It Started with a Simple Need
I had conversations I didn't want to lose. Messages with insights, discussions that shaped thinking, exchanges worth preserving. And I wanted to fine-tune a model on them — privately, without sending my thoughts to some cloud server.
The Origin Story
I wrote a simple Python script to capture conversations. Then another script to fine-tune a model using MLX on my MacBook. Nothing fancy — just a way to keep what mattered.
But as I shared it with friends, something became clear: everyone had conversations they wanted to preserve. Writers with drafts and editorial discussions. Consultants with years of case studies. Developers with debugging sessions full of hard-won insights.
Everyone had "gold" — their unique perspective, knowledge, and voice — trapped in conversations and documents, with no easy way to transfer it into an AI that actually understood them.
EdukaAI was born from that realization. The name comes from "education" — because this was fundamentally a learning experience. Every script written, every model trained, every problem solved — hands-on, practical, real. And EdukaAI carries that spirit: learning by doing, demystifying AI, making fine-tuning accessible through practical knowledge.
"Lower the barrier for entering fine-tuning and private models. Because your data — your unique essence — shouldn't be shared with anyone."
That's why everything we build is local-first. Your thoughts stay on your machine. Your model stays yours. No telemetry, no cloud dependency, no vendor lock-in.
Why It Matters
Your conversations, your writing, your knowledge — it's not just data. It's your unique intelligence. And it deserves to stay that way.
Your Conversations
Insights from chats, discussions, and exchanges that shaped your thinking
Your Voice
Writing style, tone, and perspective that makes your work distinctly yours
Your Knowledge
Years of expertise captured in documents, reports, and accumulated wisdom
The EdukaAI Toolkit
From zero to fine-tuned model — even if you have no data yet. Start with meaningful samples, learn the craft, then bring your own.
EdukaAI Studio
The fine-tuning tool. Train custom LLMs on your Mac using a simple five-step wizard. Built on Apple MLX.
AI Curator
The data OS. Capture from any source, curate your samples, export ready for training. Local and private.
Starter Pack
400 meaningful samples to fine-tune with — no data needed. Perfect for learning and experimenting.
More blog posts coming soon — sharing hands-on learnings from building EdukaAI
Open Source, Always
EdukaAI Studio and AI Curator are open source under MIT license. Free to use, free to modify, free to share. Because the best tools should be available to everyone.