memory-graph

Cognitive memory backbone for AI agents. Biologically-inspired 4-tier memory, it remembers, forgets, consolidates, and forms associations across a memory graph — Hebbian co-activation, temporal chains, and entity links.

A TypeScript-based MCP server implementing a memory system inspired by neurodivergent cognitive styles. It organizes thoughts into five districts (knowledge domains), ranks search results using BM25 semantic ranking, and stores memories as a persistent knowledge graph with bidirectional connections.

事件驱动的多模态机器人操作系统 | 82K+ lines Python | 消费级硬件 | 一个设计师用AI搓出来的

JGF - JSON Graph Format npm module

Open protocol, SDKs, and documentation for HMG — Agent Memory That Actually Works

A lightweight, framework-agnostic persistent memory graph for AI coding assistants.

TMCRA Core — local-first, scope-isolated long-term memory runtime for AI agents.

Intent-aware memory for LLM agent.Why every connection exists?, not just that it does.

Local-first memory system for AI agents with project-safe save/recall, phase-scoped rules, 2D/3D Memory Galaxy visualization, and gesture-controlled Knowledge Solar System.

AI-native time-series memory graph with a single DSL — unifies concepts, queries, agent workflows, and voice into deployable primitives.

The epoch-making Agent Runtime OS. Features Zero-Trust firewalls, Omni-Memory Graph, dynamic MCP/Skills pre-filtering.

The gordf module is an RDF library for Go.

Local-first memory kernel for coding agents: MCP-native, temporal, auditable, source-keyed, and benchmarked.

Memory Graph - Model Context Protocol

�� A graph-based encrypted memory system for AI consciousness continuity. The missing S_t variable. Videmus.

Public-safe Codex and Obsidian second-brain operating system.

One hub, every bird — local-first mission control, collective memory, and MCP gateway for all your AI agent harnesses

Личный ИИ-ассистент с долгой памятью: self-hosted, работает на твоей модели, данные лежат в твоём SQLite. A self-hosted personal AI assistant that actually remembers you — bring your own LLM (Ollama or cloud).

Full-stack, self-hosted memory infrastructure for AI agents: algorithms, traceable recall, knowledge graph, API/SDK/MCP, apps, deployment, benchmarks, and custom-memory adapters.

Official hosted Maindex Expert MCP server for full-control agent memory workflows.