Clement Deust

Persistent memory and cognitive profiling plugins for Claude Code

Persistent memory and cognitive profiling for Claude Code — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. 43 MCP tools (46 with the optional automatised-pipeline + prd-spec-generator integrations) with enriched schemas (visualization extracted to the standalone cortex-viz MCP). 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-automatised-pipeline) and PRDs (prd-spec-generator) into wiki + memory + knowledge graph. Docker image available.

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, 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 / get_methodology_graph / query_workflow_graph tools removed from Cortex 3.21.0; launch with /cortex-visualize.

Zetetic agent team for Cortex — 97 genius reasoning patterns from history's greatest minds + 19 team specialists (architect, engineer, code-reviewer, refactorer, …), 63 skills, 24 commands, 18 tools, 17 hooks, under one epistemic standard none of them can bypass. Composes with Cortex memory: every agent recalls/remembers through the Cortex MCP and routes via /genius, /agent, /zetetic, /quality, /research commands.