Skip to content
View Joona-t's full-sized avatar
🧠
Learning
🧠
Learning

Block or report Joona-t

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
Joona-t/README.md

Joona Tyrninoksa

building things to understand them. most of it breaks. that's the whole point.


the tools here are mostly for me. experiments in thinking out loud with code. some worked, some got replaced by a model update, some just taught me something and quietly retired. all of it was worth making.

LoveSpark is a passion project

Sparky is next. an iOS companion for the neurodivergent mind. not a productivity app. something more like a patient friend. I envision it being an AI companion that grows alongside you.


right now i'm learning the more technical side of things. math. physics. how models actually work. less vibe, more depth. still building while i figure it out.

the gap between what i can imagine and what i can build is the only metric that matters to me.

curiosity is the whole game.

Good Vibes Only 😎🤙⚡

Pinned Loading

  1. lovespark-a11y-toolkit lovespark-a11y-toolkit Public

    Accessibility auditing toolkit — WCAG contrast checker, Claude Code slash commands, and a recursive improvement system for extension development

    Python 1

  2. primordial primordial Public

    Forked from Zarathustra-Forge/primordial

    A philosophical around typed absence, provenance, and compaction in agent systems. Milestone 1 is now complete: https://github.com/Joona-t/primordial

    Python 2

  3. blitz-swarm blitz-swarm Public

    (experimental) Parallel multi-agent swarm architecture for collective AI intelligence. All agents live. All agents share memory. All agents iterate until consensus.

    Python 1

  4. research-swarm research-swarm Public

    8-agent AI research swarm with web search, semantic dedup, and priority-aware context compression. Ablation-tested: 8 agents match 14-agent quality with higher actionability.

    Python 1

  5. ai-in-the-loop ai-in-the-loop Public

    Automated AI/dev intelligence brief — an experiment in replacing social media with a curated agent loop.