Adaptive Memory Graph

STDIOregistry active

Summary

Gives Claude a persistent memory layer that survives across sessions using a weighted graph of knowledge nodes. Each node has a title, summary, tags, and connections to related concepts. Weights increase when nodes get accessed, decrease over time if unused, and eventually archive. The server exposes tools like amg_load_index for session startup, amg_expand_branch to pull full node content on demand, amg_get_connected_nodes for traversing relationships, and amg_log_session to record what was useful. Everything stores encrypted on disk with AES-256-GCM. Reach for this if you want Claude to remember project details, preferences, or domain knowledge between conversations without manual context pasting.

CodeRabbit

AI writes the code. CodeRabbit catches the slop.

Try For Free →

inference shell

create and run specialised agents in minutes

build now →

MCP-ready Email Sending

Plug Mailtrap into your AI workflow and let it handle the email.

Connect Mailtrap MCP →

Make your agent a DeFi expert

Agent, run crypto. Access onchain data & trade routes via 1inch.

Install now →

Capacitor - Shared memory for your team’s coding agents.

Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.

Try For Free →

CodeScene MCP Server

Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.

Try For Free →

Give your AI the whole web as clean markdown

Integrate web data into your AI product. One API to scrape website & brand data.

Get API Key Now →

belt - the only tool your agent needs

belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...

one prompt install →

CodeRabbit

AI writes the code. CodeRabbit catches the slop.

Try For Free →

inference shell

create and run specialised agents in minutes

build now →

MCP-ready Email Sending

Plug Mailtrap into your AI workflow and let it handle the email.

Connect Mailtrap MCP →

Make your agent a DeFi expert

Agent, run crypto. Access onchain data & trade routes via 1inch.

Install now →

Capacitor - Shared memory for your team’s coding agents.

Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.

Try For Free →

CodeScene MCP Server

Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.

Try For Free →

Give your AI the whole web as clean markdown

Integrate web data into your AI product. One API to scrape website & brand data.

Get API Key Now →

belt - the only tool your agent needs

belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...

one prompt install →

Adaptive Memory Graph

An MCP server plugin that gives Claude persistent, intelligent memory across sessions. It stores knowledge as weighted, interconnected nodes in a graph that evolves through conversation — nodes that get used gain weight, unused ones decay and eventually archive.

Works with Claude Code and Claude Desktop.

Features

Weighted memory nodes — Important memories stay prominent; stale ones fade
Cross-domain connections — Link related knowledge across topics
Time-based decay — Graph self-prunes so only relevant memories persist
Encrypted storage — AES-256-GCM encryption with macOS Keychain key storage
Session logging — Tracks which memories were accessed and how they were received
Domain organization — Nodes organized by domain (e.g. health_and_safety, personal, ideas_and_projects)
Chat history ingestion — Review and extract knowledge from past Claude Code sessions

Installation

pip install adaptive-memory-graph

Or with uv:

uv pip install adaptive-memory-graph

Setup

Claude Code

claude mcp add adaptive-memory-graph -s user -- amg-server

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "adaptive-memory-graph": {
      "command": "amg-server"
    }
  }
}

Config file location:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Tools

Tool	Description
`amg_load_index`	Load lightweight graph index at session start
`amg_expand_branch`	Fetch full node content when contextually relevant
`amg_get_connected_nodes`	Find related nodes across domains
`amg_log_session`	Log session summary at conversation end
`amg_update_graph`	Process pending logs and apply weight decay
`amg_export_report`	Generate human-readable graph summary
`amg_manual_adjust`	Boost, decay, archive, or delete nodes
`amg_add_node`	Add new nodes to the graph
`amg_search_nodes`	Search nodes by title, summary, tags, or content
`amg_list_chat_sessions`	List available Claude Code chat sessions for review
`amg_read_chat_session`	Read a chat session's conversation content

How It Works

Session start — Claude calls amg_load_index to get a lightweight summary of your memory graph
During conversation — If a topic is relevant, Claude expands specific nodes for deeper context
Session end — Claude silently logs which nodes were accessed and suggests new ones
Between sessions — Weight decay runs, archiving memories that haven't been useful

Nodes are stored as encrypted JSON on disk (~/.amg/graph.json.enc). The encryption key is stored in your macOS Keychain.

Requirements

Python 3.10+
macOS (for Keychain-based encryption key storage)

License

MIT

Featured

CodeRabbit

AI writes the code. CodeRabbit catches the slop.

Try For Free →

inference shell

create and run specialised agents in minutes

build now →

MCP-ready Email Sending

Plug Mailtrap into your AI workflow and let it handle the email.

Connect Mailtrap MCP →

Make your agent a DeFi expert

Agent, run crypto. Access onchain data & trade routes via 1inch.

Install now →

Capacitor - Shared memory for your team’s coding agents.

Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.

Try For Free →

CodeScene MCP Server

Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.

Try For Free →

Give your AI the whole web as clean markdown

Integrate web data into your AI product. One API to scrape website & brand data.

Get API Key Now →

belt - the only tool your agent needs

belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...

one prompt install →

Adaptive Memory Graph

Works with Claude Code and Claude Desktop.

Features

Weighted memory nodes — Important memories stay prominent; stale ones fade
Cross-domain connections — Link related knowledge across topics
Time-based decay — Graph self-prunes so only relevant memories persist
Encrypted storage — AES-256-GCM encryption with macOS Keychain key storage
Session logging — Tracks which memories were accessed and how they were received
Domain organization — Nodes organized by domain (e.g. health_and_safety, personal, ideas_and_projects)
Chat history ingestion — Review and extract knowledge from past Claude Code sessions

Installation

pip install adaptive-memory-graph

Or with uv:

uv pip install adaptive-memory-graph

Setup

Claude Code

claude mcp add adaptive-memory-graph -s user -- amg-server

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "adaptive-memory-graph": {
      "command": "amg-server"
    }
  }
}

Config file location:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Tools

Tool	Description
`amg_load_index`	Load lightweight graph index at session start
`amg_expand_branch`	Fetch full node content when contextually relevant
`amg_get_connected_nodes`	Find related nodes across domains
`amg_log_session`	Log session summary at conversation end
`amg_update_graph`	Process pending logs and apply weight decay
`amg_export_report`	Generate human-readable graph summary
`amg_manual_adjust`	Boost, decay, archive, or delete nodes
`amg_add_node`	Add new nodes to the graph
`amg_search_nodes`	Search nodes by title, summary, tags, or content
`amg_list_chat_sessions`	List available Claude Code chat sessions for review
`amg_read_chat_session`	Read a chat session's conversation content

How It Works

Session start — Claude calls amg_load_index to get a lightweight summary of your memory graph
During conversation — If a topic is relevant, Claude expands specific nodes for deeper context
Session end — Claude silently logs which nodes were accessed and suggests new ones
Between sessions — Weight decay runs, archiving memories that haven't been useful

Nodes are stored as encrypted JSON on disk (~/.amg/graph.json.enc). The encryption key is stored in your macOS Keychain.

Requirements

Python 3.10+
macOS (for Keychain-based encryption key storage)

License

MIT

Adaptive Memory Graph

Adaptive Memory Graph

Features

Installation

Setup

Claude Code

Claude Desktop

Tools

How It Works

Requirements

License

Adaptive Memory Graph

Adaptive Memory Graph

Features

Installation

Setup

Claude Code

Claude Desktop

Tools

How It Works

Requirements

License

Related AI & LLM Tools MCP Servers

Related AI & LLM Tools MCP Servers