Tom Dörr

Subscribe: x.com/tom_doerr/crea… Show top posts: x.com/search?q=(from… Show top posts recent: x.com/search?q=(from…

Generates OpenAPI specs from network requests github.com/AndrewWalsh/op…

@JaidCodes Oh wow

@tom_doerr pre-OpenClaw Steipete

Automatically hot reloads any project github.com/steipete/polte…

You all know that UNIX based systems have a really solid built in system of users, groups and permissions, right? You don't have to reinvent all of this stuff from scratch for AI agents

GPU over IP bridge for remote machines github.com/kevmo314/scuda

Pure C vector search extension that runs anywhere github.com/asg017/sqlite-…

@apaz_cli Nvfp4 model inference works much better on a 5090. Even if it would work properly on the Sparks, the 5090 has the nvfp4 compute of 3 to 4 sparks

@tom_doerr Hmm. A DGX Spark should already be pretty good for that though, no? Unless you need all three of them for hosting things?

Since every strong open model is a big chungus MoE now (Qwen 3.5/Nemotron 120Bs), it's getting harder to come up with a use for small GPUs. You kinda need unified memory, like DGX Spark or Strix Halo. And still less efficient to run at bigger batch sizes due to being MoEs.

@LlmSalaryman github.com/tom-doerr/cc_a…

@LlmSalaryman I created a hook script which reviews each command. It approves, asks me or denies execution and tells Claude what to do instead. You can set the command review instructions right in your Claude settings config

Claude is unusable without —dangerously-skip-permissions at this point

Orchestrates AI coding agents github.com/jayminwest/ove…

Python library for LLM-native data pipelines from 5000 sources github.com/dlt-hub/dlt

Monitors coding agents without lock-in github.com/illegalstudio/…

Multi-agent coding workspace unifying local AI agents github.com/xintaofei/codeg

SWE dashboard for Git and tmux github.com/rupert648/pert…

GPU accelerated robotics simulation API github.com/mujocolab/mjlab

Sideloads apps and manages pairing files for iOS devices github.com/nab138/iloader

Graph RAG with vector search and AI agents github.com/apecloud/ApeRAG

@OlivierDDR @TheRealAdamG @SemiAnalysis_ Same. Can't trust Codex if I can't connect a hook that reviews the commands using my rules. If I can't let it work on the important projects it's not that useful to me github.com/tom-doerr/cc_a…

@TheRealAdamG @SemiAnalysis_ I use CLI but yeah that’s the biggest blocker just give me AgentStop hook bro

Olympian Gold Medalist Alysa Liu, recently went viral for her Teen Vogue rant on OpenAI Codex. “I can see why Sam Altman open sourced Codex. Clearly the experience is significantly worse than Claude Code. I was unable to feel the AGI using Codex. As oppose to using Claude Code, I felt the enlightenment coming and support UBI ”

GPU physics engine for robotics simulation github.com/newton-physics…