Send voice notes to Telegram → get organized knowledge base, tasks in Todoist, and daily reports. Persistent memory with Ebbinghaus decay, vault health scoring, knowledge graph. Runs on Claude Code + OpenClaw. 5/mo.

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

用Vue写的高效背单词App，方法来自《17天搞定GRE单词》

A Parametric Framework to Generate Visual Illusions using Python

💠 单词智能复习项目 - 艾宾浩斯遗忘曲线 + 混淆词

Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.

Typed memory layer for always-on agents (Claude Code, OpenClaw, Hermes, Codex). Schema-as-code for any Obsidian vault: decay engine, health scoring, link repair, MOC generation.

My Solutions for LeetCode problems schedule according to Ebbinghaus forgetting curve.

A (self-hosted) trainer (software / program) to memorize flashcards (question-answer cards) in a webbrowser.

Ebbinghaus memory method helper. / 辅助记忆的 TODO 任务管理应用

The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.

Claude Code plugin for full-lifecycle Obsidian knowledge management — vault lint, Karpathy-style query, Ebbinghaus spaced repetition, article ingestion, and GitHub sync.

AEGIS — Agentic AI Learning Platform with Epistemic State Modeling, Ebbinghaus Forgetting Curve, and Cognitive DNA Adaptation.

在Mac上自动生成一个TXT文件，记录学习内容并且提醒复习

Ebbinghaus Memo app for storing plain text for repetitions at regular intervals to achieve incredible levels of assimilation of new knowledge

Simulate Ebbinghaus Forgetting Curve to Manage LLM Memory

Production-ready long-term memory server for AI agents. Built on memU with Ebbinghaus decay, strength-weighted retrieval, and 100% local LLM support.

Persistent memory for AI tools. Give Claude, Cursor, and Codex shared context that survives across sessions.

Enable seamless Telegram access to Claude Code for natural, context-aware coding help, editing, and project notifications from any device.