Codenano banner
Adamlixi Adamlixi

Codenano

AI community

Description

Lightweight AI coding agent SDK. Same power, 97% less complexity. Build custom AI coding agents in 1 minutes

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

codenano

[![npm version](https://img.shields.io/npm/v/codenano.svg)](https://www.npmjs.com/package/codenano) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/TypeScript-5.7-blue.svg)](https://www.typescriptlang.org/) [![Tests](https://img.shields.io/badge/tests-374%20passing-brightgreen.svg)](https://github.com/Adamlixi/codenano)

**The lightweight AI coding agent SDK inspired by production agent architecture.**

Built with battle-tested patterns from production AI coding systems. ~8,000 lines of focused code, zero bloat. Open source, fully customizable, production-ready.

πŸ’‘ **Production-Grade Patterns** β€” Agent loop architecture inspired by real-world AI coding assistants, now available as a standalone SDK.

Why codenano?

πŸš€ **Lightweight & Focused**

  • ~8,000 lines of pure, focused code
  • Zero bloat, zero overhead
  • Production-grade agent engine

⚑ **Build AI Coding Agents Fast**

npm install codenano

Build your own AI coding agent in 60 seconds. No IDE required. No restrictions.

🎯 **Battle-Tested Architecture**

Production-grade agent patterns. Proven at scale, optimized for developers.


Quick Start

**Get your first agent running in 3 lines:**

import { createAgent, coreTools } from 'codenano'

const agent = createAgent({
  model: 'claude-sonnet-4-6',
  tools: coreTools(),  // Read, Edit, Write, Glob, Grep, Bash
})

const result = await agent.ask('Read package.json and summarize it')
console.log(result.text)

**That's it.** No complex setup. No configuration hell. Just pure productivity.

Streaming? Built-in.

for await (const event of agent.stream('What files are here?')) {
  if (event.type === 'text') process.stdout.write(event.text)
}

Multi-turn conversations? Easy.

const session = agent.session()
await session.send('Read main.ts')
await session.send(