
Adaptive Memory Graph
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.
- tools
- 11
- transport
- STDIO
- last updated
- Mar 11, 2026
Tools
11 toolsPublic tool metadata for what this MCP can expose to an agent.
amg_load_indexLoad lightweight graph index at session start
Load lightweight graph index at session start
No parameter schema in public metadata yet.
amg_expand_branchFetch full node content when contextually relevant
Fetch full node content when contextually relevant
No parameter schema in public metadata yet.
amg_get_connected_nodesFind related nodes across domains
Find related nodes across domains
No parameter schema in public metadata yet.
amg_log_sessionLog session summary at conversation end
Log session summary at conversation end
No parameter schema in public metadata yet.
amg_update_graphProcess pending logs and apply weight decay
Process pending logs and apply weight decay
No parameter schema in public metadata yet.
amg_export_reportGenerate human-readable graph summary
Generate human-readable graph summary
No parameter schema in public metadata yet.
amg_manual_adjustBoost, decay, archive, or delete nodes
Boost, decay, archive, or delete nodes
No parameter schema in public metadata yet.
amg_add_nodeAdd new nodes to the graph
Add new nodes to the graph
No parameter schema in public metadata yet.
amg_search_nodesSearch nodes by title, summary, tags, or content
Search nodes by title, summary, tags, or content
No parameter schema in public metadata yet.
amg_list_chat_sessionsList available Claude Code chat sessions for review
List available Claude Code chat sessions for review
No parameter schema in public metadata yet.
amg_read_chat_sessionRead a chat session's conversation content
Read a chat session's conversation content
No parameter schema in public metadata yet.
Sponsors
Readme
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
Details
- Repository
- github.com/raskolnikovdd/adaptive-memory-graph
- Categories
- AI & LLM Tools, Documents & Knowledge
- Package
adaptive-memory-graph- Transport
- STDIO
- Registry
- MCP registry, active