Automation

Madison Rickert

@madisonrickert · Oct 3

Puts TypeSafe's Jev in front of the built-in auto-mode classifier, answering yes/no risk questions in one request to allow or deny tool calls about twice as fast.

ScriptedAlchemy

@ScriptedAlchemy · Aug 19

CLI for creating, updating and messaging bots and groups, inspecting conversation threads and scripting cleanup tasks, so you can automate a bot team from the terminal.

afshinm

@afshinm · Sep 21

Runs the typed-decisions checkpoint on Metal Performance Shaders: ~32 ms median and ~2.1 GiB RAM on M5 Pro, plus a slower ~0.74 GiB low-memory mode. Demo and benchmark included.

shagghiesuperstar

@shagghiesuperstar · Sep 15

Two ways to wire a Hermes agent into the Grok Bot app as a connector, via SSH relay or a native API.

darkdarkcocoa

@darkdarkcocoa · Sep 22

Python tool that checks which model actually answers your Codex requests, catching silent substitutions such as Astra being served by a cheaper model.

yzfly

@yzfly · Sep 20

Convert → quantize → deploy path that turns Laya (and Kev, NanoJev, PlayJev) into an INT8 ONNX service on the official wire protocol. Runtime is onnxruntime, tokenizers, numpy.

aovestdipaperino

@aovestdipaperino · Sep 20

No Python, no torch, no ONNX export. Loads the ungated safetensors directly and runs any of the three checkpoints on CPU, Metal or CUDA.

vishalmysore

@vishalmysore · Sep 22

Shows Laya's decisions running in WebAssembly to route steps of a workflow, so branching logic works without a hosted model.

ChristianAlexander

@ChristianAlexander · Sep 20

Elixir library that downloads the official checkpoint on first load and answers typed choice and noul questions; pick EMLX on Apple Silicon or EXLA for CPU/NVIDIA.