Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By cdeust
Give Claude Code persistent cross-session memory that automatically recalls past decisions, patterns, and project knowledge. Manage memories with scientific retrieval, maintenance pipelines, knowledge graphs, and cognitive profiling. Import from other AI tools and create linked wiki pages.
npx claudepluginhub cdeust/cortex --plugin cortexSet up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to automate memory behavior based on conditions.
Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or periodically to keep the memory system healthy. Also use after importing many memories or at the end of a long session.
Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality', 'rate this memory', 'restore checkpoint', 'undo', or when memories are returning incorrect or stale results.
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you need to understand the state of stored knowledge before a task.
Import memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories', 'import ChatGPT history', 'import from Gemini', 'transfer memories', or when Cortex detects another memory system is installed.
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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 (postgresql://[user[:pass]@]host[:port]/dbname). Leave as the default for a local install; set this to point Cortex at a remote or credentialed database. Your value persists across plugin updates.
${user_config.database_url}Persistent memory across Claude Code sessions using Cognis
Persistent local memory for Claude Code. Cross-session recall with vector search, automatic archiving, zero cloud dependencies.
Persistent memory for AI coding agents. Survives across sessions and compactions.
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
Universal memory runtime — cross-session cognitive memory for Claude Code. Remembers decisions, patterns, and context across coding sessions.
Persistent memory for Claude Code - store decisions, patterns, and context across sessions
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)
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Getting Started · Write Papers · What It Feels Like · Benchmarks · Science · Views
Companion projects:
cortex-beam-abstain — community-trained retrieval abstention model for RAG systems
zetetic-team-subagents — specialist Claude Code agents Cortex orchestrates with
automatised-pipeline — automated 11-stage pipeline (findings → PRs) that Cortex drives via run_pipeline
prd-spec-generator — stateless reducer that turns a feature description into a 9-file PRD (consumes Cortex memory + the pipeline's graph intel)
Claude Code forgets you every time you close the tab. Every architecture decision you explained. Every debugging session where you traced a bug through four layers of abstraction. Every "remember, we decided to use event sourcing, not CRUD" correction. Gone. Next session, you're a stranger to your own tools.
Cortex is a persistent memory engine for Claude Code built on computational neuroscience. It remembers what you worked on, how you think, what you decided and why. Not as a dumb text dump shoved into context, but as a living memory system that consolidates, forgets intelligently, and reconstructs the right context at the right time.
26 biological mechanisms. 49 MCP tools. 9 automatic hooks. Autonomous per-project wiki — 15 canonical scopes × 13 file sections, authored by a headless claude -p worker on a 6-hour cycle without you. Runs entirely on your machine. PostgreSQL + pgvector.
v3.17.0 — autonomous wiki curation: the wiki is no longer a memory dump but a self-curating per-project knowledge base. SessionStart auto-spawns a background consolidate every 6 hours; a headless authoring worker reads the curation-gap queue, calls codebase-intelligence MCP tools (codebase_context, codebase_impact, codebase_query) to ground the explanation in the actual call graph, then writes each missing section via claude -p (your existing credentials, no API key). Missing anchor pages — architecture / services / api / data-flow / operations / decisions / PRD — are authored from the source tree on demand. Every file-doc page exposes its remaining gaps inline with descriptions of what should go in each. Per-project wiki/_dashboards/<project>.md shows slot-fill rate every cycle. [[wiki/path]] cross-links resolve; mermaid diagrams have a 🔍 lens with zoom + pan. Release notes →