
Building Coding Agent (announcing soon) 📡 Previously "Mobile + AI" at @Atlassian @DisneyPlusHS @Compass @GoDaddy @Fueled 🗣️ 📝 🥗🥘 👫 @ragdroid
Delhi 🇮🇳
Joined August 2011
- Tweets3.9K
- Following1.3K
- Followers2K
- Likes8.7K
For your weekend reading: Build with Pi Durable on Cloudflare, a walkthrough of how to create a multiplayer chat agent, including subagents, on Durable Objects.
earendil.com/posts/pi-durabl…
Ritesh Gupta retweeted
Introducing Ryce.
Ryce is your everyday cooking companion for discovering recipes, planning meals, and making cooking simpler.
Download now: apps.apple.com/us/app/ryce-c…
Ritesh Gupta retweeted
Ghostty (and libghostty) now fully implement the Kitty clipboard protocol to allow apps to read/write non-textual data (like images!). Ghostty is the first to implement the full protocol outside Kitty. The biggest program to support this is probably Claude Code. Demo below.
This will be part of Ghostty 1.4, available in nightly now. Available in libghostty now.
That's a small reminder! 👇
As of June 2026, HTTP has a new method - a GET with a `body` 😎
Meet QUERY (RFC 10008).
It lets you send complex queries in the body (like POST) while staying safe, idempotent, and cacheable (like GET). Already works on servers (Node.js, Go, Laravel…).
Browsers are still adding full support, usable now with care, with widespread adoption coming later in 2026+.
Ritesh Gupta retweeted
It took Apple 15 years to add the Markdown UTI to the iOS SDK. Fascinating nit given how Markdown shaped the world of documents
daringfireball.net/linked/20…
Ritesh Gupta retweeted
cross-platform SwiftUI swiftcrossui.dev is probably BETTER way to ship great app than Electron slop. quite amazed how the project evolved 🥰
Ritesh Gupta retweeted
Testing some UI. Not Ghostty btw (but, libghostty). Not ready to talk more yet, but sharing things I'm excited about. Plenty more details soon.
Ritesh Gupta retweeted
just added this to my global user level AGENTS.md, after fable automatically spun up 52 fable subagents to do simple PR scans and exhausted my quota before i could even react
Ritesh Gupta retweeted
made a tiny terminal app to download videos from x, youtube, instagram, etc
copy a post's url, paste it, yoink it
npm i -g yoinks
github.com/pablostanley/yoin…
Ritesh Gupta retweeted
Introducing Kimi K3: Open Frontier Intelligence
🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal
🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts
🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost
🔹 Built for long-horizon agentic coding and self-evolving workflows
Kimi K3 is now live on on Kimi.com, Kimi Work, Kimi Code, and the Kimi API.
Open Weights by July 27, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.com/blog/kimi-k3
Ritesh Gupta retweeted
Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without having use CLIs or open the browser?
We built exactly that.
Using @TauriAp ps, with a Rust backend powered by LiteParse and a React frontend, we created a cross-platform desktop app that lets you:
• Drag and drop PDFs
• Convert them into clean Markdown
• Preview page screenshots with extracted bounding boxes overlaid for easy inspection
It's a simple way to understand your document's structure and verify the parsing results before handing them off to an LLM.
Check out the demo below! 👇
GitHub: github.com/run-llama/litepar…
Get started with LiteParse: developers.llamaindex.ai/lit…
Ritesh Gupta retweeted
Have you ever wanted to make your own font? Well I've written something that will hopefully dissuade you from that idea.
makingsoftware.com/chapters/…
It's free to read for the next 48hrs. Enjoy.
Ritesh Gupta retweeted
Replying to @jessethanley @nateberkopec
We’ve been automatically approving changes to tests and fully merging dependabot updates for years. Now we have agents approving safe PRs: intercom.com/blog/ai-is-appr…
Once you reframe it around safety, you can get a pretty high number of PRs fully approved.
Ritesh Gupta retweeted
Apple's shiny new (and open source!) Foundation Models Utilities package is full of gems. This seems like a great way to prove API before baking it into the OS – I love the compacting code! github.com/apple/foundation-…
Ritesh Gupta retweeted
I removed 423 GB from GLM‑5.2 without changing the model.
1,403 GB → 980 GB.
753B weights.
Bit for bit exact.
No quantization or retraining.
The weights remain compressed in VRAM instead of rebuilding the full model first.
Full writeup and repo in the next post.


























