WAY AI LABS · Build · Create · Learn Hold It AI Visual Teaching & Spatial Context 1004 Agent Tools Local & Connected AI
AI WORKSPACE · WINDOWS DESKTOP + CONNECTED WEB STUDIOS

Way AI Code

Build. Create. Understand.

Code with an agent, ask NOVA, or turn a question into an on-screen visual explanation.
Create images, narration and business content using the local engines or connected providers you choose. Provider fees, quotas and studio entitlements apply.

Download for Windows — Free Try in Browser Founder GitHub
Choose Your AI
Download a compatible local model or connect a provider or signed-in CLI. Cloud requests send the selected context to that service.
Windows x64
Desktop editor and native tools. Android companion and web studios have different capabilities; see setup below.
Chat · Agent · Engineer
Chat for answers, Agent for reviewed actions, Engineer for autonomous project work.
Security-First
Permission behavior follows your selected mode. Review connected services before sharing context.
What is Way AI Code?

One workspace for building, creating and learning.

A code editor, terminal and Git workspace sit alongside NOVA, Hold It visual teaching, Flow automation and creative studios. CampainX adds business presence, posts, reels and a calendar through connected engines and social accounts.

₹0
Local model inference fee*
1004
Agent tools built in
2105
Slash commands
10+
AI providers supported
Code
Edit files by hand or ask the agent for a targeted fix — one file, a component, or a whole folder — without losing project context.
function verifyAuth() { return token }
Flow
Drag nodes onto a canvas and wire triggers to actions — 121 node types, 48 ready templates, credential-safe and crash-recovered.
TriggerAIAction
Agent
1004 built-in tools across 37 categories — file edits, git, security scans, tests, and deploy checks — called automatically as it works.
read_file → App.jsx run_bash → npm test security_scan → 0 issues git_diff → 3 files
Engineer
One prompt → a full build. Plans the work, writes files, installs deps, runs tests, fixes failures, and opens a live preview.
Plan
Generate
Install
Run
Fix
Validate
DevOps
172
Code Intel
113
Web APIs
99
UI Design
81
Docs
79
Data
75
Testing
64
Security
55
+ 29 more categories — quality, AI/ML, automation, performance, integrations, memory, git, database, and more. 1004 tools total, verified against the live registry.
Your workspace, explained

Choose what you want to do.

Features share the app, but each uses its own engine, permissions and connected accounts. Availability below describes setup requirements, not a claim that every integration has passed live testing.

Build software

Edit, search, run a terminal and use Git. Choose Chat, Agent or Engineer. Codex, Claude Code and Gemini CLI require their own installation and valid sign-in or supported credentials.

Explore workspaces →

NOVA & Companion

Voice and typed assistance, contextual follow-ups and connected app actions. Microphone access is required for speech. App control depends on platform permissions and the target service.

Set up your assistant →

Hold It visual teaching · Preview

Question → generated visual → explanation. No existing GLB is needed. Ask in words, or mark a screen region for context. Inspect 2D/3D views and narration; realistic separated parts and exact dimensions need suitable references and generation support.

See visual teaching limits →

Creative AI & VoiceDesk

Select image, video and speech engines in Creative AI settings. Local models need downloads and compatible hardware. Optional ComfyUI, Wav2Lip and Ollama installations are not included merely because a settings entry exists.

Explore creative tools →

CampainX marketing

Set up a business profile, prepare branded posts and reels, and manage calendar drafts. Approve the desktop connection to use PC engines. Scheduling and Instagram publishing require eligible accounts, permissions and a successful service response.

Open CampainX →

Flow & integrations

Connect supported triggers and actions on a workflow canvas. Supply required credentials and inspect each run result. A saved workflow, connected account or queued publish job does not by itself mean execution completed.

Browse workflow templates →
Customer setup

Start with a question. Connect what it needs.

You do not need to prepare a 3D file before using Hold It.

1. Install & sign in

Install the Windows desktop app for native tools. Web studios run in a browser. Android Companion uses its own app and overlay permissions; feature parity varies by device.

2. Choose an AI service

Download a local model or connect a supported provider or CLI account. A developer's CLI login is not included for other customers. Provider access, subscriptions and usage limits remain account-specific.

3. Allow the needed access

Enable microphone access for voice and screen access for marked questions. Android needs overlay access. CampainX asks for PC approval before using desktop engines. Disconnect or revoke unused connections.

4. Ask, inspect, continue

Try “Explain how an electric motor works in 2D and 3D.” On Windows, hold Ctrl+Shift and speak, with or without marking. Review diagrams and factual claims, then ask a follow-up.

* Local inference can avoid per-request provider fees after model setup. Hardware, electricity, model licences, paid studios and cloud services may still have costs. A connected account does not guarantee image, video or 3D access.

Visual teaching availability

Understand the model you are looking at.

Generated teaching scenes, reconstructed exteriors and verified engineering models are different kinds of output.

Question-driven teaching

The connected model prepares drawings, geometry, parts and explanation steps from your question. Output quality depends on the model and reference material. Missing engines or failed requests must be resolved before a lesson can be generated.

Optional GLB reference

Open a local GLB to rotate and inspect an existing exterior. The local single-photo reconstruction test produced an approximate textured car. It did not produce verified separated components or an engine cutaway.

