligence MCP tools to ground each section in the real call graph, and authors missing anchor pages (architecture / services / api / data-flow / operations / decisions / PRD) per project from the source tree. 15 canonical scopes × 13 file sections; per-project dashboards under `wiki/_dashboards/`. Mermaid diagrams have a 🔍 lens with zoom + pan. Workflow graph with caller-qualified CALLS chains rendering full method-to-method dependencies (native tree-sitter, no AP required). Side panel humanized for non-technical users. Ingests codebase analysis (ai-architect-mcp-codebase) and PRDs (ai-architect-mcp-spec) into wiki + memory + knowledge graph. Docker image available.
13 skills · 3 commands · 1 MCP server · hooks
Canonical Claude Code publication for the standalone Hypermnesia MCP Viz server — a live neural-graph galaxy of every project, file, symbol, memory, discussion and wiki page, plus a per-session execution trace, a consolidation kanban, and a curated knowledge/wiki browser. Read-only bridge over Cortex's shared PostgreSQL store and the ~/.claude artifacts; it renders, it never remembers. Restores the open_visualization and get_methodology_graph tools removed from Cortex; launch with /cortex-visualize.
1 skill · 1 MCP server · hooks
Cortex persistent local-first memory for Codex: the complete tool profile and the same 11 lifecycle hooks the Claude Code plugin installs.
1 MCP server · hooks
DEPRECATED — renamed to hypermnesia-mcp. This shim registers no functional hooks; it only announces the migration at session start. Install hypermnesia-mcp from this same marketplace, then uninstall cortex. Memories and configuration are untouched (storage paths do not change).
hooks
DEPRECATED — renamed to hypermnesia-mcp-viz, first published in cortex-viz v3.1.0 (the rename itself was never tagged v3.0.0 — that version number sat unpublished in this marketplace's pin for six days). This frozen, nonfunctional migration shim has no MCP server or tools; it only announces the replacement at session start. Uninstall cortex-viz@cortex-plugins, refresh this marketplace, then install hypermnesia-mcp-viz@cortex-plugins. The repository remains cdeust/cortex-viz; only the marketplace plugin identity changed.
hooks
Shows how many plugins this repo ships, and links here.