# Adaptive Memory Graph

> Use this tool when you need to retain information across sessions and provide Claude with persistent memory. It solves the problem of knowledge loss between interactions by storing information in a weighted knowledge graph, where important memories are prioritized and stale ones are decayed over time. The Adaptive Memory Graph takes in chat history and session logs as inputs and outputs a continuously updated knowledge graph, making it ideal for use cases requiring long-term memory and contextual understanding.

Canonical page: https://skillsregistry.net/skills/raskolnikovdd-adaptive-memory-graph  
JSON: https://api.skillsregistry.net/v1/skills/raskolnikovdd-adaptive-memory-graph

## Description

Gives Claude persistent memory across sessions through a weighted knowledge graph. Stores information as interconnected nodes organized by domain, with important memories gaining weight and stale ones decaying over time. Features encrypted storage via macOS Keychain, session logging, cross-domain connections, and chat history ingestion from Claude Code sessions.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/raskolnikovdd-adaptive-memory-graph)
- **Repository:** <https://github.com/raskolnikovdd/adaptive-memory-graph>

## 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": "raskolnikovdd-adaptive-memory-graph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/raskolnikovdd-adaptive-memory-graph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/raskolnikovdd-adaptive-memory-graph/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