What is still limited

Automatic photorealistic multipart generation, verified internal assemblies and exact brand-specific dimensions are not generally available. Simplified mechanisms must be labelled. Do not use generated drawings as manufacturing instructions.

01 — Features

Built different. Ships faster.

From prompt to production — no cloud dashboard required.

AI Engineer Mode
Type a prompt — Way AI plans, scaffolds, installs deps, runs tests, and opens a live preview. One prompt, one running app.
$ way engineer "SaaS dashboard with auth + Stripe" ✓ Plan ready · 12 features · 14 files ✓ Deps installed · tests pass ❯ localhost:5173 — preview ready
Local Model Options
Way Local LLM can download and run a compatible open-weight model on your PC. Ollama and LM Studio are optional separate runtimes. Hardware, disk space and model licences matter; cloud features use their selected service.
Smart Routing
Connect supported providers and choose models for each task. Availability depends on credentials, quota and model capability. Explicit model choices report failures instead of claiming another model succeeded.
WayEditor
In-repo editor with tabs, syntax highlighting, find/replace, undo/redo, file tree, terminal, and Git workflows.
1004 Agent Tools + 2105 Commands
1004 tools, 48 Flow templates, AI review, security scan, Git, deploy, creator, data, and operations workflows in one local-first IDE.
Security-First
Encrypted credential storage and workspace checks support your chosen workflow. Chat answers without tools; Agent requests approval for actions; Engineer follows its autonomous permissions.
✓ npm audit · auto-fixed, 2 deps pinned & tracked ✓ AES-GCM · keys never in localStorage ✓ File writes · workspace-validated
way CLI
A project CLI for dev, build, lint, and release — install once, run from anywhere.
$ way dev $ way build $ way release
Hold It AI (NOVA Agent Inside)
Ask by voice or type in the Companion. On Windows, hold Ctrl+Shift to ask a question; optionally mark a screen region during that hold. Release to submit. A GLB file is not required to ask for a visual lesson.
✓ Dual Theme · Editorial Light & Titanium Dark ✓ Ctrl+Shift · Ask with or without marking ✓ Multi-Language · English, Telugu, Hindi, Tamil ✓ Selected AI service · microphone permission required
Screen-Aware Visual Teaching
Ask how something works. Hold It can generate a teaching scene with 2D drawings, 3D geometry, labels, arrows and step narration directly over your screen. Local GLB import is an optional exterior reference. Generated geometry is educational, not verified CAD.
✓ Vector Arrows, Polygons & Curves on Screen ✓ Dynamic Step Controls · Prev, Next, Repeat & Explain More ✓ Generated teaching geometry · references when available ✓ Rotate, inspect and close the lesson overlay
Spatial Context & Smart Cursor Dictation
On Windows, hold Ctrl + Shift, mark the relevant screen area if needed, and speak your question. Ask to prepare and insert text into a marked editable field. Capture, transcription and field verification must succeed before an action is reported as complete.
✓ Windows shortcut · Ctrl+Shift ✓ Spatial Area Selection · Auto Coordinate Detection ✓ Non-Destructive Cursor Text Insertion ✓ Terminal Command Preview & Safe Execution
Universal API Keys (All Agents & Models)
A single API key connects external web apps, mobile clients, and automation scripts to every autonomous Way AI agent (NOVA, Engineer, CampaignX, Creative Studio) and 10+ AI models (Gemini, Claude, GPT-4o, DeepSeek, Groq, Mistral, NVIDIA NIM).
✓ Universal All-Agents Access · NOVA, Engineer, Creative, CampaignX ✓ Multi-Provider Cascades · Gemini, Claude, GPT-4o, DeepSeek, Groq ✓ REST & Python SDK Support · Instant Bearer Token Auth ✓ Zero Configuration Lock · Granular Scopes & Live Key Management
02 — Workspaces

Four workspaces. One Way AI platform.

Move between hands-on code, autonomous building, agentic tasks, and visual workflow automation without leaving the same project context.

Way AI Code
Code Workspace

A local-first IDE surface for precise file edits, terminal work, Git, search, tabs, and AI-assisted changes.

WayEditor, file explorer, terminal, source control, global search Chat, Agent, and account routing inside the coding workflow Best for existing projects, bug fixes, refactors, and reviews
Way AI Agent
Agent Workspace

A 1004-tool agent for scoped, conversational tasks — file edits, security scans, tests, and multi-agent review, without a full build.

Architect · Executor · Reviewer multi-agent runs, swarm coordination 2105 slash commands, custom agent wizard, Knowledge Graph memory Best for scoped tasks, audits, and reviews inside an existing project
Way AI Engineer
Engineer Workspace

A full build agent that plans, generates, installs, tests, fixes, previews, and prepares projects from one prompt.

Autonomous app, website, dashboard, tool, and prototype generation Preview, logs, runtime monitoring, visual comments, and share flow Uses the same accounts, skills, tools, memories, and workspace files
Way AI Flow & CampainX
Visual Flow Studio

Unified node-based visual orchestration across pro-code engineering and CampainX marketing automation.

