KaimonSlate.jlReactive Julia notebooks, in the browser

A live, reactive notebook that edits a plain .jl file — with @bind widgets, ECharts & Makie figures, a built-in timeline, and an AI agent that builds cells alongside you.

Get Started

The AI Agent

GitHub

Reactive by construction

Cells form a dependency DAG. Change a value and every downstream cell restales and recomputes automatically — no manual "run all", no stale state hiding in the kernel.

Real @bind widgets

Widgets are ordinary Julia constructors — Slider(1:hi), Toggle, Select, ColorPicker, … — so their arguments can be dynamic. Bind a control in one cell, read it in others, and watch them re-render live.

An AI agent that builds cells

A chat pane drives the notebook through the same tools you do — adding, editing, and running cells one at a time. Scope a turn to a single cell with ✨, reference cells by @id, and pick Sonnet, Opus, Haiku, or a local Ollama model.

Interactive figures

ECharts for interactive, in-browser charts that animate on reactive updates; CairoMakie for static scientific figures. Both flow through one image interface — so the agent can see your plots, and exports embed them.

A built-in timeline

Every edit is captured to a durable, content-addressed history. Scrub the rail, diff any checkpoint, restore non-destructively, or ▶ replay the whole buildup of the notebook.

Plain .jl, shared with your editor

The notebook IS a .jl file. Edits round-trip through it, so VS Code, git, and the agent all see the same source. Export a self-contained HTML document (or print to PDF) when you're done.

Publish to the web

Turn notebooks into a site or blog — each lands at its own URL behind a generated front page. One build deploys to GitHub Pages, Cloudflare, Netlify, S3, or your own server, and you can archive a citable DOI to Zenodo at milestones.

KaimonSlate.jl

KaimonSlate is a reactive notebook for Julia that runs in your browser and edits a plain .jl file. It is built as a Kaimon extension: cells evaluate in a per-notebook gate worker, the browser stays in sync over server-sent events, and an AI agent can drive the notebook through the same tool surface you use.

Every cell's output always reflects its current inputs. Cells declare what they read and write; KaimonSlate builds a dependency graph and recomputes exactly the cells affected by a change — so nothing silently goes stale.

Quick start

Install Kaimon — the recommended runtime, which gives each notebook its own worker and powers the AI agent — then install the slate app from the Pkg REPL:

julia

pkg> app add KaimonSlate      # puts a `slate` launcher on your PATH

Run it:

slate my_analysis.jl          # start the hub, open the notebook, show a status TUI

On first run slate offers to register as a Kaimon extension (so the agent gets the slate.* tools). No Kaimon? slate --own runs standalone. See Installation and Getting Started.