Walter Korman retweeted
Introducing virtual models on AI Gateway.
Use a single virtual model ID across agents to:
• Centrally manage model strings and configs
• Immediately update to new models
• Enforce Zero Data Retention
Read the blog post → vercel.com/blog/ai-gateway-v…
Walter Korman retweeted
fx is now much faster, smaller and efficient
Try fx.sh on your iPhone Duo
fx v0.0.15
Less memory. Faster resumes. Smaller binary.
- 70% less memory in long sessions
- 7.66% smaller binary (6.15mib ← 6.66mib)
- Image-heavy turn processing up to 3.3× faster
- Session resumes about 18% faster
- Automatic model catalog refresh
- Fork conversations with /fork
- Better image handling & crash recovery in libfx
- Multiple bug fixes & security improvements
fx.sh/changelog#v0.0.15
Walter Korman retweeted
fx v0.0.15
Less memory. Faster resumes. Smaller binary.
- 70% less memory in long sessions
- 7.66% smaller binary (6.15mib ← 6.66mib)
- Image-heavy turn processing up to 3.3× faster
- Session resumes about 18% faster
- Automatic model catalog refresh
- Fork conversations with /fork
- Better image handling & crash recovery in libfx
- Multiple bug fixes & security improvements
fx.sh/changelog#v0.0.15
Walter Korman retweeted
I’ve revived my Apple II Agent project from January: An Apple IIe with an Ethernet card and a custom client
It links to Claude through a Mac proxy and allows conversational Apple II software creation similar to Claude Code
When it’s done, it loads the new program into memory
Walter Korman retweeted
Speaking of security, we created a registry for building OIDC configuration components.
Pick your providers, form and validation libraries, and token verifier (powered by jose). Then run one command to copy everything into your app.
I've built these a few times before. I know how annoying they can be to get right. Hope this helps.
ui.shadcn.com/oidc
It's time to retire long-lived static credentials.
We surveyed 1,000+ SaaS vendors and found only 8.4% support secure auth. This is our call to action and how we're doing our part.
vercel.com/blog/death-to-lon…
Walter Korman retweeted
test
Kimi K3.1 Pro is live on AI Gateway in regular and highspeed versions, with 1M context and gains in coding, 3D modeling, and finance.
• 𝚖𝚘𝚘𝚗𝚜𝚑𝚘𝚝𝚊𝚒/𝚔𝚒𝚖𝚒-𝚔𝟹.𝟷-𝚙𝚛𝚘
• 𝚖𝚘𝚘𝚗𝚜𝚑𝚘𝚝𝚊𝚒/𝚔𝚒𝚖𝚒-𝚔𝟹.𝟷-𝚙𝚛𝚘-𝚑𝚒𝚐𝚑𝚜𝚙𝚎𝚎𝚍
vercel.com/changelog/kimi-k3…
Walter Korman retweeted
200+ releases since our June launch. here’s what’s new in the eve agent framework.
ShipSF workshop with @andrew_barba:
youtube.com/watch?v=GHkBVNja…
Walter Korman retweeted
we did invent it and it's called OIDC federation
vercel and github actions do it:
- each deploy gets a short-lived signed token
- AWS/npm/other services verify it via trust policy
- you get temporary creds
no keys to paste
the problem is not enough APIs and services accept it
Walter Korman retweeted
DeepSeek V4.1 Flash 1017 is now included in Vercel Token Pass.
• New weights from DeepSeek
• 1M context window
• No config change
Get $80 of tokens for $30/mo ↓vercel.com/changelog/deepsee…
Walter Korman retweeted
Vercel AI Gateway
- Zero fees for BYOK
- Zero markup on list prices
- Zero payment fee with ACH
- Volume discounts available
[email protected]
Walter Korman retweeted
My favorite part about working on this was getting the chance to highlight AI Gateway’s best in class session affinity infrastructure.
It handles things like tracking cache state for multiple models within a session, automatic fingerprinting, and much more.
Cache hit rates can make or break inference economics, and AI Gateway helps you maximize them right out of the box. Any model, any provider.
Walter Korman retweeted
The October 2026 AI Gateway Index is live.
1. Open weight ran over 70% of tokens, and took nearly 25% of spend, up 4x since June.
vercel.com/blog/ai-gateway-p…
Walter Korman retweeted
A reusable hard drive for your cloud computer. 💻
Share and fork files across multiple sandboxes to reuse installed dependencies, enable collaboration and persist agent workspaces.
Vercel Drives is generally available. You can now run stateful agents on Vercel.
vercel.com/blog/introducing-…
Walter Korman retweeted
Introducing Token Pass. Get $80 in GLM 5.3 and Kimi K3 tokens for $30/mo.
• Two open models, one API key
• US and EU providers
• ZDR on by default
Early access is open to the first 500 Pro teams.
vercel.com/changelog/introdu…
Walter Korman retweeted
Drama 3 from @FishAudio is live on AI Gateway. 80% off for 30 days.
Direct speech with natural-language instructions, control emotion and pacing, and add pauses or whispers for voiceovers.
𝚏𝚒𝚜𝚑-𝚊𝚞𝚍𝚒𝚘/𝚍𝚛𝚊𝚖𝚊-𝟹
vercel.com/changelog/drama-3…
Walter Korman retweeted
MAI-Image-2.6 and MAI-Image-2.6-Flash from @MicrosoftAI are live on AI Gateway.
Both handle text rendering, photorealism, and targeted edits.
𝚊𝚒 𝚒𝚖𝚊𝚐𝚎 \
-𝚖 𝚖𝚒𝚌𝚛𝚘𝚜𝚘𝚏𝚝/𝚖𝚊𝚒-𝚒𝚖𝚊𝚐𝚎-𝟸.𝟼 \
"𝚅𝚎𝚛𝚌𝚎𝚕 𝚂𝚑𝚒𝚙 𝚂𝙵 𝟸𝟶𝟸𝟼"
vercel.com/changelog/mai-ima…
Walter Korman retweeted
Coding CLIs keep getting more complicated. Daemons, 3 layers of TUIs, client-server architectures.
The whole point of a CLI is to deliver intelligence with zero friction, and be unix-like.
💾 Try fx.sh. It's 6mb, starts in milliseconds, model-agnostic. It's tastefully minimal: MCP, Skills, Subagents and ACP built-in.
Walter Korman retweeted
This is the most ambitious puzzle games ever built.
It took 10 years to make.
It's size is staggering and every puzzle is a gem that has been polished by some of the best designers alive.
It's the Manhattan Project of block pushing games.
store.steampowered.com/app/4…