Full 9-tab inspector: Configure, Guide, Input, Output, Schema, Credentials, Execution, Artifacts, Notes Interactive curved Bezier wires, real-time minimap, pan/zoom controls, and live task log console 4,552+ curated marketing automation templates with bi-directional synchronization and NOVA voice commands
02.1 — Bring Your Own CLI

Already using Claude Code, Codex, or Gemini CLI? Keep using them — in one window.

Way AI Code doesn't replace the CLI tools you already trust. Each one gets its own sandboxed tab in the same editor, streaming real output back into your workspace instead of a separate terminal.

Claude Code CLI
Drives your locally installed claude CLI — same login, same account, no separate key to manage. Replies stream straight into their own tab.
$ claude -p "add input validation" ✓ streamed into the Claude Code tab ❯
Codex CLI
Runs your installed codex CLI inside the active workspace — the git-trust prompt that normally blocks a first run is handled for you.
$ codex exec "refactor the auth module" ✓ workspace trusted · no prompt ❯
Gemini CLI
Runs gemini in non-interactive plan mode, so it never sits stuck waiting on an approval prompt you can't see.
$ gemini -p "explain this diff" ✓ plan mode · no stdin wait ❯
How it actually runs — each CLI is spawned as its own sandboxed process (Windows Job Object, capped memory, no visible console window), and file writes still need your approval in workspace-write mode. Desktop app only — the web build doesn't spawn local processes. Claude Code, Codex, and Gemini CLI are products of Anthropic, OpenAI, and Google respectively; Way AI Code connects to your own local installation and login for each and is not affiliated with, endorsed by, or sponsored by any of them.
02.2 — Also Inside Way AI Code

Beyond the editor: a production studio and a voice desk.

Creative and engine workspaces that live in the same app, the same account, the same window.

THE CREATOR & 3D Comic Studio
Plan a storyboard, prepare visual assets, add voice and captions, then render and export. Local image-based animation and provider-generated motion are distinct output types. Each requires a working engine; a still preview is not a completed video.
Sovereign Voice Desk (VoiceDesk Studio)
Prepare narration and audition voices from VoiceDesk. The desktop service and selected speech engine must be available; some speech providers require internet access. Listen to the actual output before exporting.
Way AI Job Engine
Local-first career matching, resume optimization, and AI cover letter generation. Zero auto-submit bots — you remain in total control of every single click.
03 — Delivery Loop

From a good idea to a confident release.

The Delivery Loop keeps each workspace focused on the next piece of evidence: clarify the outcome, make the change, validate it, and decide whether it is ready. Nothing pushes or deploys on its own.

Way AI Agent
Delivery board — offline project search
Current focus: Verify
✓
ShapeOutcome and scope
✓
DesignSmallest safe approach
✓
BuildFocused implementation
4
VerifyTests and user paths
5
ReleaseGo / no-go decision
6
LearnKeep durable follow-ups

Evidence-first. Plans, audits, acceptance checks, and release checks are separate, explicit actions.

Try the Delivery Loop
04 — Inside Way AI Code

Four workspaces. One account, one file context.

Code, Flow, Agent, and Engineer all run on the same 1004-tool registry and the same connected account — pick the tab to see what each one actually does.

App.jsxindex.cssserver.ts
12function verifyAuth(req) { 13 const token = getToken(req) 14 return jwt.verify(token, SECRET) 15}
$ /rewind
Restored snapshot from 2 min ago — App.jsx
$ git diff --stat
1 file changed, 3 insertions(+), 1 deletion(-)
WayEditor
Multi-tab editor with syntax highlighting, find/replace, undo/redo, a file tree, and an integrated terminal — no separate app to switch to.
Automatic file snapshots
/rewind lists and restores automatic snapshots taken before every agent edit — undo an AI change the same way you'd undo a typo.
Git built in
Source control panel and terminal share the same window — stage, diff, and commit without leaving the editor.
Workspace-wide search
Search across every file in the project and jump straight to the matching line.
Agent-scoped edits
Ask for a change to one file, a component, CSS, API code, config, or an entire folder — the agent stays inside the scope you gave it.
Local or cloud AI, same window
Switch between Ollama, LM Studio, or 10+ cloud providers from the same account bar used everywhere else in the app.
▷
Webhook Trigger
Ready
✦
AI Classify
Ready
⑂
If / Else
Ready
✓ true
✉
Send Email
Credential Required
✗ false
◔
Log & Retry
Ready
13,906
Searchable cloud template gallery
Browse 13,906 cloud templates across 9 categories — Business Ops (3,901), Email & CRM (3,420), Analytics (3,009), Social Media (1,339), Dev & DevOps (901), E-commerce (746), Audio & Video (224), HR & Hiring (195), Content AI (171) — each scored for validation and one click from import. Every result also shows the 48 fully offline-ready templates that ship in the app with no network needed.

48 offline-ready templates across 13 categories

Bundled in the app — no network needed. Every category ships at least one real, runnable example, not a placeholder.

