@_stsao

[@_stsao @_stsao]

@MengTo @MengTo did you use codex to generate item/inventory too? I saw the gravehook falchion just now

[@_stsao @_stsao]

I made a 90's inspired RPG from a chinese drama I loved watching but never got to play! I generated the character images with codex, then passed them to huanyuan 3d, bound the asset in blender.

I also reused the amazing combat animations from https://t.co/u2CLBFZF9w, all in threejs too.
https://t.co/dRF9Sr97qf

@appledelhi

[@_stsao @_stsao]

@MengTo to be clear, codex has access to huanyuan and blender mcp so i only prompted

[herdr @herdrdev]

proud to share that herdr is moving to apache 2.0. 🎉

the master branch is now apache 2.0, and the next release will ship under it.

this removes the biggest adoption blocker for many teams and makes the herdr runtime open for everyone to build on.

one terminal. whole herd.🐏

[@_stsao @_stsao]

@wesbos herdr

[@_stsao @_stsao]

cloudflare/agents is all you need

[@_stsao @_stsao]

@RhysSullivan Yeah the emdashcms demo for temporary sessions is awesome

[@_stsao @_stsao]

@ethankongee @NotionStatus That’s the smoking gun

[@_stsao @_stsao]

@ArtemR from a dota lens, liz reid wins with 21 mentions in 2 turns lol https://t.co/lEyHILC7jQ

[@_stsao @_stsao]

@trq212 cool to see document parsing converge as well. dots.mocr output svg to keep more structural information than markdown. also https://t.co/VSthdz0Lch's early blog on html as canonical representation

[Jerry Liu @jerryjliu0]

We shipped a LlamaParse MCP server to let you parse, classify, split, and generally operate over your hardest documents with your favorite AI agent 📄🤖

Check out the MCP server: https://t.co/eOeDgzOCI5

This is both a useful feature and a great piece of engineering that we want to share with the community. 💡 MCP does not have built-in file upload support, so we needed to implement a URL-based upload endpoint and couple it with parse operations
💡We built in an integration with @WorkOS OAuth.
💡We built in observability and rate-limiting

Huge shoutout to @itsclelia for shipping this! Come check out our blog writeup: https://t.co/XsCZlKnzez

LlamaParse: https://t.co/TqP6OT5U5O

[@_stsao @_stsao]

Had to try building writing lenses with dynamic worker and @RhysSullivan's plugin pattern. cc @Wattenberger

Demo https://t.co/wWYoJQm7HU

[@_stsao @_stsao]

@_chenglou Table rows with dynamic height ??

[@_stsao @_stsao]

run pdf subagents https://t.co/EXt2EvEiOd

[@_stsao @_stsao]

context drag and drop on a pdf #webdev #qwen

[@_stsao @_stsao]

Collab with Agent → Review extractions → Export to Excel/Word.
Refine results on your data quickly ⚡️ #Excel #pdf

[@_stsao @_stsao]

pdf entity labeling #byok

[@_stsao @_stsao]

@mervenoyann Looks like your queries require more reasoning than my use case. I find qwen vl to be so flexible on report parsing on its own and when stacked with OCR to lower hallucination. Found similar experiments like this https://t.co/Au55dQgIOs