Skip to content
#

engram

Here are 20 public repositories matching this topic...

tensorflow-engram: A Python package for Engram Neural Networks, adding biologically-inspired Hebbian memory and engram layers to TensorFlow/Keras models, supporting memory traces, plasticity, attention, and sparsity for neural sequence learning.

  • Updated Aug 7, 2025
  • Python

Cognitive augmentation layer and Multi Agent system for Claude Code via MAX plan or API. Adds persistent memory, parallel threads of reasoning, semantic bridges between concepts and preservation of context re-injected on an Engram format. Can operate in multi-agent with cognitive inter-agent communication, stdin injection, zero API key. Local only.

  • Updated Feb 25, 2026
  • Rust

本项目是一个基于 MuZero 和 Gumbel 搜索构建的三人八子棋(Eight-in-a-Row)AI 训练与对弈系统。该系统采用了 DeepSeek MLA 作为网络骨干,并深度集成了课程学习(Curriculum Learning)、联赛机制(League)、基于种群的训练(PBT)、Engram 情节记忆以及 EfficientZero 的一致性损失等高级强化学习技术。此外,项目支持同步与多进程异步训练,并提供了基于 FastAPI 的实时对弈服务以及基于 WebSocket 的可视化训练监控台。

  • Updated Feb 25, 2026
  • Python

Improve this page

Add a description, image, and links to the engram topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the engram topic, visit your repo's landing page and select "manage topics."

Learn more