Why we built Dropstone — the AI IDE that remembers
by•
Every AI coding tool today suffers from the same flaw — amnesia.
It forgets what you’ve done, what you’re building, and how you think.
We built Dropstone to change that. Powered by our new D2 Engine, it learns, remembers, and evolves with your code. It doesn’t just autocomplete; it understands.
We’re about to launch soon, and I’d love to hear your thoughts:
What frustrates you most about current AI coding tools?
How do you imagine an AI that truly remembers could change your workflow?
Let’s start a discussion — the future of AI development might just begin here.
190 views
Replies
@adamvisu Dropstone is built as a growing intelligence rather than a static assistant. A CLAUDE.md file remains fixed, but Dropstone evolves with every interaction by remembering decisions, architecture choices, errors, patterns, and your personal workflow. Its multi-layer memory allows it to retain reasoning steps, track past attempts, avoid repeated mistakes, continue research over time, and refine its approach without modifying model weights. Static instructions guide an AI once, while Dropstone strengthens its understanding with each session. This long-term continuity contributed to its 37.8 percent result on the AGCI benchmark, available at https://www.dropstone.io/research/agci-benchmark. We’re also preparing a detailed video that walks through the entire system, so stick around and you’ll see exactly how it works and why it’s useful.