Agents & Developer Experience Ecosystems Lead EMEA at Google. O'Reilly author. Local AI, fine-tuning. Building tool-eval-bench & awesome-local-ai. Views my own.
Berlin, Germany • he/him
Joined January 2010
- Tweets26.5K
- Following1.6K
- Followers7.1K
- Likes11.3K
Pinned Tweet
I couldn't keep track of all the local AI tools flying around anymore. New engines, harnesses, tooling, benchmarks... every week.
So I started awesome-local-ai: a list sorted by what you want to do, not by hype.
The twist: it's built for agents too. Point your coding agent at it and ask it to recommend a setup for your hardware.
It's early and DGX Spark-heavy. Help me fill the gaps:
github.com/SeraphimSerapis/a…
The new place is starting to come together nicely. I might have gone a little far with the network, though 😆
The other detail I like is that most agents spend most of their time waiting, for the model or for you. So an idle agent gets checkpointed down to near-zero compute and wakes on the next tool call with its files and memory intact.
For coding agents and RL, you snapshot an environment once and fork it into thousands of copies that share memory.
It already runs Gemini, Antigravity and Google's own eval and RL pipelines. Preview on Google Cloud is targeted for the coming months.
Deep dive: cloud.google.com/blog/topics…
Google's agent sandboxes assume the attacker already controls everything inside. So there is nothing inside worth stealing.
Agent Compute Engine gives every agent its own hardware-isolated microVM. No API keys, no OAuth tokens, no network card in the box. A gateway outside the sandbox adds credentials to each request, only after it checks identity and policy.
Landed support for @googlegemma in @NVIDIAAI’s new inference engine Flare - today is a great day!
github.com/NVIDIA/flare-loca…
One terminal command, one image. No SDK script, no base64, no docs tab open.
gemini-api image "Create an isometric image for a post on X of a server rack with 8 Nvidia DGX Spark systems (GB10) neatly clustered together" --out .
It nailed the vibe, not the Sparks. Those are much smaller boxes.
The new Gemini API CLI is one zero-dependency binary for text, images, video, TTS, music and Deep Research. Open source under Apache-2.0.
🤖 Made with AI
The part I like most is how it works with coding agents. Media commands write to disk and print only the file path, so no base64 ends up in the context window. Every command describes itself offline with --help, --schema and --dry-run.
Announcement: aistudio.google.com/learn/in…
Repo: github.com/google-gemini/gem…
Install on macOS or Linux:
curl -fsSL raw.githubusercontent.com/go… | bash
Loved hearing about Sovereign AI at GTC Berlin. Throughout the sessions, the keynote, and conversations at the @GoogleCloudTech booth it was crystal clear that this topic is top of mind for people across the industry
Another cool setup I’ve seen at @NVIDIAAI GTC Berlin. This one by ABA Technology was very much about deploying a cohesive unit powered by the DGX Spark FEs
Met the one and only @christopherowen and GTC Berlin. Great chat about agents, models, inference, benchmarks, evals, and more. We could’ve probably spent the whole afternoon given how much there is to talk about in this ecosystem.
Thanks for stopping by, Christopher!
If I say “DGX Station“ three times @digitalix might appear at GTC Berlin 😁
Found my kind of place at @NVIDIAAI GTC Berlin. Including the (for now) proof-of-concept switch. I counted 2 pairs of 5 ports - so you’d be able to pair up to 10 DGX Spark systems with breakout cables.
So cool. Blazing fast @vllm_project and @sgl_project deployments coming your way!
Native PyTorch on TPUs is here—and TorchTPU is officially open source.
Train and serve models using the tools you already know: @vllm_project, @sgl_project, @_llm_d_, TorchTitan, @huggingface, and @raydistributed.
Learn more from #PyTorchConf2026 → goo.gle/4hWxEVH
I'm the Chief of LLM cycling aerodynamics and my work is paying dividends 🥸🤡😅
xitter.cf/SeraAndroid/status/211… – at Großbeeren, Deutschland
Had a blast at @NVIDIAAI GTC today in Berlin. I spent a good chunk of the day at the @GoogleCloudTech Hub just across the street of Station F to meet builders from across the region and will be at the conference for most of tomorrow, too!
Running LiteLLM? Check which version you run asap.
A major vulnerability has been disclosed in PHP. Protect your applications and read more about the identified vulnerabilities here: wiz.io/blog/php2shell-php-rc…
Cloudflare has deployed default web application firewall (WAF) protections for newly disclosed PHP vulnerabilities before public disclosure. The rules use request and response signals to stop exploit attempts and prevent exposed data from reaching attackers. cfl.re/488w8dc
