Olivier Chafik

Work @ Anthropic on MCP (views expressed = my own), ex-Google, past contrib. to OpenSCAD & llama.cpp; he/him 🏳️‍🌈 @ochafik.bsky.social @[email protected]

[Claude @claudeai]

Claude can now build interactive charts and diagrams, directly in the chat.

Available today in beta on all plans, including free.

Try it out: https://t.co/tHPAZRgQkn

[Olivier Chafik @ochafik]

Having lots of fun with local audio models…

[Prince Canuma @Prince_Canuma]

Voxtral 2 realtime coming to MLX-Audio thanks @KarnikShreyas and @ochafik

New release this coming week once we land the PR.

I believe we can get to 100-200ms range. Perfect for iOS!

https://t.co/JwNb65rjvo

[Olivier Chafik @ochafik]

@bendersej @AnthropicAI @bcherny Hey, can you make sure to put the CDP settings in the resource’s _meta? We have a few examples (https://t.co/SmPey3UhEB), if you use the registerAppTool / registerAppResource helpers in TS it should all type-check. And please feel free to file a bug if it still won't work 🙏

[Olivier Chafik @ochafik]

@bendersej @AnthropicAI @bcherny Sorry no plans for it atm! (being conservative here for security + future model introspectability reasons)

Best option is currently to turn your iframe embed itself into an MCP app. Here's a rough idea how to support both modes: https://t.co/uxaUL5qk4I

[Olivier Chafik @ochafik]

@bendersej @AnthropicAI @bcherny Hey @bendersej, yes sorry but https://t.co/e6gGUWw5Al doesn't support frameDomains.

Your app can check what CSP settings the host decided to support w/ getHostCapabilities().sandbox?.csp?.frameDomains

[Sean Strong @sean_t_strong]

You can now run apps within https://t.co/5Fv7lxjbbQ, powered by MCP Apps.

Analyze data, edit tickets, draft messages, generate diagrams and more with Claude's interactive connectors. Grateful to our team, the open source community, and our partners for this launch 🚀

[Tobin South @TobinSouth]

watch this space — Claude is about to be the only tool you open to do work

[Olivier Chafik @ochafik]

Say (https://t.co/UQ2qIZkM7W) uses the amazing Pocket-TTS to let Claude speak out loud to you, live!

[Olivier Chafik @ochafik]

Had so much fun co-authoring the MCP Apps spec and helping launch it in https://t.co/e6gGUWw5Al! 🎉

🧵 About some demo apps you may wanna check out as user or developer

[Claude @claudeai]

Your work tools are now interactive in Claude.

Draft Slack messages, visualize ideas as Figma diagrams, or build and see Asana timelines.

[Olivier Chafik @ochafik]

Pdf (https://t.co/3S0OjUg0c8 ; also available in https://t.co/e6gGUWw5Al Connectors) will show any arxiv PDF and allow you to ask Claude about any page / selection you need details about

[Olivier Chafik @ochafik]

@ericcurtin17 @ollama @ggml_org @parthsareen I think there's room for a variety of approaches to OSS.

I (and my past employer) have been happy to contribute code under a permissive license ((almost) no strings attached✌️)

And I'm thankful that Ollama's codebase is open-source 🤗 (even if I'm not a fan of Go 🤪)

[Olivier Chafik @ochafik]

@ericcurtin17 @ollama @ggml_org Ideally Ollama would use the Jinja support and constrained tool calls from llama.cpp, removing the need for their bespoke templating engine and improving their output quality. Probably would just need to wrap the relevant APIs as C?

[Olivier Chafik @ochafik]

@ericcurtin17 @ollama @ggml_org The major differences AFAICT are Ollama's tool calls are not grammar-constrained (many models can have high failure unless temperature is kept low, see https://t.co/iX6guPkRpI), and they don't support streaming in their OpenAI-compatible endpoint (and no streaming of arguments)

[Olivier Chafik @ochafik]

@ngxson Preview above wasn't for the PR that introduces --reasoning-budget, here it is again:

https://t.co/ntSKofbhZg

[Olivier Chafik @ochafik]

Wanna disable thinking in llama.cpp? Try the new `--reasoning-budget 0` flag

https://t.co/ntSKofbhZg

Should work w/ Qwen3, QwQ, DeepSeek R1 distills, Command R7B; please report any issues!

(Upcoming per-request behaviour discussed on https://t.co/Hfm7GFuSrd @ngxson)
#llamacpp

[Olivier Chafik @ochafik]

Really slick integration! MCP all the (cool) things!

[Vaibhav (VB) Srivastav @reach_vb]

You really can just do things! Use *any* Hugging Face space as a MCP server along with your Local Models! 🔥

Here in we use Qwen 3 30B A3B with @ggml_org llama.cpp and @huggingface tiny agents to create images via FLUX powered by ZeroGPU ⚡

It's quite a bit crazy to see local models be capable of so much and just be able to understand/ infer from tool description!

There's a lot of potential here in automating video generation workflows, content curation and a lot more..

Bonus: you can plug any other Inference Provider if you don't want to run locally too!

npx @ huggingface/tiny-agents run [TASK]

oh, and we provide both typescript and python client! 🐐

[Xuan-Son Nguyen @ngxson]

Months of @ochafik's work finally paid off, we have MCP w/ llama.cpp 😁😁

[Olivier Chafik @ochafik]

@profcelsofontes Support for disabling thinking is now available w/ `--reasoning-budget 0` across thinking models:

https://t.co/Npo493RoEv

(the pending generic mechanism will be useful for other things)

And my pleasure!

[Olivier Chafik @ochafik]

Wanna disable thinking in llama.cpp? Try the new `--reasoning-budget 0` flag

https://t.co/ntSKofbhZg

Should work w/ Qwen3, QwQ, DeepSeek R1 distills, Command R7B; please report any issues!

(Upcoming per-request behaviour discussed on https://t.co/Hfm7GFuSrd @ngxson)
#llamacpp

[Olivier Chafik @ochafik]

llama.cpp streaming support for tool calling & thoughts was just merged: please test & report any issues 😅

https://t.co/QsuMjPs2qp

#llamacpp

[Olivier Chafik @ochafik]

@profcelsofontes Yeah it may sound overkill, but then it allows issuing parallel calls as early as they're returned, and some more advanced scenarios (e.g. streaming diff arguments for file patching tools, think Cline / Roo - initially wanted to integrate to this: https://t.co/P5F27qtcbs)