Lab Brain for Claude Science
I built Lab Brain, a tool that turns any biomedical lab project — its code, slides, data, papers, and notes — into a shared knowledge base that both Claude Science and Claude Code can read and write.
Core trick
Shared folder conventions with claim-before-edit handoff boards and append-only logs let Claude Code and Claude Science edit one lab knowledge base concurrently.
Description
I built Lab Brain, a tool that turns any biomedical lab project — its code, slides, data, papers, and notes — into a shared knowledge base that both Claude Science and Claude Code can read and write. Everyone on a project works at the same time from their own Claude environment, and all of a project's knowledge ends up in one place instead of scattered across people's heads, chats, and folders.
Most of the work went into creating the folder and file structures and skill/command frameworks that hold that together, which I iterated on from my own lab's practices. A START_HERE page always shows the latest updates linked to their files, clickable in Obsidian; some files get overwritten to the current state while others are append-only and keep growing, so nothing is lost. Handoff boards let people claim a file before editing so no one overwrites anyone else, and give mentees a scaffold plus a feedback loop with their mentors. Figures are named by content and logged in a registry, and old work is archived rather than deleted.
Claude Science is a state-of-the-art harness, but it doesn't have a shared knowledge base — and research knowledge usually fragments across individuals working separate tasks. So I wanted to pull everything into one place that keeps growing, where people can build on each other's work, decide directions, and see what everyone's doing without losing context.
README excerpt
# 🧠 Lab Brain **A proven framework for how a whole lab runs a shared knowledge base — where to document, how to save, how to hand off, how to make figures and build the storyline, and how mentees collaborate and report to mentors — packaged so any lab can adopt it on Claude Code + Claude Science.** > Built for **Built with Claude: Life Sciences** (Builder track). Lab Brain isn't a chatbot over your > files — it's the **conventions + accessory tools** that let a whole team (peers *and* undergrads) > contribute to **one shared, cited knowledge base** without stepping on each other. Every claim is > traceable to its source, including the numbers that live only inside a figure panel. [](https://github.com/bobbyni819/lab-brain/actions/workflows/ci.yml) [](./LICENSE) · Claude Code + Claude Science · Python 3.12 · 40 tests, hermetic  > The image above is a still from **[`docs/showcase.html`](./docs/showcase.html)** — a self-contained > interactive walkthrough (open in any browser: click a file to watch it get sorted, flip the > peers/mentee toggle, explore the routing map). Prefer to just flip through it? A printed > **[PDF walkthrough](./docs/lab-brain-walkthrough.pdf)** is in the repo. --- ## Why this exists Every lab loses knowledge for the same reason: **not becaus