📦 Automation Reference Pack14
⚡ NOVA Forge5
🚀 Growth4
📱 Social Media3
📧 Email & CRM3
🎨 Content AI3
💼 Business Ops3
🛒 E-commerce3
📊 Analytics3
🎬 Media AI2
🔧 Dev & DevOps2
👥 HR & Hiring2
🎵 Audio & Video1
GrowthWebsite Sales Lead → WhatsApp Alert
Social MediaComment-to-Lead Capture
Email & CRMCustomer Renewal Assistant
Dev & DevOpsAPI Incident Triage
E-commerceOrder Exception Control
HR & HiringEmployee Access Onboarding
See all 48 templates, with details →
Encrypted credential vault
API keys and OAuth tokens for every connector live in AES-GCM secure storage, never plaintext — with automatic migration off the old localStorage format and silent token refresh before expiry.
Crash-safe workflow store
Flows, versions, and run history persist to a durable, file-backed store with atomic writes — a crash or restart never loses an in-progress automation.
Run queue with retries
Executions go through a concurrency-controlled queue with automatic retry and backoff, so a flaky webhook or rate-limited API doesn't fail your whole flow.
Per-node readiness checks
Every node reports Ready, Setup Required, Credential Required, or Local Runtime Required before you hit run — no debugging a flow that was never going to work.
NOVA narrates your flow
Ask Way AI to build a flow from a prompt and NOVA talks you through it out loud while it drafts nodes, wires connections, and repairs invalid configs automatically.
Connector SDK
A pluggable connector registry with audit logging, retry policies, and credential resolution — build your own integrations without touching core Flow code.
Just reviewed for this release — undo/redo canvas history, right-click node and canvas context menus, drag-select multi-node editing, autosaved flow drafts synced to your account, and self-hosted media pipeline nodes (image/video generation) with local or remote GPU workers and result caching. All verified against the test suite before shipping.
read_fileApp.jsx✓
security_scansrc/0 issues
run_bashnpm test✓ 42 passed
git_commit
1004 tools, 37 categories
File edits, git, security scans, tests, and deploy checks — the same registry verified earlier on this page, called automatically as the agent works.
2105 slash commands
Every skill is also a typed /command you can call directly when you want to skip the conversation.
Custom agent wizard
Build a named agent with its own system prompt and allowed tool list through a guided wizard — no config files to hand-edit.
Architect · Executor · Reviewer
/multi runs three specialized agents on one task — a planner, an implementer, and a reviewer that checks the result for bugs and regressions.
Knowledge Graph memory
Indexes files, components, functions, APIs, and past decisions so the agent recalls prior context instead of re-discovering your codebase every session.
Swarm coordination
Fans a task out across 2–16 specialist agents — researcher, fixer, tester, reviewer — for debugging, review, or architecture work too large for one agent.
Plan
Generate
Install
Run
Fix
Validate
ReloadDesktopMobileOpenCopy URLSnapshotCommentsDeployShare
Six-phase build loop
Plan → Generate → Install → Run → Fix → Validate — the same phases the app tracks internally while it builds, not marketing labels.
Live preview toolbar
Reload, switch between desktop and mobile viewport, open the preview externally, or copy its URL — all from the same running build.
Visual comments
Click anywhere on the live preview to leave a comment the agent reads and acts on directly — no separate bug tracker needed.
Automatic fix loop
Failing tests, install errors, or crashes are caught and retried automatically before the build is handed back to you.
1004 tools available
The same tool registry used in Agent mode — analysis, security scans, and build verification run as part of every Engineer build.
One-click share
Hand a running preview link to a teammate or client straight from the toolbar — no separate deploy step required to show progress.
05 — Core

Core: a live map of your business, not just your code.

Departments, staff roles, and integrations rendered as one connected graph — with every money, legal, hiring, customer-facing, or destructive action held for your approval before it runs. Nothing executes on its own.

Safe Autopilot v1 — held for your approval: Send invoice reminder to 12 customers
9 departments, one graph
CEO/BrainOS, Sales, Comms, Finance, Docs/Legal, Operations, Web/Growth, Media Studio, and HR/Admin — each with defined staff roles and capabilities, rendered as a live, rotating 3D node graph you can explore.
Safe Autopilot v1
Six escalating autonomy levels, from observe to full execution. Anything touching money, legal, hiring, customer sends, or destructive actions is automatically held for your approval — enforced server-side, not just a UI setting.
16 connectors, 8 categories
Stripe, GitHub, Twilio, SendGrid, YouTube, OpenAI, Gemini, and more — wired directly into the departments that use them, from Finance to Media Studio to Developer Ops.
Call it whatever you want
"NOVA" is just the default. The wake word is a plain text field — type any name and that's what activates it. No fixed identity, no restrictions.
What Core actually is — a planning and approval-gated automation layer, not an autonomous decision-maker. It drafts, recommends, and queues; you approve. Every action that touches money, legal, hiring, or a customer directly requires your explicit sign-off before it executes.
06 — Modes

Two modes. One serious builder.

Code Mode and Engineer Mode both work with local AI or cloud AI. Choose the workflow that matches the job.

Code Mode
Editor + agent assist

For hands-on coding. Edit manually, ask the agent to change an individual file, work inside an existing folder, or make a targeted fix without losing project context.

Manual editor workflow with WayEditor, terminal, Git, and file tree.
Agent can edit one file, a component, CSS, API code, config, or an entire folder.
Best for existing projects, bug fixes, refactors, and precise file changes.
Local AICloud AIPrecise edits
Engineer Mode
Full build agent

For building complete outcomes from a prompt. Ask for apps, websites, small games, Excel sheets, tables, dashboards, management tools, or automation flows.

