EXPERIMENTS & LABS

Labs: where the next company starts.

15 active experiments — domain AI, spatial computing, native apps, voice capture, autonomous orchestration, and product factories that scale.

GAME DEV + EDUCATION

Godot 4.x Game Engine

Station Zero (sci-fi base builder) and Himalayan Dawn (atmospheric explorer). Export to Mac, Windows, iOS, Android, and Web — no Unity/Unreal overhead. Godot engine, continuous improvement via GDScript + Rust plugins.

2 games · 28 tasks · 70% complete
Click to expand ↓

Done

  • Godot 4.4 project scaffold (GDScript)
  • Himalayan Dawn procedural terrain
  • Atmospheric fog + lighting system
  • Station Zero base-building grid
  • Cross-platform export pipeline
  • Sprint orchestration via DevPilot

In Progress

  • Station Zero resource management
  • Himalayan Dawn exploration mechanics
  • Godot + Rapier physics integration
  • Educational module generation for Saathi

Planned

  • AR/VR/3D educational views by age level
  • DevPilot plugins for Godot
  • Dynamic difficulty filters via DP
  • WASM export for browser play
  • Steam + itch.io listing
Godot 4.4GDScriptRapierWASMCross-Platform
View in Portfolio
EDUCATION OPEN SOURCE SOON

Saathi Explorer

Interactive 3D learning platform — atoms, molecules, DNA, and beyond. Built with Three.js + Rapier physics (Rust → WASM). Open-source, community-driven. Our contribution to education — empowering learners of all ages to never stop exploring.

10 GLB models · 45 topics · 42/42 done
Click to expand ↓

Done

  • 10 GLB 3D models (atoms, molecules, DNA)
  • Three.js renderer with orbit controls
  • 45 STEM topics with interactive views
  • PWA manifest + offline support
  • Rapier physics in Rust → WASM
  • All 42 sprint tasks complete

Tests & Results

  • GLB model loading: <1.2s avg
  • 60fps on M1+ MacBooks
  • WebGL fallback for older GPUs
  • WASM physics: 120fps simulation

Vision

  • Beyond STEM: AI, Robotics, Agriculture, Health
  • AR/VR views via Godot + WebXR
  • Dynamic age-level filters
  • Bridge: students → academia → industry
  • Open source (copyleft) — free forever
Three.jsRapierRust WASMPWAAGPL-3.0Free Forever
Visit Site
AI SURVEY

Conversational AI Surveys

42-question interactive survey with research context injection. Chat-based UX for founder decision-making. Purpose-built for technical founders.

1,821 LOC chatbot · 7 gateway methods
Click to expand ↓

Done

  • 1,821 LOC chatbot UI (web/survey/)
  • 7 gateway JSON-RPC methods
  • Survey template engine in DB
  • 12+ architecture decisions per survey
  • Research context injection into questions

In Progress

  • Password-protected shareable surveys
  • Voice-first survey capture (Telegram bot)
  • Auto-sprint creation from answers

Key Experiments

  • 6 surveys completed (TryOn, 3DPilot, OSS, SaaS, Domain, Voice)
  • JotForm competitor research (35M+ users)
  • ZK proofs for survey integrity
Alpine.jsJSON-RPCPostgreSQLTemplates
Visit DevPilot
FLAGSHIP

FoundersCockpit

macOS native command center (SwiftUI). Sprint management, brainstorm agent, project portfolio, deploy pipeline. SaaS web version + mobile planned. Connects to 370+ gateway handlers.

macOS native · SwiftUI + dp-gateway
Click to expand ↓

Done

  • CoPilot Flutter app: 776 files, 17 screens
  • 370+ JSON-RPC gateway handlers
  • Sprint board with kanban view
  • Knowledge brain with 6,868 learnings
  • Real-time WebSocket connection

In Progress

  • SwiftUI macOS native rewrite
  • Brainstorm agent with visual companion
  • One-click deploy pipeline
  • Project portfolio dashboard

Planned

  • SaaS web version (Axum + Leptos)
  • iOS + Android via Flutter
  • Voice command interface
  • Multi-tenant for founders
SwiftUIFlutterWebSocketJSON-RPCmacOS
Visit Site
DOMAIN AI

Domain Expert Agents

AI Product Manager for any vertical. On-demand research + pre-built domain packs + organic learning. Temporal knowledge graphs (Graphiti + Microsoft GraphRAG). $68.7B market.

