slvDev
Featured
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.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It is notable as a practical, minimalist example of a research talk built with Quarto, and it explicitly states that the slides themselves were drafted by coding agents, making it a concrete demonstration of the workflow it discusses.
Who it is for
- Researchers interested in using AI coding assistants
- Data scientists and epidemiologists using computational workflows
- Academics preparing reproducible talks or presentations
- Quarto users looking for slide project examples
Use cases
- Learning how coding agents can assist in drafting research presentations
- Reusing the Quarto project structure for conference or lab meeting talks
- Demonstrating AI-assisted research workflows to colleagues or students
- Adapting the included layout, partials, and figures for other slide decks
Strengths
- Clear and simple project layout with separated content sections
- Automated build, preview, and validation tasks via Task or Quarto
- Includes a hosted rendered version for easy viewing
- Directly relevant to current conversations about AI in research workflows
Considerations
- The repository is slides rather than a reusable tool or library
- Requires familiarity with Quarto and optionally Task for local building
- The README provides no in-depth technical detail beyond build and file layout
README quick start
How I am LLM
Slides for a 15-minute talk on integrating coding agents into research workflows.
Sam Abbott, London School of Hygiene & Tropical Medicine, 30 July 2026.
Rendered: samabbott.co.uk/how-I-llm
Building
Requires Quarto and, optionally, Task.
task # render to _site/
task preview # live-reloading preview
task check # validate the Quarto project
Layout
index.qmd— title slide, talk plan, and section includes_partials/— one file per sectionfigures/— figures, including the model diagram from BVDOutbreakSizestyle.css— presentation styling
These slides were themselves drafted by coding agents; the final section describes how.
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
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.