Skip to content
View Daedu86's full-sized avatar

Block or report Daedu86

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Daedu86/README.md

Hi, I'm Daniel πŸ‘‹

Welcome to my personal tech playground.

I use this space to experiment with LLMs, build systems around them, and explore new technologies and tech stacks.

Most projects start with curiosity. Some remain small experiments, others evolve into larger systems, and some are existing projects I explore to understand how they work.

This GitHub is a record of that process.

πŸ§ͺ My Experiments β€” A Timeline

Each project started with a question.

2025 β€” Exploring Interfaces, Vision & AI Context

March 2025 Β· DOM Button Identifier

How can software understand what's on a webpage?

My early experiments with browser interfaces, DOM inspection, and programmatic element identification.

Explore project

May 2025 Β· Screen Object Detection

What if software could understand what's happening on my screen?

Exploring computer vision with YOLOv8, real-time screen capture, and interactive overlays.

Explore project

October 2025 Β· Nodes AI Canvas

What happens when working with an LLM becomes more than a linear chat?

Started exploring visual AI workflows, branching, persistent context, and how to organize work around LLMs.

Over time, the experiment expanded into agent orchestration, evaluation, infrastructure, and more complex AI system architectures.

Explore project

October 2025 Β· Hey Nano

How can I give an LLM the right context from what I'm looking at?

Experimenting with ways to give LLMs more precise browser context through DOM selection, voice interaction, and contextual interfaces.

Explore project

2026 β€” Building Applications & Expanding Experiments

April 2026 Β· Dicta

Can an LLM turn language practice into something that adapts to the learner?

Exploring adaptive language learning, browser speech technologies, and full-stack application development.

Built with React, TypeScript, Supabase, and Vercel.

GitHub repository created in May 2026.

Explore project

πŸ”¬ What I'm Exploring

  • LLMs and agent systems
  • Context engineering and orchestration
  • AI reasoning and evaluation
  • Computer vision and browser interaction
  • New frameworks, infrastructure, and tech stacks

πŸ”„ My Approach

Get curious β†’ Experiment β†’ Build β†’ Test β†’ Break β†’ Learn β†’ Repeat

Not everything here is meant to become a finished product.

Some repositories are original projects, while others are forks or external projects I use for experimentation. Having a repository here doesn't necessarily imply original authorship.


Just a place to explore technology, build things, and see where curiosity leads.

Pinned Loading

  1. Nodes-AI-Canvas Nodes-AI-Canvas Public

    AI decision workspace for branching, comparison, and synthesis (released 2025-10)

    TypeScript

  2. Dicta Dicta Public

    Real-time adaptive dictation trainer for Browser TTS in 5 languages, with Supabase auth/sync and OpenRouter-powered training generation (released 2026-04).

    TypeScript

  3. kgnt kgnt Public

    Forked from kagent-dev/kagent

    Go

  4. labs-OO-Agents labs-OO-Agents Public

    Forked from NVIDIA-NeMo/labs-OO-Agents

    NVIDIA Object Oriented Agents

    Python

  5. assistant-ui/assistant-ui assistant-ui/assistant-ui Public

    Typescript/React Library for AI Chat πŸ’¬πŸš€

    TypeScript 13.4k 1.4k

  6. OpenShell OpenShell Public

    Forked from ai-openshell/openshell

    OpenShell is the safe, private runtime for autonomous AI agents.

    Rust