Building in the open — early development

Sharpen your code,
natively.

A native, AI-powered code editor for every platform. Written in TypeScript, compiled to native via Perry. No Electron. No compromise.

Follow on GitHub Learn more ↓
server.ts
auth.ts
routes.ts
1import { createServer } from 'hone/http'
2import { authMiddleware } from './auth'
3
4const app = createServer({
5  port: 3000,
6  middleware: [authMiddleware],
7})
8
9app.get('/api/users', async (req, res) => {
10  const users = await db.query('SELECT * FROM users')
11  res.json({ data: users, count: users.length })
12})
13
14// Compiled to native. No V8. No Electron.
15app.listen()
AI Chat
Add pagination to the users endpoint
Claude
I'll add offset/limit pagination with a total count header. Applying changes...
Agent
✓ Modified server.ts
✓ Added tests
✓ All tests pass
main TypeScript UTF-8
Ln 11, Col 4 Claude Sonnet 4.5
Why Hone

Everything an editor should be.
Nothing it shouldn't.

Built from scratch in TypeScript, compiled to native binaries via Perry. Every component is designed for performance, modularity, and developer joy.

Truly Native

No Electron, no Chromium, no V8 runtime. Perry compiles TypeScript directly to native binaries. Under 50MB, under 100MB RAM, sub-second startup.

🧠

AI-First Architecture

AI isn't bolted on — it's woven into the editor's core. The AI sees your syntax tree, your errors, your git diff, your terminal. Deep context, not just text.

🔑

Bring Your Own AI

Claude, GPT, Gemini, Ollama, or your company's private model. Your API key, your choice. Mix different providers for different features. No vendor lock-in.

🤖

Agent Mode

Describe what you want. The agent reads your code, plans changes, edits files, runs tests, and iterates — with per-hunk approval before anything is committed.

🔍

Native PR Review

Review pull requests in-editor with full syntax highlighting, LSP intelligence in diffs, and AI-powered annotations that catch bugs before humans do.

🧩

Modular & Composable

hone-editor, hone-terminal, and hone-core are independent packages. Use the editor component in your own app. Build your own IDE on Hone's foundation.

Performance

The numbers Electron
can't reach.

When you eliminate the browser, everything gets faster. These are our targets — and we intend to hit every one.

<1s
Cold start
vs 3-5s (VSCode)
<100
MB RAM idle
vs 300-500MB (VSCode)
<50
MB binary
vs ~300MB (VSCode)
<10
ms keystroke latency
vs 30-50ms (VSCode)
AI Integration

Your AI. Your keys.
Your choice.

Hone never resells API access. You bring your own keys and route different providers to different features. When the next hot model drops, it works immediately.

Inline

Ghost Text Completion

Context-aware suggestions powered by any provider. Sees your syntax tree, not just raw text. Renders at native speed with zero Electron overhead.

Chat

Context-Aware Chat

The AI automatically sees your open files, errors, terminal output, and git state. No manual @file tagging. Switch models mid-conversation.

Agent

Autonomous Coding Agent

Multi-file edits, terminal commands, test execution, error recovery. Full transparency with a live activity log and diff approval before any change lands.

Review

AI-Powered PR Review

AI pre-analyzes every diff for bugs, security issues, and style problems. Review annotations appear inline. One-click fixes. Submit reviews back to GitHub/GitLab.

Bring Your Own Key. Mix & Match.

Route each AI feature to a different provider. Use a fast local model for autocomplete, a powerful cloud model for agent tasks, and something in between for chat. Your infrastructure, your budget, your rules.

Anthropic (Claude)
OpenAI (GPT)
Google (Gemini)
Ollama (Local)
AWS Bedrock
Any OpenAI-compatible
Platforms

One codebase.
Every platform.

Written once in TypeScript. Compiled to native on each platform by Perry. Native look, native speed, everywhere.

🍎
macOS
🪟
Windows
🐧
Linux
📱
iOS
🤖
Android
🌐
Web

Built in the open.

Hone is in early development. Follow along, contribute, or just watch.

Star on GitHub