repowiserepowise

MCP server

goniszewski / grimoire

Bookmark manager for the wizards 🧙

★ 2,891stars on GitHubTypeScriptMIT

This connects Repowise to goniszewski/grimoire's code. It does not install grimoire.

Repowise maps public repos from their source. Not affiliated with goniszewski. What is Repowise?

github.com/goniszewski/grimoireIndexed at 5323001

What is grimoire?

grimoire is a local-first bookmark manager for people who save technical resources and need to find them later. It saves links, imports browser bookmarks, extracts readable content, and searches by keyword or meaning, with optional AI providers that can summarize and organize the library. Saved bookmarks are processed through a durable SQLite job queue and the data stays on the user's machine. Its main language is TypeScript. To install it, run git clone https://github.com/goniszewski/grimoire.git and follow the steps below. Its code health is 6.6 out of 10 (Fair), ranked #167 of 4,000+ indexed repos. The last commit to grimoire was on Aug 3, 2026, and 1 person has contributed.

As of commit 5323001, indexed Aug 13, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsgrimoire.md

Repo facts: type, license, health, rank, contributors
grimoire facts
TypeMCP server
LicenseMIT
Code health6.6 / 10 (Fair)
Health rank#167 of 4,000+ indexed repos
Last commitAug 3, 2026
Contributors1
Bus factor1
Size542 files, 105,276 lines

Install grimoire

Commands copied from the README

  1. 1Clone the grimoire repository.
    git clone https://github.com/goniszewski/grimoire.git
  2. 2Move into the grimoire folder.
    cd grimoire
  3. 3Clone the repository and install the root dependencies with npm.
    npm install
  4. 4Install the daemon dependencies with Bun from the daemon directory.
    cd daemon && bun install
  5. 5Start the daemon in its own terminal.
    npm run daemon:dev
  6. 6Start the frontend in a separate terminal and open the Vite app.
    npm run dev

Releases on GitHub (latest v1.4.0, Nov 18, 2026)

Full install notes on GitHub

Explore grimoire

Ask about this code in your agent

This connects Repowise to grimoire's code. It does not install grimoire. To install grimoire, use the install steps.

Useful if you want to change or fork grimoire: your agent can ask how it is put together and get answers that cite its files.

Ask about grimoire

Answers come from grimoire's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of goniszewski/grimoire from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

goniszewski/grimoire FAQ

What is grimoire?

grimoire is a local-first bookmark manager for saving technical links, importing browser bookmarks and extracting readable content. Your data stays on your machine.

How does grimoire work?

grimoire runs a React frontend and a Bun and Hono daemon backed by SQLite. Saving a URL queues a job that fetches the page, extracts its text and updates the search indexes.

How do I install grimoire?

grimoire can run from a source checkout by installing npm dependencies, installing daemon dependencies with bun and starting the daemon and frontend. Docker Compose is also documented. See the install steps

What language is grimoire written in?

grimoire is written mainly in TypeScript, with some JavaScript, shell scripts and a Dockerfile.

How is the grimoire code organized?

grimoire splits its code into a frontend in src/ and a Bun daemon in daemon/. The daemon's HTTP and MCP servers are in daemon/src/server.ts and daemon/src/mcp/server.ts.

Who is grimoire for?

grimoire is for people who save technical resources and need to find them later. It keeps the library local and works without AI providers.

What license does grimoire use?

grimoire uses the MIT license, identified as MIT.

Code health

6.6out of 10Fair

Hotspots average 5.1, the place fixes pay off most.

On the leaderboards:#52 of 66 TypeScript repos

Key features of grimoire

  • Saves public http and https URLs from the app, the API, MCP, the import flow or a browser bookmarklet.
  • Extracts readable content from web pages, PDFs, GitHub repositories and issues, StackOverflow pages and YouTube metadata and transcripts where available.
  • Searches with SQLite FTS5 keyword search, semantic embedding search or a hybrid ranking mode.
  • Runs without AI providers and supports optional ones such as OpenAI, Ollama and Anthropic.
  • Creates, verifies, encrypts and restores local backup snapshots.

How goniszewski/grimoire works

Input enters through the React frontend under src/, the HTTP API, the MCP endpoint, the import flow or the browser bookmarklet. The daemon under daemon/ is built on Bun, Hono and SQLite and listens on 127.0.0.1:3210 by default. Its entry points include daemon/src/index.ts, daemon/src/server.ts and daemon/src/mcp/server.ts. The REST contract is defined in daemon/src/api/contract.ts, and daemon/src/routes/backup.ts holds the backup routes. Each saved URL is queued, fetched, turned into readable text and indexed, with optional AI enrichment and embeddings applied afterwards.

The codebase has 542 files and 2,232 symbols in 6 modules, led by TypeScript, JavaScript and Shell. Code health is 6.6 out of 10, rated fair.