Plans the work, creates files, runs commands, installs dependencies, and opens preview.
Uses 1004 tools for analysis, security, build checks, file edits, testing, and verification.
Best for new products, dashboards, internal tools, prototypes, and complete workflows.
Local AICloud AIFull build
Plan
Generate
Install
Run
Fix
Validate
07 — Compare

Way AI vs the rest.

Feature
Way AI Code
Lovable
Replit
Works offline
✓
✗
partial
Local AI (Ollama)
✓
✗
✗
Free tier cost
₹0
$20+/mo
$20+/mo
Full code editor
✓
basic
✓
Terminal + Git
✓
✗
✓
Data stays local
✓
✗
✗
Agent tools
1004
~15
~20
08 — Pricing

Honest pricing. Zero lock-in.

Free forever with local AI. Upgrade only for cloud power.

Free Trial
₹0/3 months
Full IDE + 90 days complimentary studio access.
✓3 Months Free: CREATOR & VoiceDesk
✓3 Months Free: Job Engine
✓Unlimited Ollama / LM Studio local models
✓All 1004 agent tools & Developer suite
✓Full IDE + Terminal + Git forever
Download Free Trial
Most Popular
Cloud Studio
₹399/mo
Connected cloud generation. Provider access and quota required.
✓Full THE CREATOR & 3D Comic Studio
✓NOVA VoiceDesk (Cloud Voice Cloning)
✓Auto Reel 9:16 Video Generator
✓Way AI Job Engine with AI cover letters
✓Google Veo & Higgsfield motion video
Start Cloud Studio →
Best Value · Power Users
Power Engine
₹1,299/6 mo
Offline local engine. Unlimited device rendering.
✓Everything in Cloud Studio Plan
✓Unlimited local FFmpeg video & comic exports
✓Local VoiceDesk engine with zero credit costs
✓Offline AI models & private project vault
✓Priority local processing queue
Get Power Engine →
Teams
₹2,999/mo
Multi-seat collaboration & enterprise sync.
✓Everything in Studio & Power Engine
✓2000 cloud requests/month
✓Claude Opus 4 · GPT-5 models
✓Team memory sync · 5 users included
✓Invoice billing & dedicated support
Contact Sales
Accepted payment methods
UPI GPay · PhonePe · Paytm Credit Card Debit Card Netbanking
09 — Upcoming

What's next out of Way AI Labs.

Early looks at what we're building on top of the in-training Way AI LLM.

Coming soon

3D Core Studio

Describe a scene in plain language and Way AI generates a live, editable 3D model right inside Core — powered by the same proprietary Way AI LLM that's still in training. A preview build is up now; the in-app workspace lands once training completes.

Preview 3D Core Studio → Way AI LLM training in progress — this is a preview build, not the shipping feature.
10 — About Us

Way AI Labs builds tools for independent builders.

Way AI Code is created by Way AI Labs under Gadadhara Home Innovations OPC Pvt Ltd, Hyderabad.

Mission
Local-first AI development without platform lock-in.

We are building an AI IDE where developers can use their own machine, their own models, and their own rules. Way AI Code combines a real editor, terminal, Git, local models, cloud providers, 1004 agent tools, 48 Flow templates, and product-ready workflows so a prompt can become a working app.

CompanyGadadhara Home Innovations OPC Pvt Ltd, based in Hyderabad, India.
Way AI LabsAI product studio behind Way AI Code and the upcoming proprietary Way AI LLM.
Product ecosystemWay AI Code, Interioway, Comfort Corner, and future AI products under one builder-led company.
PromiseFree local AI, transparent upgrades, and tools that keep control with the developer.
The Founder

Ajay Kumar Veera

Civil Engineer Structural Engineer MBA Data Science AI Builder Hyderabad, India

Civil and structural engineer turned AI builder. After an MBA and specializing in Data Science, built Way AI Code — a local-first IDE with 1004 agent tools, 10+ AI providers, and a complete auth/billing backend. Ships apps from a single prompt. Supports local models and connected services, depending on setup.

Under Gadadhara Home Innovations OPC Pvt Ltd, also runs Interioway® (AI interior design) and Comfort Corner (sofa & furniture manufacturing) — all from Hyderabad.

Civil Engineering Structural Engineering MBA · Data Science AI / ML Tauri · Rust · React Interior Design Furniture Manufacturing
Gadadhara Home Innovations OPC Pvt Ltd
Registered company · Hyderabad, Telangana, India
Way AI Labs · Interioway® · Comfort Corner
11 — Contact Sales

Need teams, training, or custom rollout?

Send your requirements to the Way AI Code team. Submissions are saved and emailed straight to sales@wayaicode.com.

Based inHyderabad, India
We read every message personally — no ticket queue.
Saved to our system and emailed to sales@wayaicode.com. If sending fails, your email app will open instead.

Start building. It's free.

Download Way AI Code. Bring your own models.
Choose local models or connected providers. Review setup, quotas and charges.

Download for Windows — Free Open Web App

"Choose your models and services. Built in India."

All versions

Every Windows release, newest first. Need to roll back? Install any earlier build below — it replaces the one you have.

