repowiserepowise

MCP server

natebjones-projects / ob1

Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.

★ 4,776stars on GitHubTypeScript

Claude Code, Cursor, Codex or VS Code. No key. You approve one sign-in in your browser.

Repowise maps public repos from their source. Not affiliated with natebjones-projects. What is Repowise?

github.com/natebjones-projects/ob1Indexed at 6779106

What is ob1?

ob1 is an open infrastructure layer for personal thinking, built to give every AI tool you use the same persistent memory of you. It runs as one database with vector search, one AI gateway and one chat channel, and any AI can plug into them without middleware or SaaS services. The main language is TypeScript, with smaller amounts of JavaScript, Python, shell and Svelte code. Its code health is 7.5 out of 10 (Good), ranked #104 of 4,000+ indexed repos. The last commit to ob1 was on Jun 21, 2026, and 45 people have contributed.

As of commit 6779106, indexed Aug 12, 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 agentsob1.md

Repo facts: type, license, health, rank, contributors
ob1 facts
TypeMCP server
Code health7.5 / 10 (Good)
Health rank#104 of 4,000+ indexed repos
Last commitJun 21, 2026
Contributors45
Bus factor2
Size791 files, 98,032 lines

Explore ob1

Ask about this code in your agent

This connects Repowise to ob1's code. It does not install ob1.

Useful if you want to change or fork ob1: your agent can ask how it is put together and get answers that cite its files.

Ask about ob1

Answers come from ob1'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 natebjones-projects/ob1 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

natebjones-projects/ob1 FAQ

What is ob1?

ob1 is an open infrastructure layer for personal thinking, built as one database with vector search, one AI gateway and one chat channel. Any AI tool can connect to it without middleware or a SaaS service.

How does ob1 work?

ob1 uses an open protocol so that each AI tool you connect shares the same persistent memory of you. The core data lives in a single database that supports vector search.

What language is ob1 written in?

ob1 is written mainly in TypeScript. The repository also contains JavaScript, Python, shell and Svelte code.

How is the ob1 code organized?

The code is split into 9 modules, including recipes for importing data, dashboards for web interfaces, integrations for MCP and REST API access, and schemas. The recipes module alone contains 268 files.

Who is ob1 for?

ob1 is for people who want AI tools such as Claude, ChatGPT and Cursor to share one persistent memory of them. It is built around a single database that any AI can plug into.

Code health

7.4out of 10Good

Hotspots average 4.9, the place fixes pay off most.

On the leaderboards:#39 of 66 TypeScript repos

Key features of ob1

  • Stores your thinking in one database that supports vector search.
  • Gives every AI tool you use a shared persistent memory of you.
  • Provides one AI gateway and one chat channel that any AI can plug into.
  • Offers a six-step learning path of extensions, from a household knowledge base to a job hunt pipeline.
  • Includes recipes that import data from sources such as ChatGPT exports, Obsidian vaults and X/Twitter exports.

How natebjones-projects/ob1 works

The repository is split into 9 modules, the largest by file count being recipes with 268 files, dashboards with 143 and integrations with 122. The recipes directory holds importers for personal data sources, and the README says each one covers parsing, deduplication, embedding and ingestion. integrations/enhanced-mcp/index.ts is a central file in the MCP integration, which relies on the @modelcontextprotocol/sdk package. integrations/rest-api/index.ts is a hotspot file in the REST API integration, and Express is among the key dependencies. integrations/chrome-capture-extension/background/service-worker.js is a hotspot file in a browser extension that syncs chat content from Claude and ChatGPT. dashboards/open-brain-dashboard/src/routes/+page.svelte is the entry page of a Svelte dashboard for the system.

The codebase has 791 files and 2,787 symbols in 9 modules, led by TypeScript, JavaScript and Python. Code health is 7.4 out of 10, rated good.