Code Your Vision.
Build Your Dream

OperatorX02 — an AI IDE built with boundless memory and multi-file autonomous coding. Multiple AI agents at your command. Open source, 100% local, no login required.

100%
Open Source
∞
Boundless Memory
Multi
AI Agent
編程是藝術Coding is Artコーディングは芸術だ프로그래밍은 예술이다Programação é arteProgrammieren ist KunstProgramar es arteCoder, c'est de l'artKodlama sanattırการเขียนโค้ดคือศิลปะКодирование — искусствоLập trình là nghệ thuậtالبرمجة فنकोडिंग कला हैPengaturcaraan adalah seni
Programação é arteकोडिंग कला हैKodlama sanattırコーディングは芸術だ프로그래밍은 예술이다البرمجة فنการเขียนโค้ดคือศิลปะCoder, c'est de l'artProgrammieren ist KunstProgramar es arteКодирование — искусствоPengaturcaraan adalah seniLập trình là nghệ thuật

Coding is Art. Feel it. Enjoy it.

Every developer has their own style, their own taste, their own way of creating. That's why Operator X02 is open source — build the IDE that matches YOUR vision. Create your masterpiece.

— Heng Chang Song
🌟 Open Source
🧠 Boundless Memory
🔄 VCS Aware
🤖 Multi-File Coding
🔀 Multi AI Agent
⚡ 8 Quick Actions
🔒 100% Local
🎨 Full Customization
Boundless Memory

AI That Never Forgets Your Project

Other tools forget after one session. Operator X02 remembers everything — so your AI gets smarter the more you use it.

🧠

Boundless AI memory that saves full context across sessions, makes smarter decisions on large codebases, and scales to massive projects.

⚡AI Code IDE - OperatorX02 BETA
─
☐
✕
☰FileProjectView▶ RunPluginGit▶ npm (Node.js) · 4 scripts
Files
Terminal
Search
SVN
📁 MY-AUTH-PROJECT
AllStructMinimalCode
📁src
📄  auth.tsM416B
📄  main.tsM235B
📄  api.tsA189B
📄  utils.ts97B
📁components
📄  Login.tsx364B
📄  Dashboard.tsx512B
📦package.json698B
📋tsconfig.json611B
◆ auth.ts (416)×
◆ main.ts (235)
C: > Users > dev > projects > my-auth-project
1import { jwtDecode } from'jwt-decode'
2import'./auth.css'
3
4export classAuthService {
5  private token: string | null = null
6
7  // Fixed: auto-refresh before expiry
8  asyncrefreshToken() {
9    const decoded = jwtDecode(this.token!)
10    if (decoded.exp * 1000 < Date.now()) {
11      this.token = awaitthis.fetchNew()
12    }
13  }
14
15  asynclogin(email: string) {
16    const res = awaitfetch('/api/auth')
💬
📝
📊
⚙️
Operator X02
▾ 29 earlier messages
What did we fix yesterday in auth?
🔍Trigger: "yesterday" + "fix"
🧠History: 3 matches · 15ms
🔄SVN: 2 modified files
⚡Context injected: 2,335 chars
12:23 PM Operator X02
🧠 Memory🔄 SVN
Yesterday we fixed the JWT token expiry bug in auth.ts. The token wasn't auto-refreshing before expiry, causing logout loops.

I see auth.ts and main.ts modified in SVN — the fix is in place. Ready to commit.
Generate commit message
12:23 PM Operator X02
🔄 SVN
fix(auth): resolve JWT refresh loop on token expiry
Ask me anything...
✨
➤
<>
🔍
📎
📷
📄
🔗
⎇ main
TypeScript
Ln 9, Col 12
UTF-8
Spaces: 2
🟢 OperatorX02 Beta Released! NEW
How Boundless Memory Works
💬
User Message
"What did we fix yesterday?"
🔍
172+ Triggers
Auto-detect past references
🧠
History Search
~15ms local search
🔄
VCS Context
SVN/Git status + diffs
⚡
Context Inject
Invisible to user
✨
AI Response
Context-aware answer
User sees clean messages · AI receives full context with history + VCS data · 100% local, no cloud
💾

Saves Full Context

Every conversation, every decision, every bug fix — stored locally and searchable. Ask "why did we change this?" and AI finds the exact conversation from weeks ago. No cloud. No token limits.

