# claude-total-memory

> Use this tool when you need to retain and visualize knowledge from code interactions, leveraging auto-extracted knowledge graphs and multi-representation embeddings for enhanced understanding. It solves problems of information loss and complexity, providing a self-hosted solution with optional Ollama integration. Ideal for use with Claude Code and Codex CLI, particularly when working with git repositories.

Canonical page: https://skillsregistry.net/skills/vbcherepanov-claude-total-memory  
JSON: https://api.skillsregistry.net/v1/skills/vbcherepanov-claude-total-memory

## Description

Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL   ▎  visualization. LongMemEval R@5=97.45%. Self-hosted, Ollama-optional

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [GitHub](https://github.com/vbcherepanov/claude-total-memory)

## 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": "vbcherepanov-claude-total-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vbcherepanov-claude-total-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vbcherepanov-claude-total-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