JevX

Your code is full of hardcoded rules that are really judgment calls: regexes that guess what an error means, keyword lists that guess what a customer wants, slice(0, 3) that guesses what's best. JevX finds them, scores each one three ways (your AI, TypeSafe/Jev, patterns learned from real Jev projects) and replaces the strong fits with a Jev decision (TypeSafe noul · choice · score) — keeping the old rule as the fallback, and proving it with your own tests.

npm i -g @vij-sameerb5/jevx
cd your-project
jevx --dry-run      # preview: scorecards + red/green diffs, nothing written
jevx                # change strong fits (70%+), run your tests, auto-revert what breaks
jevx undo           # put everything back

Or from the AI you already use — Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Gemini CLI, Codex:

jevx mcp install    # then say: "use jevx to find where Jev fits in this repo"

Claude Desktop users can also double-click jevx.mcpb (from the releases) and pick their project folder.

Why you can trust it

• Your key, your AI. JevX never ships a key; the terminal version uses your xAI / OpenRouter key.

• Safety lives in the tool: only strong fits change by default, the old rule stays as the fallback, files you're editing are skipped, your tests run before and after, jevx undo restores.

• Private by default. Code goes only to your own AI. --share (opt-in) sends generic patterns — never code, file or function names — so JevX learns which changes hold up.

Full docs: apps/jevx/README.md · website: site/ · changelog: apps/jevx/CHANGELOG.md

Related MCP server: jev-mcp

Working on JevX

git clone https://github.com/vij-sameerb5/JevX.git && cd JevX
pnpm install
pnpm test              # ~240 tests, no network, no keys
pnpm dev               # the CLI from source (shows the welcome)
pnpm jevx --help       # every command
pnpm mcp-smoke examples/jev-demo   # the MCP server, end to end

See CONTRIBUTING.md. MIT © Sameer Shaik.