esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
它将ENISA的高层安全原则转化为具体、可操作的检查清单,并提供渐进式采用指导,覆盖从设计到报废的整个产品生命周期。
A practical collection of 22 Secure by Design and Secure by Default playbooks for SMEs, based on the ENISA Secure by Design and Default Playbook: A Practical Guide to Secure by Design and Default for SMEs.
Secure by Design represents a fundamental shift in product security, embedding protective measures from conception rather than retrofitting them post-development. Secure by Default ensures products ship with the most secure configuration reasonably possible, reducing reliance on user expertise and limiting the potential for misconfiguration.
This repository provides a list of playbooks that aims to bridge the gap between aspirational security principles and practical implementation within SME constraints. It provides structured, easy-to-follow checklists that development teams can apply during design, build, deployment, maintenance, and decommissioning.
The guidance is intended as a practical starting point rather than an exhaustive or prescriptive implementation framework. Its application should be adapted to the product’s intended use, context and associated risks, as well as applicable requirements. It does not provide legal guidance.
Each playbook contains:
Secure by Design embeds protective measures into products during development, rather than adding them retrospectively.
| Architectural Foundations | Operational Integrity |
|---|---|
| • Trust boundaries and threat modelling• Least privilege• Strong identity and authentication architecture• Attack surface minimisation• Defence in depth• Open design | • Life-cycle management• [User-centric design](playbooks/08-user-centric |
A practical collection of Secure by Design and Secure by Default playbooks for SMEs, based on the ENISA Secure by Design and Default Playbook.
根据分类、Topic 和编程语言匹配的相似项目。
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.