







Fast and streamable Excalidraw MCP App
the tiny corp on Twitter / X
Qwen 3.5 27B getting 18.5 tok/s on Mac Mini with external 7900XTX. It should be able to be 3x faster than this with work, SSM stuff is still in PR. Hopefully Mac eGPU support brings in devs. pic.twitter.com/2aMkUpXY1S— the tiny corp (@__tinygrad__) April 1, 2026

MCP Apps - Bringing UI Capabilities To MCP Clients
MCP Apps is now live as the first official MCP extension — tools can return interactive UI components that render directly in the conversation.

Combining NVIDIA DGX Spark + Apple Mac Studio for 4x Faster LLM Inference with EXO 1.0
Disaggregating Prefill and Decode: Faster First Tokens, Faster Streams

Combining NVIDIA DGX Spark + Apple Mac Studio for 4x Faster LLM Inference with EXO 1.0
Disaggregating Prefill and Decode: Faster First Tokens, Faster Streams

Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.

mitchellh/libxev
libxev is a cross-platform, high-performance event loop that provides abstractions for non-blocking IO, timers, events, and more and works on Linux (io_uring or epoll), macOS (kqueue), and Wasm + WASI. Available as both a Zig and C API.
Optimising ATproto applications is complicated (but that's okay) - Navyfragen App Blog
Bluesky, as a decentralised platform, poses a unique challenge for engineers trying to optimise for latency. Where is the AppView hosted? What about the locatio...

OpenTools on Twitter / X
.@AnthropicAI will support stateless remote MCP servers with “just HTTP” as transport.We’re quite excited about this! So we gave a “lightning talk” at an MCP meetup hosted by @paulgb @CloudflareDev yesterday. pic.twitter.com/ooZHus81cg— OpenTools (@opentools_) March 19, 2025
MCP Apps: Extending servers with interactive user interfaces
Introducing the MCP Apps Extension proposal (SEP-1865) to standardize interactive user interfaces in MCP, developed with the MCP-UI creators and maintainers from OpenAI and Anthropic.

EXO Labs reveals that they have been working with Apple for the past year on low-latency RDMA networking over TB5 which allows a cluster of 4 x M5 Ultra Mac Studios to scale to an aggregate memory bandwidth of 4.8TB/s
OpenMemory - AI Memory MCP Server for Coding Agents | Mem0
With OpenMemory, add persistent, project-aware memory to Cursor, Windsurf, and VS Code agents. Store preferences, patterns, and context that get retrieved automatically.

mattt/iMCP
A macOS app that provides an MCP server to your Messages, Contacts, Reminders and more
mattt/iMCP
A macOS app that provides an MCP server to your Messages, Contacts, Reminders and more
Build an MCP server - Model Context Protocol
Get started building your own server to use in Claude for Desktop and other clients.
