rsafaya

Thank you. Let me know if you have any feedback.

Really nice. It should save a bunch of time in research.

Maybe it's time scrapers actually paid publishers via something like HTTP 402 for their data instead of an arms race with Cloudflare on one side and residential proxies on the other.

Really good project for a quick data back end.

One feature suggestion: webhook support for row changes:

If my Sheet updates (say, a new waitlist signup), I'd want to trigger for e.g. a Slack notification. Supabase has something similar with their database webhooks. I use that extensively for kicking off signup workflows.

Many years ago I saw the "pale blue dot" photograph by voyager 1 from the 90s. I use it as a reminder to myself to make the most of our time here.

Can confirm good canvas renderer performance. Just tested it with a real-time smart meter dashboard — 62 meters streaming over MQTT via JustinX.ai (our data ingestion platform), 60 msg/s (peak), 500ms refresh. Almost no flicker, smooth updates across all meter cards. Much nicer way to handle high-frequency streaming data than xterm.js.

Check out the video screen grab: https://streamable.com/hcga8t

I think the A2A space is wide open. Great to see this approach using App Server and Channels. I tried built something similar (at a high level) for a more B2C use case for OpenClaw https://github.com/agentlink-dev/agentlink users. Currently I think the major Agents have not fully owned the "wake the Agent" use case fully. Regardless this is a very cool approach. All the best.

I think this would be super useful as a claude code / visual studio extension, so I can see the cost impact of changes I am making in code. For example by adding a prompt pre-processing function how much am I actually going to save in LLM token cost.

Great initiative igor. Really like the clean mermaid diagram support.

Super cool. How do you see people using this vs. something more generic like miro?

Makes a lot of sense. Any plans to support openrouter? We use that extensively instead of connecting directly to the model providers.

Setting up WhatsApp is a pain and this really helps. I really like your docs page explains the "how do I do this" really clearly. All the best.

Very nice idea. I have sent a little note to me and my founder in the future. It has a nice "time capsule" like feel to send a message out. Really makes you think about what you want to say.

Well done. All the best.

What are your thoughts on OC security?

There is a real risk but probably not directly from someone targeting you. Your agent reading a webpage or email that happens to contain injected instructions is a risk. It is really a surface area problem. I would suggest you ask claude/whatever to scan your OC dirs regularly.

Ok Ill be honest. I have not tried it yet. But I just loved the fire animation!

I wish I had found this earlier. Nothing like looking at thousands of EV charger logs all day to mak you appreciate something like this.

Cool project — the "agent is a folder" philosophy is genuinely appealing. I spend most of my day in Claude Code, which is basically a primitive version with: flat memory files, file tools for self-management, context that gets trimmed.

The one thing I'd push on: the bet that the agent will reliably manage its own memory with read/write tools hasn't played out for me in practice. Claude has file tools and a memory directory today, and it still forgets things I've told it dozens of times — the bottleneck isn't storage, it's that the LLM doesn't reliably decide what to save or when to retrieve. That said, preserving full JSONL history on disk and only trimming at inference time is a genuinely better model than lossy compression — I wish Claude Code did that instead of auto-compact.

Have you thought about layering lightweight semantic retrieval over the knowledge/folder so the agent doesn't have to manually grep its own brain?

Great work. As someone who spends many hours a day in Claude Code and dreads the dreaded auto compact moment, the memory problem is genuinely a big point of frustration.

Right now I use a skill on every commit (or when the auto compact warning starts showing up) that forces Claude to update its "memory" . It is a flat markdown file that gets stuffed into conversations, not v smart. Claude forgets things I've told it dozens of times.

Your MCP server approach makes total sense. The create_atom tool alongside semantic_search makes it read/write from day one. I would love to wire a stop hook to automatically atomize session insights (the write side). That's the dream: I work on something in my code, Claude learns why, and that knowledge flows into Atomic without me saying "remember this."

I have not doodled in a while. That was fun :)