Cortex
技能 已验证 活跃Search and retrieve memories from Cortex persistent memory. Use when the user asks 'what did we decide about X', 'do you remember', 'what was the fix for', 'find that thing about', 'search memories', 'what do we know about', 'have we seen this before', or when you need context about past decisions, patterns, bugs, or architecture choices. Also use proactively when working on something that likely has relevant historical context.
To provide AI agents with a persistent, intelligent memory that reconstructs relevant context from past interactions and decisions, enhancing continuity and understanding across sessions.
功能
- Intelligent memory retrieval using WRRF engine
- Structured context assembly for long-horizon conversations
- Neuroscience-inspired memory mechanisms (forgetting, gating, reconsolidation)
- Local execution with PostgreSQL and pgvector backend
- Tools for hierarchical recall, causal chain tracing, and knowledge graph navigation
使用场景
- Use when needing context about past decisions, patterns, or fixes.
- Use proactively when starting work on a topic with likely historical context.
- Use to reconstruct agent context after session compaction or restarts.
- Use to explore project history and relationships via the knowledge graph.
非目标
- Storing memories in a proprietary format or external cloud service.
- Replacing the core LLM's reasoning capabilities; it augments them with memory.
- Providing general-purpose database functionality beyond memory management.
工作流
- Formulate a natural language query for memory retrieval.
- Optionally, specify filters like domain, tags, time range, or store type.
- Execute retrieval using `cortex:recall` or `cortex:recall_hierarchical`.
- Navigate related memories using `cortex:navigate_memory`.
- Trace causal chains using `cortex:get_causal_chain`.
实践
- Memory Management
- Context Reconstruction
- AI Agent Augmentation
- Local Data Processing
先决条件
- PostgreSQL 15+ with pgvector extension
- Python 3.10+
- Local execution environment
Errors
- info:Actionable error messagesWhile the SKILL.md outlines error paths conceptually, specific actionable error messages with remediation steps are not explicitly detailed.
安装
请先添加 Marketplace
/plugin marketplace add cdeust/Cortex/plugin install Cortex@cortex-plugins质量评分
已验证类似扩展
Orchestrate
100Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
Rag Architect
100Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.
Cortex Debug Memory
100Debug 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.
Memory Management
99AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.
Cortex Remember Global
99Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global rule', 'shared convention', 'infrastructure note', 'cross-project', or when the content is clearly universal (clean architecture, SOLID, deployment configs, server addresses).
Lean Ctx
100AI 代理的上下文运行时 — 包含 59 个 MCP 工具、10 种读取模式、95+ 种 shell 模式、支持 18 种语言的 tree-sitter AST。将 LLM 上下文压缩高达 99%。用于读取文件、运行 shell 命令、搜索代码或探索目录。如果不存在，则自动安装。