Now you can give your agents a search engine for your own data. Point AI Search at your files or a site you own and we handle crawling, embedding, and retrieval.
Get a /search and /mcp endpoint to share with your users, or keep it private to your team.
https://t.co/3O1oJ8rZZM
familymart self checkout system deserves more hate.
- UI has no indication of when I can scan items vs which page is order from counter
- each item take 30s to load after scanning
- payment, card not accepted but still shown as an option
@FamilyMartMY_ do better
We created the Cloudflare Codex, a governed body of engineering standards that AI agents consume across the development lifecycle. https://t.co/uagE5pWgUt
Kumo is at 3k+ stars & 135k weekly downloads
If you like beautiful compositional UI components for your React applications... you'll love Kumo :)
Team works hard building back all of our learnings from using it to build Cloudflare itself.
https://t.co/B03WejjSxO
We’ve decided to open-source a multi-agent harness we use internally at YC.
We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!).
The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
https://t.co/AUKzoQ5Ikb
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Today we're opening up the DoorDash CLI in limited beta.
`dd-cli` lets you order DoorDash directly from your agent: search stores, find the best deals, check out, and more.
Early access for US/Canadian macOS developers by waitlist. Excited to see what folks build!
We're coming out of stealth.
We've built our first racks after a successful A0 tapeout, $1B+ in customer contracts, and $800m raised.
Early customer tests show us achieving SOTA throughput, latency, and power efficiency on inference workloads.
Our first racks ship this summer.
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.
I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!
Meet Kimi Work - a local AI agent on your desktop that does the work for you.
🔹Native agent swarm: Up to 300 AI agents running in parallel on your local machine.
🔹Browser use: Paired with WebBridge extension, your agent will navigate websites in your browser: search, scroll, click, type and complete tasks.
🔹Built for Finance: Native global market data tool call from Yahoo Finance and World Bank - no complex API setup required.
🔹Memory system: Kimi Desktop keeps a running diary of your preferences, past decisions, and context to know you better.
Available for macOS (Apple Silicon) and Windows.
🔗Try it now: https://t.co/yhiai2VWIy