Launching today
LNAI

LNAI

One config for all your AI coding tools

3 followers

Visit website
Every AI coding tool has its own config format. Claude wants `.claude/`, Cursor wants `.cursor/`, Codex wants `.codex/`. Update a skill? Update it everywhere. LNAI lets you define configs once in `.ai/` and sync to native formats for Claude Code, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf, and Codex. It handles each tool's quirks automatically and uses symlinks so changes propagate instantly.
LNAI gallery image
LNAI gallery image
Free
Launch tags:Open Source•Developer Tools•Artificial Intelligence
Launch Team
Wispr Flow: Dictation That Works Everywhere
Wispr Flow: Dictation That Works Everywhere
Stop typing. Start speaking. 4x faster.
Promoted

What do you think? …

Krystian Jońca
Maker
📌
I built LNAI because I got tired of maintaining the same rules across Claude Code, Cursor, and Codex. The problem is simple: every AI coding tool has its own config format. Claude wants `.claude/`, Cursor wants `.cursor/`, Codex wants `.codex/`. When you update a skill/rule, you update it everywhere, or more likely, you forget one and your tools drift out of sync. LNAI lets you define everything once in a `.ai/` directory: .ai/ ├── AGENTS.md ├── rules/ ├── skills/ └── settings.json # Permissions & MCP servers Then `lnai sync` exports to native formats for each tool. It's not just copying files, it actually transforms configs appropriately. Cursor rules get converted to `.mdc` with the right frontmatter. Gemini rules get grouped by directory (because that's how Gemini reads them). Permissions like `Bash(git:*)` become `Shell(git)` for Cursor. The sync uses symlinks where possible, so a change to `AGENTS.md` propagates instantly to all tools without running sync again. Three commands: npm install -g lnai lnai init # Create .ai/ configuration lnai validate # Check for errors before syncing lnai sync # Export to native tool configs It's MIT licensed, works with Claude Code, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf, and Codex. Would love feedback from anyone juggling multiple AI tools.