172+Trigger patterns
∞History depth
~15msSearch speed
🎯

Better Decisions

With full project history, AI understands why code exists — not just what it does. It knows your architecture patterns, past trade-offs, and team conventions.

🔄 Session 1"Here's a generic auth implementation..."
🧠 Session 47"Based on your JWT refresh pattern, here's a fix that matches your existing auth flow..."
📁

Scales to Big Projects

Large codebases with hundreds of files need AI that understands the full picture. Operator X02 injects project structure, file relationships, and VCS status — so it never suggests changes that break other parts.

Multi-fileAwareness
VCSIntegration
LocalStorage only
Open Source

Your IDE, Your Rules

Fork it. Modify it. Make it yours. No restrictions.

🔓

Fully Open Source

Complete source on GitHub. MIT license. Use, modify, distribute.

🎨

Full Customization

Change the UI, add features, modify AI prompts. Every line is yours.

🤝

Community Driven

Built by devs, for devs. Contribute features, shape the roadmap.

🔧

Self-Hostable

Run your own instance. Deploy for your team. Full control.

Fine-tune every AI provider for every task. Your matrix. Your rules. Total control over how each model performs.

⚙️Provider Calibration✕
📊 Matrix
📋 Summary
🕐 History
⚙️ Settings
High (70%+)
Medium (40-69%)
Low (<40%)
Disabled
Override
Provider
<>CODE
🔧FIX
📖DOCS
⚡QUICK
🧠THINK
✍️WRITE
👁️VISION
🌐LANG
📝SUM
💬CHAT
⚡ OPERATOR X02
50%
50%
50%
50%
20%
20%
OVERRIDE
20%
20%
20%
🔥 GROQ
20%
20%
20%
50%
20%
20%
OVERRIDE
50%
50%
20%
✨ GEMINI
20%
20%
20%
20%
20%
50%
50%
20%
50%
50%
🔵 DEEPSEEK
50%
50%
50%
20%
50%
20%
OVERRIDE
20%
20%
20%
🟠 CLAUDE
50%
50%
20%
20%
50%
50%
50%
20%
50%
50%
🟢 OPENAI
50%
50%
20%
20%
20%
50%
50%
20%
50%
50%
🗑 Reset All
⬆ Export
Done
6+
AI Providers
More Coming Soon
10
Task Types
60
Calibration Points
Editing Modes

Auto Mode & Classic Mode

Two ways to let AI edit your code — both protected, both precise. You choose how much control you want.

🚀
Auto Mode
Recommended

AI reads your file first, then applies surgical line-level patches. Only the exact lines that need changing are touched — no full-file replacements, no accidental deletions.

✓ Surgical line-level patches
✓ File verification before applying
✓ Auto backup per command
✓ Atomic multi-file batch operations
✓ Create / rename / delete from natural language
🛡️
Classic Mode
Full Control

AI generates the full code block, you review the visual diff, then accept or reject. Every change goes through the 8-stage Surgical Edit Engine — highlighted in purple, one-click rollback.

✓ 8-stage Surgical Edit Engine
✓ Visual diff before every apply
✓ Purple highlights on changed lines
✓ One-click rollback to any backup
✓ 91%+ destructive change detection
Auto Mode Flow
💬
AI Response
Code generated
🔍
File Verify
Case-corrected
💾
Backup
Auto-created
🔬
Patch
Lines only
✅
Applied
Recoverable

Everything You Need, Nothing You Don't

All the AI power you need, with the flexibility to make it your own.

🧠

Boundless AI Memory

No context limits. No forgotten conversations. 172+ triggers, unlimited history, all stored locally.

No Limits
🔄

VCS Awareness

AI knows your real Git/SVN status. Ask "what changed?" and get actual modified files with commit messages.

Real-time
📚

Multi-File Autonomous

AI modifies multiple files simultaneously. Visual diff shows changes. Enter to accept, Escape to reject.

Autonomous
⚡

8 Quick Actions

Select code → Click ⚡ → Explain, Optimize, Comment, Refactor, Test, Type, Security, Simplify.

