ConvAI Innovations

Tony Dinh

@tdinh_me · Sep 21

Tony Dinh ran laya-mlx on a MacBook against Jev in real-time Tetris. Laya decided far faster but stacked itself to the ceiling; Jev won every round.

r33drichards

@r33drichards · Sep 19

Adds image understanding to Laya using a small SmolVLM-256M backbone, so you can ask calibrated yes/no, choice and score questions about a picture plus text.

fstandhartinger

@fstandhartinger · Sep 21

Describe a past conversation in plain language and Chat Seek finds it across local agent histories, reranks with the receptron Laya runtime, and offers a Resume action.

Simplifying AI

@simplifyinAI · Sep 21

Simplifying AI ran the identical Snake and typed decisions for 30 s on each model. Laya (421M, local) scored 46 at 86.5 decisions/s; Jev 1.13.0 over the API scored 1 at 3.2/s.

Dev Ed

@developedbyed · Sep 21

A maze demo on a base M5 Mac where local Laya answered in about 19 ms median against roughly 300 ms for the hosted Jev API. Shows the latency gap that on-device decision models open up.

0xBakeer

@0xBakeer · Sep 20

Typed-decision server on NVIDIA GPUs or Apple Silicon that speaks the Jev wire format, with coding-agent integrations. Built after a cat woke the author at five on a Sunday.

keeltrace

@keeltrace · Sep 18

Nerve gives Hermes agents typed System One decisions, ranking, verification and an opt-in tool gate, using Jev or the open Laya model to oversee spending and risk.

Tom Siwik

@tomhacks · Sep 21

Tom Siwik’s point: the model matters less than how you define the decision space and batch. Jev wins networked; Laya-mlx and his own JAX build tie locally.

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.

ChenneyZhuang

@ChenneyZhuang · Sep 21

Local decider for the browser-agent loop: hand it a numbered table of page controls and it picks the operation and element. Playwright/CDP driver, speaks /v1/systemone.

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.

ruban-24

@ruban-24 · Sep 20

An open-source router that asks Jev or a self-hosted Laya how hard each prompt is, then picks the model and reasoning effort so simple turns stay cheap.

sfmqrb

@sfmqrb · Sep 26

A single Rust binary that lets you ask questions about log lines, diffs or JSON and explore the answers live, running Laya on CPU with no server.

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.

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.

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.