KERNEL github.com/dogum/kernel · Apache-2.0

Open source · Single file · Runs in your browser

A Python notebook that lives in one HTML file.

KERNEL is a complete notebook — cells, real Python, plots, DataFrames, a variable inspector, data mounting, .ipynb round-trip — built on Pyodide and packed into a single self-contained .html. No install, no build step, no server.

Open the file and you have a kernel. The core notebook stays local — Python runs in your tab. When you use the Agent, its active context goes directly to the model provider you select.

Pyodide downloads ~10 MB of WebAssembly on first run (cached after). Desktop browser recommended.

Three ways to use it

notebook · agent · mobile

KERNEL Live

The notebook itself. Write Python and markdown, run cells in execution order, get plots, interactive Plotly, rendered DataFrames, KaTeX math and Mermaid diagrams. Mount CSVs and files, inspect every variable, export to .ipynb — all client-side.

Launch KERNEL →

No account, no key, nothing to configure.

KERNEL Agent v2.3 Live

A durable notebook agent that plans, writes and runs cells, sees results, tracks lineage, and recovers safely after interruption. Bring an Anthropic, OpenAI, or xAI key; threads, artifacts, runs, checkpoints, outputs, and environment travel as one portable workspace.

Launch the Agent →

Bring your own key · Anthropic / OpenAI / xAI · read the spec

KERNEL·M Live

The Agent, rebuilt for your phone. A single-column notebook with the Agent, Files and Variables as bottom sheets and a bottom nav bar. Installs to the home screen as a Progressive Web App and keeps working offline after the first load. Bring your own key, same as the Agent.

Launch on mobile →

Installable · offline-capable · touch-first

What's in the box

capabilities

The kernel-notebooks skill

for Claude

A Claude skill that teaches the model to author exceptional notebooks for this runtime — well-structured, narrated analyses that use exactly the capabilities KERNEL has and none it doesn't. It's also the system prompt behind the agentic build: how to run the loop, read text and image outputs back, and explore with a human in the loop.

  1. Claude.ai: download kernel-notebooks.skill, then Settings → Capabilities → Skills → upload.
  2. Claude Code: copy the skill/ folder into your skills directory:
git clone https://github.com/dogum/kernel.git
cp -r kernel/skill ~/.claude/skills/kernel-notebooks