A browser-native, local-first workspace for reading, experimenting, and creating with AI, powered by pi.
Try Gamma Reader. Import documents into your browser; no account is needed for browser-only projects.
The app opens on a Tutorial project that shows every feature in use; its chapters are also readable in tutorial/.
- Read PDF, Word, Excel, CSV, Markdown, HTML, images and source code in tabs, each with the controls its format allows.
- Write Markdown with formulas, diagrams and images, and save it in the browser.
- Link notes by name with
[[…]], see what links back, and embed one note, section or passage in another. - Run code in Labs, Markdown with Scheme, Clojure, Python and TypeScript cells, and embed p5 sketches and HTML pages at any size.
- Ask the assistant about what you read: it searches and reads your files, compares sources, runs Lab cells, searches the web when allowed, and writes notes. Its agent loop runs in the browser.
- Organise files in projects, bring in folders and links, and keep a project in step with a source.
| Mode | Start here | Save back |
|---|---|---|
| Browser only | Open the online reader and add files, a folder or a URL | Export files to your computer |
| Remote git repository | Configure a server to keep pulling a clone | Read-only by default; GAMMA_SOURCE_PUSH=1 enables commit and push |
| Local git working tree | Run npx gamma-reader in your checkout |
Save above Files writes to disk; you commit and push with git |
All three keep a copy of the imported or synced documents in this browser's IndexedDB. Adding a folder is a one-time import with filters; connecting a source keeps the copy in sync.
The online reader needs nothing installed. For a local working tree, install Node 24 and git, then run:
npx gamma-reader # the current folder, at http://127.0.0.1:3302
npx gamma-reader ~/notes --exclude tmp,output # or name one; --help lists the optionsThe project is named after the folder, which must belong to a git working tree. Chat uses GLM_API_KEY or DEEPSEEK_API_KEY from the process environment, or a model added in the reader. npx does not load .env automatically; see Configuration for loading it and setting chat allowances.
Previewing, parsing, searching and the pi agent loop run in the browser. A connected source can also hold your documents on disk or in a repository. AI inference runs at the model provider: on the shared allowance through a Node proxy that holds the credentials but stores no conversation content, and with a reader's own key straight from the browser. Web search queries go through the server to Tavily. See Your data and models for what leaves the browser.
Use Node 24 and pnpm 10.14.0.
corepack enable
pnpm install
pnpm devOpen http://localhost:5302. Reading, editing, and experiments work without keys; chat needs GLM_API_KEY, DEEPSEEK_API_KEY, or both in an untracked root .env, or a reader's own model. To read a working tree with the code as it is, name it when starting:
GAMMA_SOURCE_NAME=notes GAMMA_SOURCE_WORKTREE=$HOME/notes pnpm devpnpm check runs Biome, TypeScript, and package tests without rewriting source. Tests do not call external model services. AGENTS.md describes the packages and how the web source is layered, and Self-hosting lists every variable and covers deploying with Docker and releasing a version.
The independent React Code Lab package lives in ui-packages/code-lab. Run its standalone examples with pnpm --filter @gamma-reader/code-lab-playground dev.
tutorial/ ships with each deployment and is served at /api/tutorial, listed afresh on each request. Every reader has a Tutorial project kept in step with it: a first visit opens it, and after a deployment that changes the folder, the project offers Update. To write for it, edit the folder and run pnpm dev; the open Tutorial offers the change at once. Add a section to What's new.md when a release adds a feature.