  1. v2.50.1 Latest

    Way AI Code v2.50.1: Renamed sovereign telephony suite to Way AI Telecaller with pure Way AI Code dark obsidian design system tokens (#0C0D10, #141518, #18191E, #26282E, #EDEEF0, #8C8F98), removing all third-party color accents. Retains full Edge-TTS neural voice synthesis (Ajay Male & Saryu Female personas), 1-click Nothing Phone (1) wireless ADB contact sync (1,405 contacts), drag-and-drop brochure upload, automated WhatsApp catalog delivery, and sequential campaign dialer.

  2. v2.50.0

    Way AI Code v2.50.0: Sovereign Festival Telecaller Studio & Multi-Source Contact Hub integrated into Desk tab with luxury InterioWay theme (#163A2B, #C5A059). Supports Telugu Edge-TTS neural speech (Ajay Male & Saryu Female), 1-click Nothing Phone (1) wireless ADB contact sync (1,405 contacts), drag-and-drop brochure upload, automated WhatsApp catalog delivery, and sequential campaign dialer.

  3. v2.49.2

    Way AI Code v2.49.2: Complete Hold It AI 1:1 Android parity with zero-freeze non-blocking pass-through reticle and smooth 60 FPS OS cursor tracking. Professional Lucide SVG vector icon design across Companion Cube Mascot Studio, Companion Hub, and Recap modal with pure obsidian aesthetic. Seamless live web deployment and desktop installer update.

  4. v2.49.0

    Way AI Code v2.49.0 (Hanuman Red Kite AI Companion & Hold It AI Screen Guide Architecture Overhaul): 1:1 Android Hanuman Red Kite AI Companion Cursor with dual-facet vermilion/maroon shading, white spine strut, sinusoidal waving tail, 5 dynamic cyan sound wave bars, and revolving thinking spinner. Complete Screen Guide unfreeze architecture with non-blocking asynchronous screen capture, initial pass-through set_ignore_cursor_events, and instant Escape key dismiss. Dedicated in-app Hold It & Screen Guide Settings modal (In-App Fluid 144Hz vs Desktop OS Window, Ctrl+Shift hold duration slider, Web Audio mechanical click synthesizer, Telugu/English preferences). Neatly redesigned Light Luxury Editorial bottom companion popup with frosted glass capsule, 1-click Mark Screen button, and quick action chips. Web deployment to app.wayaicode.com and desktop installer sync.

  5. v2.48.0

    Way AI Code v2.48.0 (Living Mascot Studio & Screen Guide Overhaul): Redesigned Mascot Companion to Living Bouncy Cube in Way AI Studio with dynamic sound synthesis and beat sync. Clicky Windows 3-tier hybrid pointer and interactive tutor core. Live workspace vision explain, autonomous voice navigation, and daily Instagram scheduled flow agent with Prompt Enhancer. Integrated Screen Guide completeWorkflow engine with Hold It AI speech bubbles and core runtime injection.

  6. v2.47.0

    Way AI Code v2.47.0 (ACP & Safety Architecture Overhaul): Standard Agent Client Protocol (ACP) JSON-RPC 2.0 daemon (`way acp`) enabling external IDEs (VS Code, JetBrains, Cursor, Zed, Neovim) and programmatic pipelines to command Way AI Code headlessly. Zero-Interference Pure Ctrl & Shift Global Windows Shortcuts via native Win32 low-level hook (`WH_KEYBOARD_LL`) with 100% Escape key pass-through. Multi-Tier ExecutionGuard with 4-level deterministic risk classification (Safe, Moderate, High, Critical) and Infinite Loop Prevention (repeat-tool-reminder). Transactional SessionEventLog (.jsonl streaming) for durable audit trails and Haute Ghost Living Screen Companion.

  7. v2.46.1

    Fix: CLI Tab 'Allow file edits this turn' checkbox is now fully interactive and clickable across Claude Code, Codex, and Gemini tabs. Eliminates disabled checkbox and auto-promotes System Control Mode from Safe to Developer mode upon check with real-time UI synchronization, ensuring file edits proceed without requiring manual navigation to Settings.

  8. v2.46.0

    NOVA Voice Agent & Model Picker Resilience Overhaul: Comprehensive Telugu and English wake word detection ('నోవా', 'మేలుకో', 'విను', 'Hey Nova', 'Jarvis') with fuzzy phonetic tolerance. Fixed desktop AudioContext auto-resume and continuous chunk buffering. Model Picker Direct Routing: Explicitly selected models (Claude, Gemini, GPT-4o, DeepSeek, etc.) bypass credit router proxy and dispatch directly to user accounts. Fixed silent empty model reply failures with multi-tier emergency auto-fallback and proactive agent re-prompting.

  9. v2.45.0

    Universal Corner-by-Corner Live Testing Engine & In-App Diagnostics Center: Full subsystem verification suite with real-time health telemetry across all 12 core application pillars (Safe Storage, Multi-Workspace Isolation, Agent Sessions CRUD, Scheduled Task Manager, AI Provider Routing & Fallback, Flow Readiness & Connector CSP, Web Audio & Indic Voice, Monaco Virtual FS, Creative Studios, Security AST Guard, Event Bus, and Active Projects). Integrated Live Testing Center into the Test Panel and Status Bar with real-time health orb, 20-second background monitoring, one-click auto-heal for quota/registry recovery, latency benchmarking, and instant JSON diagnostics export.

