DEV Community

Cover image for I built a zero-dependency alternative to GitNexus for AI-assisted coding
Cyber Audio Mind
Cyber Audio Mind

Posted on

I built a zero-dependency alternative to GitNexus for AI-assisted coding

The Problem

Every AI coding tool — Claude Code, Cursor, Copilot — needs to understand your codebase. But they don't. Not really.

They see individual files, but miss the big picture: which components depend on what, how API routes connect to database models, what auth pattern each page uses.

Current solutions like GitNexus solve this with a graph database (KuzuDB) and an MCP server. That's powerful, but it's also heavy: you need to run a server, install dependencies, and it only works with Claude Code.

I wanted something simpler.

The Solution: Structured Markdown

Fondamenta ArchCode runs static analysis on your codebase and generates structured Markdown files. That's it.

npx fondamenta-archcode analyze
Enter fullscreen mode Exit fullscreen mode

No database. No server. No runtime dependencies. Just .md files that any LLM can read natively.

What It Generates

.planning/
├── DEPENDENCY-MAP.md          # Architecture overview, impact areas
└── dependencies/
    ├── pages-atomic.md        # Every page: imports, auth, data fetching
    ├── components-atomic.md   # Every component: props, state, hooks, used-by
    ├── api-routes-atomic.md   # Every API route: methods, auth, models
    ├── lib-atomic.md          # Every utility: exports, imports, env vars
    ├── schema-crossref-atomic.md  # DB models, fields, relations, enums
    └── component-graph.md     # Visual dependency tree
Enter fullscreen mode Exit fullscreen mode

Example: pages-atomic.md

### `/dashboard`

- **File:** `app/(dashboard)/dashboard/page.tsx`
- **Type:** Server Component
- **Auth:** auth()
- **Data Fetching:**
  - DB: findMany (courses)
  - DB: count (flashcards)
- **Components:** CourseCard, StatsWidget, RecentActivity
Enter fullscreen mode Exit fullscreen mode

Every AI agent understands this format instantly. No special tools needed.

How It Works

  1. Discovers files using fast-glob (respects .gitignore)
  2. Parses TypeScript/TSX using the TypeScript Compiler API (not regex!)
  3. Builds an in-memory graph of imports, exports, components, hooks
  4. Classifies each file: page, component, API route, lib, hook
  5. Analyzes Prisma schema for models, fields, and relations
  6. Generates structured Markdown with consistent formatting

The TypeScript Compiler API is key here — it gives us a real AST, not fragile regex patterns. We can detect server vs client components, extract hooks, find API calls, and trace the full dependency tree.

Real-World Results

Tested on a 1000+ file Next.js project:

Metric Count
Pages analyzed 116
Components mapped 487
API routes documented 291
DB models cross-referenced 109
Total time < 3 seconds

Beyond analyze: Full Workflow

# Detect what changed since last analysis
fondamenta diff
fondamenta diff --ci    # Exit code 1 if outdated (for CI pipelines)

# Watch mode — regenerate on file changes
fondamenta watch

# Generate AI context files
fondamenta ai-context --claude   # CLAUDE.md
fondamenta ai-context --cursor   # .cursorrules
fondamenta ai-context --copilot  # copilot-instructions.md
fondamenta ai-context --all      # All of the above
Enter fullscreen mode Exit fullscreen mode

vs Alternatives

Fondamenta ArchCode GitNexus Repomix
Output Structured .md files Graph DB (KuzuDB) Single concatenated file
Runtime deps None KuzuDB + MCP server None
AI integration Any tool (reads files) Claude Code only (MCP) Any tool
Framework-aware Yes (routes, pages, auth) AST only No
Schema-aware Yes (Prisma) No No
Human-readable Excellent Requires queries Poor (wall of text)
Git-friendly Yes (meaningful diffs) No (binary DB) Poor (single file)

Try It

npx fondamenta-archcode analyze
Enter fullscreen mode Exit fullscreen mode

GitHub: github.com/talionwar/fondamenta-archcode
npm: npmjs.com/package/fondamenta-archcode

Currently supports Next.js App Router + Prisma. Multi-framework support (Nuxt, SvelteKit, Remix) is on the roadmap.

Feedback and contributions welcome!

Top comments (0)