0xTHAC0

[Mr. Makham @MakhamDev]

Monopteros #PixelComposer

https://t.co/QHZEHRK3rB

[Basit A. Khan @basit_designs]

More Visuals, more aesthetics ❤️

[Stella Peng ✶ @abtste11a]

made something for my name, it’s a character most people have never seen :D

[Arlan Marat @arlanmarat]

new design system for AI apps and developer tools!

copy code here:
https://t.co/0TUsuvGXzl

[Noor @noordesignn]

Tried to recreate the new ChatGPT UI

[Harsh Nisar @NisarHogaya]

In love with what @SabhyataDesign has cooked for @Bharat_Digital_'s website. It has been months in making and has so many tiny thoughtful details that reflect what we care for and stand for.

Bharat Digital, a non-profit dedicated to humanising and modernising how governments use tech in service of the people.

visit: https://t.co/UmCwvbG7Ck

[Lydia Hallie ✨ @lydiahallie]

Just to avoid some confusion: auto-compact does summarize. When it runs, your whole conversation is replaced by a short summary. It doesn't keep the last 1M tokens around.

The ~967K is only when it runs on 1M models. Compacting itself is just one request that reads about as many tokens as the message you sent right before it, and it's mostly cache reads if your cache is still warm.

What @rohit3a found is that waiting until 967K means every message before that point uses a lot of tokens, because each one includes your whole conversation so far. Most of it is read from the cache, which is much cheaper (so this is usually fine as long as your cache is warm), but it still counts toward your usage and adds up as your conversation grows.

/autocompact 400k makes it summarize at 400K instead, so your messages never get that big.

[Sumanth @Sumanth_077]

I built a data analyst agent with Jev as the review layer!

Qwen handles the main agent work, Jev acts as the review layer, and Vercel eve runs the agent loop, tool execution, and human approval flow.

The agent takes a plain-English question about the data, inspects the database schema, writes the SQL, runs the query, and explains the result.

The interesting part is what happens around that main loop.

Qwen is responsible for generating the SQL and the final answer, while Jev reviews the parts where semantic judgment is actually useful. Anything that can be checked reliably with code stays deterministic.

Jev reviews the agent at three points:

- Before the agent starts, it checks whether the user's question is clear enough to answer from the available data.
- After Qwen generates the SQL, it checks whether the query actually represents what the user asked.
- After the query runs, it checks whether the final explanation is grounded in the returned rows.

For example, we tested it with:

“Who is our best customer?”

The question sounds simple, but “best” could mean highest revenue, most purchases, highest average order value, or something else.

Instead of letting Qwen silently choose a metric, Jev flagged the question as ambiguous and asked for clarification.

The same separation applies to SQL execution.

Qwen can propose a query, but it cannot decide whether that query is safe to run. The tool accepts only a single read-only `SELECT`, SQLite runs in read-only mode, results are capped at 200 rows, and queries without a `WHERE` clause can require human approval before execution.

Those checks do not need another model call.

But a query can be completely safe and still answer the wrong question.

A deterministic rule can verify that the SQL is read-only. It cannot reliably judge whether a query for “revenue last month” accidentally calculates revenue across all time.

That is where Jev comes in.

It reviews the proposed SQL against the original question and schema before execution. After the rows come back and Qwen writes the explanation, Jev reviews that answer again to check whether the claims are actually supported by the returned data.

The project uses a local SQLite sales database, Qwen through the Vercel AI Gateway, Gradio for the interface, and only two database tools: "inspect_schema" and "run_sql".

No single model is responsible for everything. Qwen generates, Jev reviews, deterministic code controls execution, and Vercel eve manages the agent loop and approval flow.

GitHub Repo: https://t.co/OJ2TOvl1C0

100% open source.

[Framer @framer]

Watch Rachel from @fuzzco explain how mastering the fundamentals of Jev helped her perfect the animation with the Framer Agent

[Jotaroo SEO @JotaroSeo]

Je vous présente la nouvelle version de mon bébé : PushRank 🚀

On sort officiellement de la bêta.
🧡🧡🧡

→ UX/UI entièrement repensée
→ Nouvelle feature backlink, ayez une stratégie de backlink sans faire aucun effort.
→ Plein de fonctionnalités optimisées
→ Un programme partenaire à 30% à vie
Et pleins d’autres choses qui arrivent…

Gros merci à toute la team dev qui a charbonné sur cette version 🤲

Lien du site :
https://t.co/wP6W3Xjkfg

[Cognition @cognition]

Introducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work

At night Devin self-improves its memory to remove stale records and discover latent information

We are creating an OSS standard called Agent Memory Repo: https://t.co/b6qzEJsaeT

[miggi from figgi @miggi]

Using the agent for motion in @figma is super helpful, helps you see the idea, then you can just tweak the timeline.

There are additional starter prompts including this one, here: https://t.co/dXwUUqiDib

[Doot 🪲🪷 Wishlist Milki Delivery 🐮🚲 @doot_dodo]

What would you do? 🍄🤔

[無量光秀＠アートゥルデザイン @ArtwlDesign]

GPT-6.1でHD-2Dなワールド試作して歩いてみる🧙‍♂️
キャラはRPGツクールの素材を使ってます🙏

[Osmo @osmosupply]

Getting a list of cards to animate in with a stagger on scroll can be tricky, especially when the number of columns changes across breakpoints. This Queued Scroll Reveal setup uses a shared queue to keep the stagger timing consistent, no matter how the grid changes. Just add two attributes to the parent and you’re good to go.

↓ Use Osmo in your project
https://t.co/hHRGWuA0BJ

[m1negishi @m1negishi]

やきいも (Roasted sweet potato)
#ドット絵 #pixelart

[m1negishi @m1negishi]

#ドット絵 #pxelart

[Maitree Mervana Parekh @maitreemervana]

built a virtual closet & outfit generator from raw closet videos. classification + semantic search thanks to jev 🥰. clueless closet dreams finally coming to life

[Ivan Boroja @ivanboroja]

Health metrics

[Albia @AlbiaHossain]

An animation can elevate any design 🔥