lee-to / ai-factory
You want to build with AI, but setting up the right context, prompts, and workflows takes time. AI Factory handles all of that so you can focus on what matters — shipping quality code.
github.com/lee-to/ai-factoryIndexed at ac92bebUp to date with upstream
About this codebase
AI Factory is a codebase documentation engine that, end-to-end, consumes a target repository (inputs such as source files, skill metadata, and optional agent/skill/MCP selections), traverses and parses the code into AST-based facts, analyzes dependencies and extensions, and then generates LLM-synthesised wiki-style knowledge artifacts served to humans and agents (outputs include indexed evidence plus generated page content, with optional MCP server configuration). It’s “Stop configuring. Start building.”—the goal is to reduce setup friction by installing relevant skills, applying best practices, and keeping the workflow spec-driven, resumable, and reviewable across many supported coding agents.
Written by gpt-5.4-nano from the index
297 files and 853 symbols in 5 modules, led by TypeScript (26 files) and Shell (23).
Code health
This codebase scores 6.2 out of 10 for code health, which we rate fair. It also scores maintainability 7.1 and static performance 9.2 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 10 of 297 files are git hotspots, and they average 4.8 — which is where the fixes pay off most.
Do next
1 thing worth doing this quarter.
Worth planning
Fix 1 broken reference in
skills/aif/SKILL.mdThe document points readers and agents at a path this repository no longer has.
- broken references
- 1
- first
- skills/aif/SKILL.md#architecture-generation
Small effort
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 effortReview the 12 proposed decisions
None is accepted yet, so nothing can drift from one and agents get no enforced guidance from them.
- proposed
- 12
- accepted
- 0
Medium effort
Use lee-to/ai-factory 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/lee-to/ai-factoryOne command, run anywhere. Adds the server to your local Claude Code config.
Docsclaude mcp add --transport http repowise https://api.repowise.dev/mcp/lee-to/ai-factory \ --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 ai-factory put together?")
- get_why("why is ai-factory 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, 124 pages, 11 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 lee-to/ai-factory. 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/lee-to/ai-factoryFor 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/lee-to/ai-factory?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/lee-to/ai-factory?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/lee-to/ai-factory?src=badge_card)How lee-to/ai-factory works
You want to build with AI, but setting up the right context, prompts, and workflows takes time. AI Factory handles all of that so you can focus on what matters — shipping quality code. This page is a map of the lee-to/ai-factory repository, written primarily in Shell, 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 297 files and 853 symbols in 5 modules, led by TypeScript, Shell and JavaScript. Code health is 6.2 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.