5 verticals researched · Architecture designed
Click to expand ↓

Research Done

  • 5 vertical deep-dives: medical, fintech, edtech, 3D/AR, AI/ML
  • Andrew Ng insight: coding solved, domain knowledge is bottleneck
  • $3.1B → $68.7B market (42.9% CAGR)
  • Architecture designed: 3 layers (on-demand + packs + organic)

Key Findings

  • Combines domain research with automated spec generation
  • Graphiti temporal KG for knowledge persistence
  • Microsoft GraphRAG for domain retrieval
  • IndiaAI Rs65/hr GPUs for training

Planned

  • Domain pack marketplace
  • Vertical-specific agent templates
  • Curriculum builder integration
  • MVP sprint: 8 tasks scoped
GraphitiGraphRAGKnowledge GraphsAIProvider trait
Visit DevPilot
3D / AR / VR

TryOn AI + Spatial Computing

Virtual try-on for ethnic wear (pixel-space diffusion, no existing dataset = moat). Godot 4.x game experiments. AR/VR product visualization pipeline. Three.js interactive 3D models.

Research + prototype · Multi-angle unsolved
Click to expand ↓

Experiments Done

  • Pixel-space diffusion (no VAE) preserves embroidery detail
  • Competitor analysis: OOTDiffusion, IDM-VTON, StableVITON
  • Architecture survey: 15 decisions locked
  • No ethnic wear dataset exists (moat)

Unsolved Challenges

  • Multi-angle generation from single photo
  • Embroidery/zari detail preservation at scale
  • Custom dataset creation pipeline

Planned

  • AR try-on with Apple Vision Pro
  • WebXR browser-based try-on
  • B2B API for fashion retailers
  • Ethnic wear dataset (sarees, lehengas)
DiffusionThree.jsGodotWebXRARKit
View in Portfolio
NEWSLETTER

PostPilot

AI-powered newsletter platform. Listmonk + AWS SES = Rs 1K for 100K subscribers (100–500x cheaper than Mailchimp). Founder Approval Gate for content review.

Research complete · Sprint planned
Click to expand ↓

Research Done

  • Listmonk (Go, self-hosted, AGPL-3.0)
  • AWS SES pricing: $0.10/1000 emails
  • Cost model: Rs 1K for 100K subscribers/mo
  • Competitor analysis vs Mailchimp, Substack

Architecture

  • Axum backend + Listmonk API
  • AI content generation (multi-provider)
  • Founder Approval Gate before send
  • Template library (20+ designs)

Planned

  • MVP sprint: 12 tasks scoped
  • A/B testing engine
  • Analytics dashboard
  • Multi-brand support
ListmonkAWS SESAxumAI Content
View in Portfolio
OFFENSIVE SEC

ForgeStrike Fuzzing

Smart fuzzing + vulnerability scanning engine. REST API + CLI. Generates pentest reports. Works standalone or as DevPilot red team module.

12 tasks · Scaffold complete
Click to expand ↓

Done

  • Rust CLI scaffold with clap
  • HTTP fuzzer: header/param/path mutation
  • Report generator (PDF + JSON)
  • SecurityGate integration hooks

In Progress

  • Smart payload mutation engine
  • Rate-limiting aware crawler
  • CVE database integration

Planned

  • REST API for CI/CD integration
  • Nuclei template compatibility
  • Web dashboard for findings
  • Bug bounty program support
RustFuzzingPentestSecurityGate
View in Portfolio
PRODUCT FACTORY

LaunchGate Plugins

Every product auto-registers, inherits shared config (company, legal, brand), generates its own landing page, deploys with one click. Self-serve via FoundersCockpit.

7 sprint tasks planned · Architecture done
Click to expand ↓

Done

  • 22 landing pages deployed via LaunchGate
  • Nginx auto-config + SSL per subdomain
  • Waitlist + form submission to DB
  • GOLDEN-047 status bar on all pages
  • Deploy script: rsync + nginx reload

In Progress

  • Plugin auto-registration system
  • Shared config inheritance (legal, brand)
  • Pre-deploy verification gates

Planned

  • Self-serve via FoundersCockpit
  • Template marketplace (10+ designs)
  • A/B testing for landing pages
  • Form bot detection + DB checker
NginxrsyncSSL22 sites
Visit Site
OBSERVABILITY SPRINT 1 DONE

DSXRay — System Health X-Ray

12-step data hygiene pipeline: Discover, Classify, Score, Flag, Review, Clean, Verify, Index, Enrich, Surface, Learn, Evolve. Swift macOS native app with full terminal emulator communicating via fd 3/4 JSON protocol.

