sujee/visual-stories

Open-source, reproducible visual explainers for AI and software concepts. Watch them. Reproduce them. Remix them.

Python

0

28 commits

updated Oct 5, 2026

See the code

See what people are saying

README

Visual Stories

Open-source, reproducible visual stories for AI, software, and technical concepts.

Watch them. Reproduce them. Remix them.

▶ YouTube Playlist

Browse the stories · Reproduce one · Create your own

The code and templates are licensed under Apache-2.0, and the original videos and soundtracks under CC BY 4.0. If you build something cool with them, a link back is always appreciated (not required). Most of the projects here are open source, unless noted otherwise.

Working with Agents

AGENTS.md

Explore and reproduce

Each visual story is self-contained.

On your own:

git clone https://github.com/sujee/visual-stories.git
cd visual-stories/projects/neural-network-training
# install the prerequisites listed in its README.md, then:
./render.sh          # all deliverables, final quality (4K, takes a while)
./render.sh draft    # quick draft preview

With a coding agent: start it in the story's folder (or the repository root) and ask:

Read AGENTS.md and README.md. Install the prerequisites and render the final video.

Create a new story

Start a coding agent in the repository root (the new story's folder doesn't exist yet) and ask, for example:

Create a new story about prefill vs decode.

The agent starts by writing a brief.md for you to review, then renders drafts (v1, v2, …) for your feedback. Once you approve a version, ask it to prepare the Repro Bundle before committing.

Or start by hand: copy templates/story/ to projects/<name>/ and fill in the placeholders.

Stories

All the videos are in one YouTube playlist.

PublishedStoryWhat it's aboutWatch
2026-10-05linux-historyLinux at 35. from "just a hobby" post to running the cloud, phones and MarsVideo · Short · release
2026-10-03jev-vs-llmJev, TypeSafe AI's "System One" model, vs. a chat LLMVideo · Short · release
2026-09-27neural-network-trainingHow a neural network learnsVideo · Short · release
2026-09-27neural-network-training-cartoonThe same story in a bright cartoon styleVideo · Short · release
animated-visualization
explainer-video
visualization

sujee/visual-stories

Open-source, reproducible visual explainers for AI and software concepts. Watch them. Reproduce them. Remix them.

Python

0

28 commits

updated Oct 5, 2026

See the code

See what people are saying

README

Visual Stories

Open-source, reproducible visual stories for AI, software, and technical concepts.

Watch them. Reproduce them. Remix them.

▶ YouTube Playlist

Browse the stories · Reproduce one · Create your own

The code and templates are licensed under Apache-2.0, and the original videos and soundtracks under CC BY 4.0. If you build something cool with them, a link back is always appreciated (not required). Most of the projects here are open source, unless noted otherwise.

Working with Agents

AGENTS.md

Explore and reproduce

Each visual story is self-contained.

On your own:

git clone https://github.com/sujee/visual-stories.git
cd visual-stories/projects/neural-network-training
# install the prerequisites listed in its README.md, then:
./render.sh          # all deliverables, final quality (4K, takes a while)
./render.sh draft    # quick draft preview

With a coding agent: start it in the story's folder (or the repository root) and ask:

Read AGENTS.md and README.md. Install the prerequisites and render the final video.

Create a new story

Start a coding agent in the repository root (the new story's folder doesn't exist yet) and ask, for example:

Create a new story about prefill vs decode.

The agent starts by writing a brief.md for you to review, then renders drafts (v1, v2, …) for your feedback. Once you approve a version, ask it to prepare the Repro Bundle before committing.

Or start by hand: copy templates/story/ to projects/<name>/ and fill in the placeholders.

Stories

All the videos are in one YouTube playlist.

PublishedStoryWhat it's aboutWatch
2026-10-05linux-historyLinux at 35. from "just a hobby" post to running the cloud, phones and MarsVideo · Short · release
2026-10-03jev-vs-llmJev, TypeSafe AI's "System One" model, vs. a chat LLMVideo · Short · release
2026-09-27neural-network-trainingHow a neural network learnsVideo · Short · release
2026-09-27neural-network-training-cartoonThe same story in a bright cartoon styleVideo · Short · release
animated-visualization
explainer-video
visualization