One-Click
🎨

Fully Customizable

Open source means you control everything. Modify AI prompts, change UI, create plugins.

Open Source
🔒

100% Local & Private

No account. No telemetry. All data local. Ollama for 100% offline AI. Air-gap ready.

Your Data
🔌

Embedded Development

Native Arduino, ESP32, STM32 support. One-click compile. Serial monitor built-in.

Arduino Ready
More MCU coming soon
🛡️

Safety-Critical

MISRA C:2012 guidelines. ISO 26262, IEC 61508, IEC 62304 workflow support.

MISRA C
OperatorX02 IDE features — Per-File AI Analysis, Project Analysis, and AI Quick Actions
📂 Per-File AI Analysis
Explain, Summary, Architecture & Dependencies — per file.
🧠 Project Analysis
Quick (~2K tokens) or Deep (~10K tokens) whole-project analysis.
⚡ AI Quick Actions
Analyse single code — AI Refactor, Add Comments, Error Handling & ISO 26262.
Multi AI Agent

AI That Adapts to Your Team

Assign roles, calibrate providers, create projects with AI, and track every decision.

👤

AI Role Selection

Assign specific roles to AI: Architect, Developer, Reviewer, Tester, Debugger, Documenter, PM, Security. Each role has optimized prompts for that task. Perfect for team specialization.

8 Roles
⚙️

Provider Calibration

Fine-tune which AI handles which task. Set percentages for CODE, FIX, DOCS, THINK, WRITE, VISION across 6 providers. Color-coded matrix shows strengths at a glance.

10 Task Types
✨

AI Project Advisor

Describe your project in plain text → AI recommends the best template. Supports Web, Desktop, Mobile, Backend with React, Next.js, Vue, Vite, and more. Project created in ~5 seconds.

BETA
📊

Context Analytics

Track every decision: Create, Modify, Delete, Refactor, AI Suggestion. See file type distribution, message count, context size. Export your workflow data anytime.

Decision Tracking
📦

Multi-Project Templates

Start any project type instantly: Web Application, Desktop App, Mobile App, Backend Service. AI generates project structure based on your description. 40+ build systems supported.

40+ Templates
🔀

Auto-Route Intelligence

Let the system automatically choose the best AI provider for each task based on your calibration settings. Smart routing for optimal results without manual switching.

Smart Routing
AI Project Advisor - Create New Project
The Journey

From Vision to Reality

15 February 2026

OperatorX02 Beta V1.0

Public beta (.exe) released — download now

18 February 2026

OperatorX02 Beta V1.1

Enhanced embedded development features — AI Serial Monitor, Signal Plotter, Pin Visualizer. More info →

22 February 2026

OperatorX02 Beta V1.2

Introducing the Surgical Edit Engine — an 8-stage Rust-powered pipeline that makes every AI code edit accountable. Automatic backups before any file is touched, destructive change detection that blocks 91%+ deletions, real-time pipeline visibility, and full AI context awareness. Every edit tracked, every change recoverable — in ~36ms. More info →

25 February 2026

OperatorX02 Beta V1.3

Introducing Android Development Support — build, debug, and deploy Android applications directly from Operator X02 with AI-powered assistance. More info →

1 March 2026

OperatorX02 Beta V1.4

Introducing Auto Mode — the AI that reads your code before editing it. Three editing modes, zero destroyed code. Auto Mode uses surgical line-level patches instead of full-file replacements, with built-in backup per command, atomic multi-file batch operations, and full file management (create, rename, delete) from natural language. Classic Mode stays available with the Surgical Engine as its guardian layer — 8-stage pipeline, purple highlights, one-click rollback. Every developer protected, every edit recoverable. See the full comparison →

4 March 2026

OperatorX02 Beta V1.5

Introducing NVIDIA Jetson Support — SSH connect, real-time tegrastats monitoring (GPU%, temps, power, RAM), CUDA syntax highlighting in Monaco, one-click .cu / .py deploy with on-device nvcc compilation, Jetson project templates, and a GPU status bar widget. Full Phase 1 & Phase 2 shipped. More info →

15 March 2026

OperatorX02 Full Release

Complete app, full source code release, production-ready with all features and documentation.