1,200 LOC · 34 tests · 8 CLI commands
Click to expand ↓

Done

  • Table health scanner + classifier
  • Hygiene scorer (0-100 per table)
  • Stale data cleaner (safe mode)
  • Full pipeline orchestrator
  • dp xray CLI (8 subcommands)
  • 34 unit tests across 6 files

In Progress

  • Gateway integration (16 methods)
  • Swift macOS native UI
  • Terminal emulator in SwiftUI
  • fd 3/4 JSON bridge protocol

Planned

  • AI-powered cleanup suggestions
  • Tiered autonomy graduation
  • Visual health dashboard
  • Auto-archive policy engine
RustSwiftSwiftUIPostgreSQLmacOS Native
AI RESEARCH $68.7B MARKET

Domain Expertise System

AI Product Manager for any vertical. Integrates domain knowledge acquisition with product specification generation. Three layers: on-demand research, pre-built knowledge packs, organic learning from sprints.

5 verticals researched · Graphiti + GraphRAG
Click to expand ↓

Research Done

  • Medical vertical deep-dive
  • 3D/AR vertical analysis
  • Fintech vertical study
  • EdTech vertical mapping
  • AI/ML tooling landscape

Architecture

  • Temporal knowledge graphs (Graphiti)
  • Microsoft GraphRAG integration
  • Domain pack format specification
  • Curriculum builder engine

Vision

  • Andrew Ng insight: coding solved, domain knowledge = bottleneck
  • Pre-built vertical packs (medical, fintech, edtech)
  • Organic learning from sprint data
  • Growing category with strong demand
Knowledge GraphsGraphRAGGraphitiAI PMMulti-Vertical
PRODUCT FACTORY PHASE 1 DONE

LaunchWave — 14-Product Beta Pipeline

12-step pipeline from ideation to beta launch for all 14 products simultaneously. Shared auth crate (surya-auth), per-product smoke tests, monitoring Docker, automated landing page generation.

11 sprints · 59 tasks · surya-auth shipped
Click to expand ↓

Done

  • surya-auth crate (13 files, 15 tests)
  • Auth migration (users, sessions, events)
  • launch_wave CLI command
  • 9 smoke test scripts
  • Monitoring Docker compose

In Progress

  • Per-product landing pages
  • Beta registration flows
  • Health check aggregator

Planned

  • 14 parallel product agents
  • Shared config registry
  • Waitlist → onboarding automation
  • Multi-product deploy orchestration
Rustsurya-authDocker14 ProductsBatch Deploy
VOICE + NLU

Voice-First Idea Capture

Telegram bot captures voice notes → STT transcription → intent classification → automatic injection into DevPilot pipelines. Ideas, bugs, and decisions via voice — anywhere, anytime.

TelegramAdapter · 615 LOC · 15 voice intents
Click to expand ↓

Built

  • TelegramAdapter (615 lines)
  • Voice controller (15 intents)
  • Survey module (9 gateway methods)

In Progress

  • voice_note handling in Telegram parser
  • Whisper STT transcription
  • Note classification pipeline

Vision

  • Multi-platform (Slack, WhatsApp)
  • Real-time transcription streaming
  • Voice → sprint task creation
  • Kokoro TTS for voice replies
TelegramWhisper STTKokoro TTSNLURust
CORE PLATFORM ACTIVE

Autonomous Platform — 85-15 Split

The vision: DevPilot handles 85% of work deterministically (sprint CRUD, builds, deploys, quality gates). AI only handles the 15% that actually needs thinking — code generation, research, spec writing. 47 MCP tools, intent classifier, 3-layer API key resolver.

