Clean baseline implementation of PPO using an episodic TransformerXL memory
A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.
Code for paper "Episodic Memory Deep Q-Networks" (https://arxiv.org/abs/1805.07603), IJCAI 2018
Lu, Q., Hasson, U., & Norman, K. A. (2022). A neural network model of when to retrieve and encode episodic memories. eLife
PyTorch implementation of Episodic Meta Reinforcement Learning on variants of the "Two-Step" task. Reproduces the results found in three papers. Check the ReadMe for more details!
NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory. CVPR 2023.
Psifr: Analysis and visualization of free recall data
A PyTorch library that replaces standard replay buffers with a learnable memory system.
Memory-centric architecture for scalable, energy-efficient AI agents and long-term cognition.
Stop your AI agent from repeating same mistake and learn from previous failures
Living Memory Dynamics - A novel framework for narrative-generating episodic memory with creative leaps. Features the Joshua R. Thomas Memory Equation.
A research-oriented Python framework implementing the DREAM architecture for long-term episodic memory in AI agents.
Persistent filesystem-based memory system for Claude Code. Pure MIF Level 3 compliant memory storage with YAML frontmatter, bi-temporal tracking, and proactive hooks. No dependencies - just markdown files and git.
Ignis is a locally-ran AI assistant that combines advanced cognitive memory systems with dynamic personality evolution - all while maintaining complete privacy on your hardware.
Local-first agent architecture separating episodic (events) and semantic (facts) memory, with provenance tracking, defense-in-depth LLM sanitization, and multilingual support via Qwen-2.5 + BGE-M3.
Pepper implementation of the cognitive architecture for Trust and Theory of Mind in humanoid robots applied to Vanderbilt's experiment.
ESTMS enables natural interaction with any VLM agent that learns from the conversation with the user and can help with everyday tasks.
Claude Codeプラグインマーケットプレイス。EpisodicRAG（階層的長期記憶）、EmailingEssay（AI駆動エッセイ配信）、VisualExpression（表情表現）の3プラグインを提供。
BIOMIND: A computational architecture integrating Global Workspace, Integrated Information, and Active Inference theories.
Add a description, image, and links to the episodic-memory topic page so that developers can more easily learn about it.
To associate your repository with the episodic-memory topic, visit your repo's landing page and select "manage topics."