Before ChatGPT, There Was Ditto

But only if you could coax it to run on Omar’s laptop.

Back then, even I (Peyton, proud lifelong nerd) would sweat through command-line rituals just to show a friend how Ditto could remember their last conversation or turn off the living-room lights with a single prompt.

That was five years, dozens of prototypes, and one patent application ago.

Our North Star

Our North Star has always been the same: lower the barriers between people and powerful technology.

We started in music, learned to tame neural nets before they had a catchy name, and finally realized our true path—building a personal AI that actually remembers you.

For the full origin story—meeting minutes, GitHub commits, and the vision we had before anyone was talking about AI agents—read Before ChatGPT: We Were Building AI That Does Things on the OmniAura blog.

The Journey Before the Boom

While others were focused on general AI, we were deep in the trenches of what would later become the foundation of modern AI systems:

• 2020: Omar built LLMs from scratch with tiny training sets—generating Donald Trump tweets, Rick & Morty scripts, and Yelp reviews when tokens were still characters, not words
• Pre-ChatGPT: We knew about multimodal LLMs before they existed, understanding how to concat and add modalities together through neural layers
• The Patent: Our Multimodal Neural Network (MMNN) patent application outlined AI systems that could translate between senses—like a universal language translator for human experience

What We Learned in the Deep Learning Years

Omar was studying transformers, GAN image generators, BERT embeddings, and RESNET architectures when ChatGPT didn’t exist yet. We understood the potential, but we didn’t know how much data it would take to make it truly work.

The real breakthrough came when we realized that memory wasn’t just about storing conversations—it was about building relationships.

Fast-Forward to Today

A lot has changed since those command-line days. Ditto is now a full product you can use right now:

• ✅ Self-organizing knowledge graph — every conversation automatically builds a living network of ideas, people, and topics. No manual tagging or linking required
• ✅ Multi-provider AI models — choose from OpenAI, Anthropic, Google, and Meta. Switch models mid-conversation without losing context
• ✅ MCP integration — Ditto is both an MCP server and client. Connect your memories to Claude, Cline, or any MCP-compatible tool. Register external servers like Zapier, GitHub, and Notion
• ✅ Persistent memory system — short-term and long-term memory with pre-computed summaries, a memory dashboard, and transparent context cards showing exactly which memories were retrieved
• ✅ Web search & image generation — real-time Google search and AI image creation built in
• ✅ Multimodal chat — text, images, voice recording, PDFs, and audio files
• ✅ Bookmarks & goals — save conversations into named collections, set goals your AI proactively supports
• ✅ Works everywhere — progressive web app with offline support, cross-device sync, and mobile-first design
• ✅ Free to try — instant Google sign-in, no credit card required

And we’re still obsessed with removing friction. Passion isn’t meant to be rushed, but it is meant to be shared—so here we are, shipping Ditto to everyone.

The Ditto Difference

What makes Ditto special isn’t just that it remembers—it’s how it remembers. We’ve built:

• A Self-Organizing Knowledge Graph: Connections form automatically as you chat. Interactive network visualization shows how your ideas link together over time—patterns in your thinking you never knew existed
• Agentic Memory Search: Our proprietary approach to finding relevant memories when you need them, with learned retrieval weights that improve over time
• Personality Adaptation: Ditto develops a deep understanding of your communication style, preferences, and personality through natural conversations
• MCP: Your Memory, Everywhere: A bidirectional bridge between your memory and every AI tool you use. Zero LLM cost for MCP users—bring your own API keys and Ditto only stores your memories

What’s Coming Next

We’re not slowing down. Here’s what’s on the roadmap:

• Thought Trains — a visual 2D canvas to curate exactly what context your AI uses. Drag subjects, memories, and notes onto a canvas, activate it, and every response is grounded in your curated context
• Conversation Sessions — named, switchable threads for work, personal, and creative contexts
• Weekly Reflections — auto-generated summaries of your topics and goal progress
• Real-Time Voice — talk to Ditto like a phone call with full memory continuity

We Need You

Now we need you.

What do you wish an AI companion could do better? Which rough edges snag you? What makes you smile when Ditto gets it right?

Your feedback goes straight to our small, stubborn team—no bots, no auto-responders. We read every word and use your feedback to shape the next build.

Ready to Experience the Future?

Try Ditto for free and see what it’s like to have an AI that truly understands you.

Thanks for giving Ditto a spin. We can’t wait to hear what you think.

With gratitude, Peyton & the Ditto Team

P.S. If you run into anything weird—or wonderful—let us know. That’s how we keep lowering those barriers.

Want to share your feedback? Reach out to us at peyton@heyditto.ai or join our community discussions.