Building MARNE V2T: private, local voice-to-text for Windows. No hotkeys needed (optional). Talk, switch apps, send. For devs & everyday users. #BuildInPublic
SW Florida
Joined May 2026
- Tweets3.1K
- Following2.4K
- Followers1.2K
- Likes1.9K
Pinned Tweet
Devs Helping Devs: Edition #8 🛠️ The Beyond-Code Toolkit
We tested 5 tools plus 2 standouts: an engineering simulator, a kids' reading app, a builder directory, an audio splitter and an image model.
Each tested at its own level, and we say which. #DevsHelpingDevs 👇
I run a ChatGPT dot and a Grok Bot side by side. What made both useful: giving each one its own lane. Not a ranking, just my setup, step by step. 🧵
9) Build a bridge so they share the load. The dot does heavy research and drafts, saved as one doc per item in a shared Drive folder. Grok Bot checks it and acts only after I say yes. Watching limits? Hand heavy work to the second model.
10) Read the work. Both can make mistakes.
No dot? Pro (18+, not EU/UK/CH) or Business Premium. Steps 6-8 stand alone. Bookmark this.
Sources:
openai.com/index/introducing…
docs.x.ai/grok-bot/skills-ro…
1,172 of you here now, and a lot of you are building something alone.
So let's flip it today: what are you stuck on right now? A bug, a launch, a tool that won't install.
Drop it below. Someone in this crowd may have already solved it 🤝
I don't hand-code. The part of this work I've gotten good at is noticing when an AI agent starts drifting off the job, then building the checks that keep it on track.
Nobody hands you a title for that.
If you work with agents, what's the first sign one is drifting for you?
Every week we test open source tools for Devs Helping Devs, and the catches teach me as much as the wins.
So I'm curious: what's a tool you quit using this year, and what made you drop it?
Standouts 🌟
ComfyUI Character Card Studio (JGRFW on GitHub, v1.2.1, MIT): all 9 layout checks passed. No image generated.
Update: Earshot by @lexnlin, 0.3.0 in Ed4, now 0.4.0. We rendered a whoosh, listened, and it's clean. Catch: one sound only; a wider test run stalled.
SAVE THIS: every link from Devs Helping Devs Edition #8 🔖
1. FieldCraft by Tangency Labs on GitHub, engineering simulation
Repo: github.com/tangency-labs/fie…
Site: tangency-labs.github.io/fiel…
Catch: early software. We tested portable v0.7.0 on Windows (CPU, no API key): a sample cantilever and 18 MCP tools, not the native GUI or other solvers. MIT OR Apache-2.0.
2. Yara Reads by Eli Finer (finereli on GitHub), early reading practice
Repo: github.com/finereli/yararead…
Hosted app: yarareads.finereli.com
Catch: we tested the hosted app only (7 books, the "six" sound tiles, page turns). The local Windows story checker failed on a malformed path. Teaching quality and pronunciation not rated. LICENSE file says MIT; package metadata says ISC.
3. WhatAreYouBuilding.AI by @netadror, hosted product directory
Site: whatareyoubuilding.ai
Agent notes: whatareyoubuilding.ai/llms.t…
Catch: not open source. We tested public read endpoints and MCP discovery (9 tools), not submission or accounts.
4. ComfyUI-DBS by @geneLab_999, audio stem separation
Repo: github.com/hiroki-abe-58/Com…
Catch: we ran the underlying models on CPU with a synthetic 4-second signal, not a real soundtrack, a listening test or a ComfyUI queue. MIT node pack; model terms differ.
5. MOSS-Image-SFT by @Open_MOSS, text-to-image
Model: huggingface.co/OpenMOSS-Team…
Demo: huggingface.co/spaces/OpenMO…
Catch: one hosted-demo image only, no local run. Apache-2.0.
Standouts
6. ComfyUI Character Card Studio (JGRFW on GitHub), v1.2.1
Repo: github.com/JGRFW/ComfyUI-Cha…
Catch: component tests only (9 layout checks, renderer smoke tests). No image was generated; it needs ComfyUI and a Qwen workflow. MIT.
7. Update: Earshot by Leon Lin (@lexnlin), audio tools for agents
Ed4 post (tested 0.3.0): teapaw.org/CleanFix_Dev/status/21…
Repo: github.com/Leonxlnx/earshot
Release: github.com/Leonxlnx/earshot/…
Catch: now tested at v0.4.0 on Windows (CPU, no API key, about 1.1 GB of audio models downloaded): one 0.8-second whoosh (peak at 0.321 s, -1.0 dBFS, no clipped samples; we listened and it's clean), 51 focused sound-bank tests passed, MCP listed 16 tools. A broader test run stalled and was interrupted, so no full-suite pass. Film-level fit and realism not validated. MIT.
That's Edition #8. Thank you, builders 🙏 Star the repos, it tells a builder someone noticed.
Have you shipped something in the last 5 days? 🚀 Reply with what it is and a link, and we'll feature it. Shipped highlights go out Mondays and Fridays 👇
🤝 #DevsHelpingDevs #buildinpublic #connect 👋
Earshot by Leon Lin (@lexnlin). A sound bank and objective audio meters for agents doing code-driven sound work.
Tested a 0.3.0 snapshot: 16 model-free checks passed. Semantic listening, classification and large models untested.
github.com/Leonxlnx/earshot
5/7
ALT earshot card: audio tools for agents, built by Leon Lin, tested Earshot 0.3.0 snapshot, github.com/Leonxlnx/earshot.