  10. v2.44.0

    Way AI Engineer 100% Autonomous Overhaul & Universal Live Preview Canvas: Fixed mid-run freezes and 'No AI account found' blockers with automatic multi-hop provider rotation (Claude, ChatGPT, Gemini, Groq, NVIDIA, Ollama), auto-unbenching, and resilient offline Ollama (11434) detection (Qwen 2.5 Coder, Llama 3.2). Injected fullstack-dev, visual-review, and animation skills autonomously into execution and planning. Modern glassmorphic dark-mode responsive design rules for all frontend components and robust Express + SQLite3 REST backend generation with live sample data seeding. Universal interactive preview generator covering 8 app categories (Finance, E-Commerce, Tasks/Kanban, Chat/Social, Analytics, Games, Websites, Full-Stack Apps) with dual-probe IPv4/IPv6 localhost resolution, eliminating dev server timeouts and blank error screens.

  11. v2.43.0

    Unified Sovereign Indic Voice Engine & 1-Click Multi-Engine Workstation: Complete architectural unification of voice settings across NOVA, VoiceDesk Studio, and Creative AI Settings. One-click online activation and real-time status monitoring for all 5 workstation engines: ComfyUI (8188), Wav2Lip (7861), Stable Diffusion (7860), Ollama (11434), and VoiceDesk (8010). Fixed voice audition routing and eliminated robotic Windows browser fallback so tests consistently play calibrated neural Telugu/Indic personas with exact speed and pitch.

  12. v2.42.0

    Unified Way AI Marketing & Creative Flow Engine: 52+ Curated Autonomous Flow Templates spanning Fashion & E-Commerce, Food & Hospitality, Home Decor & Interior, Automotive & Electronics, and Cosmetics & Fitness. Features zero-configuration AI Provider Router (OpenAI, Claude, ElevenLabs, Higgsfield, Gemini, Suno AI, Sovereign Indic-TTS) with User Vault auto-injection (brand logos, theme colors, social tokens, compute credits). Interactive Preview & Scheduling Hub with 1080p 60fps video player, format switcher (9:16 Reel, 16:9 YouTube, 1:1 Square), and 1-Click Action Controls: Direct Post Now (omni-channel broadcast), Schedule on Calendar, and Save Preset Draft to Vault.

  13. v2.41.0

    Creative AI Control Center: Unified workstation for image, video, audio, lip-sync, local engines, camera defaults, and generation history. Integrated Image Studio (Text-to-Image / Image-to-Image with style presets and aspect ratios), Video Studio (Text-to-Video / Image-to-Video with cinema camera motions), Audio Studio (Sovereign VoiceDesk Indic neural TTS with 8 native personas, pitch/speed DSP sliders, quick audition), Lip-Sync Studio (Character face portrait + speech audio talking head synthesis), Camera Defaults & Directives (11 cinema camera presets, lens specs, lighting environments, and prompt enricher), Local Engines Dashboard (real-time live probe of ports 8010, 8188, 7861, 7860, 11434 with latency tracking and 1-click relaunch), and Generation History Vault (searchable, filterable gallery with one-click prompt re-use and media downloads).

  14. v2.40.1

    Fix: Granted dialog:allow-confirm and dialog:allow-ask in desktop capabilities ACL to fix unhandled rejection when confirming tool actions, model downloads, or deletions. Added resilient try/catch fallback in confirmDialog.

  15. v2.40.0

    Multi-Project Command Center & Context Isolation Engine: Complete Display Options with Group By (Project, Workspace, Status, None), Sort Conversations (Last Updated, Last Prompt, Alphabetical, Date Added), and Archived Only filter. New Project dropdown with native folder picker and Quick Start. Project row hover actions (+ New Conversation in Project, ⋮ Project Context Menu with Copy Name, Settings, Show in File Explorer, and Delete Project). Empty project state showing 'No conversations yet'. Conversation row hover actions (⋮ Menu with Rename, Mark Unread, Copy, Split, Delete; 📌 Pin to top with pushpin badge; 📥 Archive). Floating status preview card on hover showing full prompt preview text, project name, Active badge, and formatted timestamp.

  16. v2.39.0

    Multi-Project Command Center & Explorer: Unified multi-project orchestration hub in Way AI Agent workspace. Quick actions for + New Conversation, Conversation History, and Scheduled Tasks. Conversation History modal with cross-project search and instant context switching. Scheduled Tasks manager with custom schedules and Flash execution. Prompt composer with Project Selector dropdown, Worktree popup menu (Local / New Worktree), and branch switcher.

