Annas Bin Adil

Engineer at heart โ€ข Exploring AI, robotics & the human experience

Project archive ongoing

Things Iโ€™ve made
and learned from.

A working record of products, research, and experiments. Some became useful systems. Others were simply a good way to find the next question.

22 entries ยท 2024 to now

Selected field notes

03 / 22
01 2026

threedpt

An on-device movement lab that turns webcam pose capture into traceable observations about form, asymmetry, tempo, and joint load.

02 2026

Tessera

Cross-session retrospectives and live coaching for people who build with Claude Code, Codex, and Gemini CLI.

08 2025

SimGen

A multimodal sketch-to-simulation prototype that turns drawings and text into interactive physics scenes.

Complete archive

Newest first
  1. 01 2026

    threedpt

    An on-device movement lab that turns webcam pose capture into traceable observations about form, asymmetry, tempo, and joint load.

    Movement Computer vision
  2. 02 2026

    Tessera

    Cross-session retrospectives and live coaching for people who build with Claude Code, Codex, and Gemini CLI.

    Agent tools Developer tools
  3. 03 2026

    Clicky for Windows

    A Rust push-to-talk companion combining streaming transcription, screen context, Claude, and spoken replies.

    Voice Systems
  4. 04 2026

    Cosmic Garden

    A generative ecosystem of evolving plants, creatures, weather, sound, and shareable worlds, grown through a nested agent loop.

    Generative art Simulation
  5. 05 2026

    Meta-Ralph

    A nested autonomous improvement loop with builder and supervisor agents, file-based handoffs, and explicit validation.

    Agents Workflows
  6. 06 2025

    Prince of Persia Remake

    A TypeScript browser-game experiment reimagining the movement and atmosphere of Prince of Persia.

    Game Creative code
  7. 07 2025

    Concept Visualizer Agent

    An agent prototype that researches concepts, plans explanations, and generates visualizations across several rendering tools.

    Agents Visualization
  8. 08 2025

    SimGen

    A multimodal sketch-to-simulation prototype that turns drawings and text into interactive physics scenes.

    Physical AI Simulation
  9. 09 2025

    Lumina

    A Windows speech-to-text app with global hotkeys, tray controls, voice-activity detection, and local Whisper inference.

    Voice Windows
  10. 10 2025

    Distilled World Model

    A consumer-GPU world-model prototype for generating interactive 2D environments through compact latent dynamics.

    World models Research
  11. 11 2025

    Sesame CSM Replication

    A research implementation exploring conversational speech through cross-attention, hierarchical RVQ, and prosodic memory.

    Speech Research
  12. 12 2025

    Claude Code Research Agent

    An autonomous research loop that finds, verifies, and deduplicates emerging Claude Code practices into a living knowledge base.

    Agents Research
  13. 13 2025

    PEFT & LoRA Implementation

    A practical exploration of parameter-efficient fine-tuning and its memory-performance tradeoffs.

    Fine-tuning Research
  14. 14 2025

    AI Papers Research Agent

    An automated research workflow for finding, extracting, and synthesizing new papers from arXiv.

    Agents Research
  15. 15 2025

    Lesson Lab 2.0

    A multi-step lesson-planning assistant with resource search, scoring, saved plans, and traceable generation stages.

    Education Applied AI
  16. 16 2025

    Attention Mechanism Visualizer

    An interactive teaching tool that makes transformer attention visible step by step.

    Education Visualization
  17. 17 2025

    FastSentiment API

    A production-minded sentiment API built around fast inference, caching, and horizontal scale.

    ML systems API
  18. 18 2025

    Enterprise RAG System

    A production retrieval system paired with an eight-metric evaluation framework.

    Retrieval Evaluation
  19. 19 2024

    Multimodal Chain-of-Thought with DPO

    Research into preference optimization for vision-language reasoning, including a purpose-built multimodal CoT dataset.

    Research Multimodal AI
  20. 20 2024

    Image to Ingredients

    A small full-stack experiment that turns a food photograph into a useful ingredient list.

    Applied AI Interface
  21. 21 2024

    ML Systems Engineering

    An end-to-end model-serving pipeline exploring caching, health checks, and autoscaling.

    Infrastructure ML systems
  22. 22 2024

    Traffic Sign Classification

    A real-time computer-vision pipeline built with transfer learning on ResNet50.

    Computer vision ML