cabinetai / cabinet
AI-first knowledge base and startup OS
github.com/cabinetai/cabinetIndexed at 92ed8a6Up to date with upstream
About this codebase
Cabinet is a knowledge-base-first AI runtime that lets you install an agent team, run it against your cabinet directory, and steadily compound results into versioned markdown artifacts and embedded apps—so you (and your agents) can stop re-explaining context every new Claude session. The inputs are your cabinet folder (markdown plus optional `index.html` and embedded app files), your agent templates (roles, recurring jobs, recommended skills), and user questions during onboarding; the pipeline installs/starts the app, builds a custom AI team in the knowledge base, executes agent “missions” and scheduled routines, and continuously writes back edits and generated content; the outputs are mission reports, edited cabinet documents, and rendered embedded apps you can version via git. New developers generally start by using the CLI (`npx`) or the onboarding wizard in the running web app, and end by operating “Your Team” and “Knowledge Compounds” day to day.
Written by gpt-5.4-nano from the index
1,074 files and 5,680 symbols in 9 modules, led by TypeScript (872 files) and JavaScript (34).
Start reading
Code health
This codebase scores 6.3 out of 10 for code health, which we rate fair. It also scores maintainability 8.4 and static performance 9.7 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 63 of 1,074 files are git hotspots, and they average 2.8 — which is where the fixes pay off most.
On the leaderboards:#30 of 37 TypeScript repos
Do next
Nothing stands out in the week to Aug 25, the last indexed commit.
Improve what Repowise can see
Add a test coverage report
Without one, Repowise cannot tell tested code from untested code, so every test-related action says “unknown”.
- line coverage
- Unknown, no report
Small effort
Use cabinetai/cabinet in your agent
Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.
https://api.repowise.dev/mcp/cabinetai/cabinetOne command, run anywhere. Adds the server to your local Claude Code config.
Docsclaude mcp add --transport http repowise https://api.repowise.dev/mcp/cabinetai/cabinet \ --header "Authorization: Bearer rw_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
This repo is public, so anyone with a Repowise account and an API key can connect.
Try asking
- get_overview()
- get_answer("how is cabinet put together?")
- get_why("why is cabinet structured this way?")
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.
Go deeper
- OverviewEverything the index found, what changed this week, commits and decisions.
- DocumentationModule-by-module documentation, 1,167 pages, 54 written by a model.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score, the findings behind it, tests and refactoring plans.
- CommitsEach commit's effect on code health, with agent provenance.
- ContributorsWho owns what, and where one person holds most of the knowledge.
- DecisionsArchitectural decisions mined from commits and pull requests.
- Ask this codebaseSign inGrounded answers over the indexed code.
Maintain this repo? Claim the page
Sign in with GitHub and we check that you are an admin or maintainer of cabinetai/cabinet. Then add a badge to the README that links readers here.
Use this repo from Claude or ChatGPT
Add this URL as a custom connector and sign in with repowise when asked. No API key to copy.
https://api.repowise.dev/mcp/cabinetai/cabinetFor maintainers
Add a badge to your README
Every badge is public, cached, and updates on its own after every index. Nothing to install.
Repowise badge
Links to this page, with no score on it. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/cabinetai/cabinet?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/cabinetai/cabinet?src=badge_health)Code health card
A larger card with the score, its change since the last index, and when it was measured. The HTML version follows the reader's light or dark theme.
[](https://repowise.dev/repo/cabinetai/cabinet?src=badge_card)How cabinetai/cabinet works
AI-first knowledge base and startup OS This page is a map of the cabinetai/cabinet repository, written primarily in TypeScript, rebuilt from the source each time it is indexed. Repowise parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the architectural decisions into documentation you can read here or query through MCP.
The codebase has 1,074 files and 5,680 symbols in 9 modules, led by TypeScript, JavaScript and Shell. Code health is 6.3 out of 10, rated fair.
Use the links above to open each view, or connect this repository to your agent for grounded answers inside Claude, Cursor, Codex or VS Code.