  17. v2.38.0

    Sovereign VoiceDesk Engine: 100% private, local Indic neural voice synthesis on port 8010 with 1-click background launch and zero terminal setup. 8 native Indian personas (Madhuri, Aditya, Priya, Vikram, Sneha, Rohit, Neerja, Rohan) with authentic Telugu, Hindi, and Indian English cadences and natural breath pauses. Real-time Tone & Acoustics Bar: dynamic Pitch shift (0.50x to 1.50x), Speed, and Echo/Reverb DSP sliders. Instant Quick Audition: 1-second preview playback in <0.5s without retyping full scripts. Unified CampainX Creative OS & Visual Flow Studio: full 9-tab inspector parity (Configure, Guide, Input, Output, Schema, Credentials, Execution, Artifacts, Notes), interactive Bezier canvas, real-time Minimap, pan/zoom controls, live Task Log console, and 4,552+ curated marketing automation workflow templates with bi-directional synchronization and autonomous NOVA agent voice orchestration.

  18. v2.30.0

    New: a photo template. Take the next unposted picture from your Drive category folders, crop it to the shape Instagram shows largest, add your logo, handle and a contact strip along the bottom, write the caption and hashtags for its category, and post it to Instagram and your Facebook Page - logged so the same picture never goes out twice. Fix: the desktop app could not reach its own native layer after the last update, which stopped NOVA's voice commands, the active workspace path and file operations. Fix: right-click and text selection in the code editor, which the desktop content policy was silently blocking. Fix: the editor counted errors for files you had already closed.

  19. v2.28.0

    NOVA now works on its own when you want it to. Autonomous mode carries out file edits, commands and Flow changes without asking each time, and saying “stop” or “ఆగు” cancels whatever it is doing immediately — not just what it is saying — with no wake word needed. NOVA also remembers you between sessions: say “remember that …” and it keeps it, and it carries your last conversation forward instead of starting as a stranger. Ask for a rocket, car, vase, bottle, cup or house in 3D and NOVA draws the 2D profile and builds it in Blender. Deleting is still refused in every mode.

  20. v2.27.1

    Fix: the background error banner that appeared while editing code — the AI inline completions provider was missing a hook the editor calls when it tears a suggestion down. NOVA can now open any app you have installed, not just a fixed list: it finds it the way you would say it, including shorthand like "vs code" or "ms word". NOVA can also edit a node in the Flow you have open by voice — say which node and what to change, and it asks before touching your workflow.

  21. v2.27.0

    Licensing is now verified on your device by signature instead of a local setting, so the paid studios cannot be unlocked by editing anything on the machine. Your licence is fetched and renewed automatically when you are signed in, and keeps working offline for 90 days. NOVA can now search your workspace, read and edit files, run commands and start Flows — file edits, commands and Flow runs ask first, and NOVA never deletes anything. Fix: THE CREATOR no longer shows "Something went wrong" when local storage fills up.

  22. v2.26.14

    Multi-project workspace support: open and run multiple projects simultaneously in the same window with live agent context and file operations across all folders. Fix: desktop Monaco code editor loading in Windows WebView2. THE CREATOR: self-healing storage eliminates quota exceeded errors, storyboard motion clip and voiceover generation buttons, 1-click reel mode switcher, and private Cheetah trading desk integration.

  23. v2.26.13

    The Drive folder now decides a video's type before the AI, so cards, category, playlist and hashtags follow your folders.

  24. v2.26.12

    Complete posts by video type: YouTube title, description, tags, category, playlist, language, recording date and AI / paid-promotion disclosures; Instagram caption with hashtags, contacts and cover frame; Facebook title and description. Fixes blank titles and captions.

  25. v2.26.11

    Stylish animated cards with styles (motivation, sales, work in progress, project completed) chosen by you or AI; scheduled runs missed while the computer was off catch up when back online; failed publish steps show red; YouTube uploads stay on the chosen channel.

  26. v2.26.10

    Fix: YouTube auto-publishing works with a Google login that has upload permission only (it failed with insufficient authentication scopes).

  27. v2.26.9

    Fix: an expired Google Drive or Sheets login no longer stops a Flow when another saved Google login works; expired logins renew with the OAuth client saved on Google Workspace.

  28. v2.26.8

    Fix: Flow steps reading Google Drive and Sheets, or posting to Instagram and Facebook, failed in the desktop app with Failed to fetch. Those services are now allowed.

  29. v2.26.7

    One-click updates: Update Now installs and reopens the app, plus an Update automatically option. The update notice appears reliably again. Building a Flow in chat now handles video auto-publishing end to end: Drive videos, logo and contact details, one step per platform, peak-time posting and no duplicate posts.

  30. v2.26.6

    Auto-publishing brands every clip: your logo in the corner you choose (Google Drive link or a file on this computer), and an end card with the logo large, your closing line and your phone, WhatsApp, website, email and address over dimmed footage.

  31. v2.26.5

    Flow canvas: press the mouse wheel and drag to pan from anywhere, even over a node; scroll moves the canvas, Shift+scroll moves sideways, and Ctrl+scroll zooms the canvas instead of the whole window. Workspace picker text readable again.

  32. v2.26.4

    Drive to social auto-publishing really posts: the next unpublished clip from your Drive category folders is captioned by AI, branded with ffmpeg and published as an Instagram Reel, YouTube Short and Facebook Page video at its peak time, then logged so it is never posted twice. New Run on schedule here switch and a redesigned workspace picker.

  33. v2.26.3

    THE CREATOR runs as one pipeline (project types, consistent characters, storyboard, animation, caption position). Google sign-in fixed, CLI tabs no longer fail with directory name is invalid, voice-over falls back across routes, exact token counts in Accounts.