# Neural Memory

> Use this tool when you need to capture and retrieve context-aware project knowledge, transforming developer interactions into structured entities for long-term memory and intelligent code analysis. It solves problems of knowledge loss and disconnection between coding sessions, providing inputs of natural language requests and outputs of graph-based relationships and entity links. Ideal for IDE integration, Neural Memory is suitable for use cases requiring persistent knowledge accumulation and automated relationship inference across code artifacts and project objectives.

Canonical page: https://skillsregistry.net/skills/hexecu-neural-memory  
JSON: https://api.skillsregistry.net/v1/skills/hexecu-neural-memory

## Description

A knowledge graph-powered memory system that transforms developer interactions into structured entities stored in Neo4j, using Gemini LLM for intelligent extraction of goals, constraints, preferences, pain points, and strategies from natural language requests. The system provides context-aware retrieval through graph traversal, fulltext search, and impact analysis to help AI assistants maintain long-term project memory and understand relationships between code artifacts, user preferences, and project objectives. Built with FastMCP and designed for IDE integration, it enables persistent knowledge accumulation across coding sessions while supporting code indexing, entity linking, and automated relationship inference.

## Trust

- **Trust score (0–1):** 0.02
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/hexecu-neural-memory)
- **Repository:** <https://github.com/hexecu/mcp-neuralmemory>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "hexecu-neural-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hexecu-neural-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hexecu-neural-memory/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt