state-memory-mcp
Active·★ 48·MIT·Updated 2026-10-03
@putervision/state-memory-mcp is a zero-infrastructure, deterministic Model Context Protocol (MCP) server designed to provide AI coding assistants with a structured, persistent SQLite graph for tracking workflow state. It offers efficient context management, reduces latency by offloading to a local database, and supports multi-agent collaboration with a shared blackboard.
#State Management#Context Management#SQLite#AI Development#Multi-Agent#Workflow Automation#Local-first#TypeScript
01
Features
01Deterministic State Memory & Compact TaskSlices for fast evaluation
02Efficient Context Management & Decision Thresholding to prevent graph bloat
03Multi-Agent Blackboard for shared context and parallel subagent updates
04100% Local & Private architecture, ensuring all state stays within your workspace
05Interactive 3D Visualizer for graph exploration
02
Compatibility
Node.js
Runtime
Verified via docs
TypeScript
Language
Verified via docs
SQLite
Database
Verified via docs
AI Coding Assistants
Integration
Verified via docs
VS Code
IDE
Verified via docs
03
Quick start
1
$ npm install -g @putervision/state-memory-mcp
2
$ state-memory-mcp init
04
Use cases
↳Providing persistent workflow state to AI coding assistants like Cursor and Copilot
↳Managing context and decision-making for autonomous agents
↳Facilitating multi-agent collaboration on complex tasks with a shared context store
↳Auditing and tracing agent activities with a tamper-evident event ledger
↳Improving agent efficiency and reducing latency in task retrieval and context processing
05
Alternatives
mcp-local-memory★ 60
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
sqlite-memory-mcp★ 18
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
squish-memory★ 12
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
mnemosyne★ 151
Evidence-backed memory for AI agents: local-first recall, temporal history, tested skills, and gradual migration.
projectmem★ 868
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
AgentRecall-X★ 371
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
Comments
Log in to leave a comment
No comments yet. Be the first!