47 MCP tools · 750+ JSON-RPC · 3 phases
Click to expand ↓

Done

  • 47 MCP tool bridge (complete)
  • 3-layer API key resolver
  • Survey AI chat via gateway
  • Cross-task context sharing
  • 4 reasoning format engines

In Progress

  • Intent classifier (NL → tool routing)
  • Template registry (project scaffolds)
  • Build queue coordination

Planned

  • DSXRay Swift app integration
  • Ship pipeline profiles
  • Agent observability dashboard
  • Voice command integration
MCPJSON-RPCIntent ClassifierRustDeterministic
AI + FASHION RESEARCH

TryOn AI — Virtual Fashion Try-On

Pixel-space diffusion for ethnic wear virtual try-on. Key insight: no existing ethnic wear dataset = competitive moat. Multi-angle generation is the critical unsolved challenge. Friend's idea, deep research completed.

2,441 lines of research · 15 survey decisions
Click to expand ↓

Research Done

  • Competitor analysis (387 lines)
  • Technical architecture (558 lines)
  • Planning document (1,496 lines)
  • Survey: 15 architecture decisions
  • PDF decision guide generated

Key Findings

  • Pixel-space diffusion (no VAE) preserves embroidery
  • No ethnic wear training dataset exists
  • Multi-angle generation = unsolved challenge

Next Steps

  • Train on ethnic wear dataset
  • Multi-angle pose estimation
  • Embroidery detail preservation
  • E-commerce integration
DiffusionEthnic WearPixel-SpaceComputer VisionFashion AI
MEDIA

Video & Animation Factory

Programmatic video and animated graphics generation. Manim for math/explainer animations, custom Rust renderers for data visualizations, FFmpeg pipelines for production output. All code-driven, zero manual editing.

Active · Manim + Rust renderers operational
Click to expand ↓

Built

  • Manim scene rendering pipeline
  • Rust-based chart/diagram generators
  • FFmpeg video composition automation
  • dp content render integration

In Progress

  • Animated architecture diagrams
  • Sprint timeline video generation
  • Custom motion graphics templates

Planned

  • AI-narrated product demos
  • Customer-facing explainer video API
  • Real-time dashboard video streams
ManimRustFFmpegPythonSVG
GAMES

Interactive 2D/3D Game Engine

Browser-native hyper-interactive games pushing beyond 30 FPS. SaathiAI performance upgrades with custom rendering pipelines, WebGL optimizations, and Godot HTML5 exports for educational and simulation games.

In Progress · Performance pipeline active
Click to expand ↓

Built

  • Godot HTML5 export pipeline
  • SaathiAI 3D library (Three.js + SceneKit)
  • AR marker tracking (MindAR)
  • WebGL shader pipeline

In Progress

  • 60 FPS target on mobile browsers
  • Custom rendering beyond default Godot limits
  • WASM-based physics (Rapier)

Planned

  • Multiplayer WebRTC game sessions
  • Procedural level generation
  • Educational game template library
GodotWebGLWASMRustThree.jsRapier
SPACE / VIZ

Live Celestial Viz & Simulations

Real-time star field and celestial object rendering pulling live data from astronomical databases. Accurate orbital mechanics, planetary positions, constellation mapping for education and simulation platforms.

Active · Vyomyaan engine + live data feeds
Click to expand ↓

Built

  • PSLV-XL orbital mechanics engine (Rust)
  • Stage separation + gravity turn modeling
  • Godot 4.4 3D visualization (SceneKit fallback)
  • Atmospheric drag + multi-body gravity

In Progress

  • Live star catalog data (HYG, Hipparcos)
  • Real-time planetary position API (JPL Horizons)
  • Constellation overlay rendering

Planned

  • ISS live tracking overlay
  • Satellite collision prediction viz
  • Educational planetarium mode
  • NASA APOD integration
RustGodotSceneKitNASA APIsJPL HorizonsHYG Catalog

Why experiments matter

Every product starts as an experiment. We validate with real code — not pitch decks. If an experiment proves value, it becomes a sprint. If a sprint ships, it becomes a product.

From Research to Revenue

Experiments that prove market fit become full products. AdPilot started here. QuickBill Pro started here. The lab is the first stage of a shipping pipeline, not a sandbox.

Cross-Pollination

A bug fix in one experiment prevents the same bug across 33 projects. 6,868 learnings feed every new build. The knowledge graph compounds — each experiment makes every future experiment faster.

Giving Back

Saathi Explorer is planned as our first open-source contribution — interactive 3D learning, free for everyone. What we learn from building these experiments feeds back into the platform and into the community.

Want to build with us?

Every experiment is a bet on a future company. Bring your domain and let's build one together.