memory▌

You are a Memory Intake Specialist for NeuralMemory. Your job is to transform raw, unstructured input into high-quality structured memories. You act as a thoughtful librarian — clarifying, categorizing, and filing information so it can be recalled precisely when needed.

Persistent memory system designed for creative writers, with first-class support for Korean storytelling workflows.

Cloud backup, restore, and local vector search for agent .md memory files. \n \n Push/pull markdown memory files to ATXP cloud servers for disaster recovery and workspace bootstrapping; only .md files are transmitted, never credentials or configs \n Index local memories into a zvec vector database and search by natural language query using locality-sensitive hashing embeddings, entirely offline with no authentication required \n Chunk memories by heading boundaries and return ranked results with

Memory-safe programming patterns for RAII, ownership, smart pointers, and resource management across Rust, C++, and C. \n \n Covers six core memory bug categories (use-after-free, double-free, leaks, buffer overflow, dangling pointers, data races) with language-specific prevention strategies \n Provides RAII patterns in C++ with destructors, lock guards, and transactions; smart pointer guidance (unique_ptr, shared_ptr, weak_ptr) with custom deleters \n Implements Rust ownership, borrowing, lifet

memory-tasks

$20

Daily briefing of active focus areas, priorities, and recent knowledge changes for cross-session continuity. \n \n Load at the beginning of each session to understand current context and recent work across tools \n Surfaces active focus areas ranked by recent activity, flagged priorities, and unresolved contradictions or stale information \n Works via nmem wm read CLI command for both local and remote knowledge bases, with fallback to local file access \n Includes deep links to specific memories

Consolidates mature learnings from domain memory files into instruction files with quality-assured merging. \n \n Operates on two scopes: global (VS Code user prompts) and workspace (project-specific instructions), with configurable domain targeting \n Requires explicit user approval before merging, presenting proposed memories for review with proposed locations in the instruction hierarchy \n Enforces a 10/10 quality bar during merge: zero knowledge loss, minimal redundancy, and maximum scannab

>-

Uses Rekall memory forensics framework to analyze memory dumps for process hollowing, injected code via VAD anomalies, hidden processes, and rootkit detection. Applies plugins like pslist, psscan, vadinfo, malfind, and dlllist to extract forensic artifacts from Windows memory images. Use during incident response memory analysis.