Stop rebuilding the same agent setup for every domain tool.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Stop rebuilding the same agent setup for every domain tool. OpenHarness is an open-source framework for running coding agents with domain-specific tools and live viewers. It helps you package a repeatable agent workflow by combining an engine, instructions, tools, a project template, and an optional viewer in a small harness folder with a `harness.json` manifest. Key features: • Multiple coding engines – runs Claude Code, Codex, OpenCode, and other engines in persistent terminal sessions • Small harness format – package a workflow as a folder plus manifest without changing the desktop app
Posted by Dan Kornas (99.1k followers) 1 h ago · 6 likes · 630 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- This is Step 5 Preview in comparison with other frontier models. — @vikktorrrre
- Your saved links are useless if you can’t find the source when it’s time to write. — @DanKornas
- first we got Jev from TypeSafe AI, a model that's insanely cheap! — @vikktorrrre
- Qwen-Image-2.1 is coming! — @ItsmeAjayKV
- きしださんのjevを採用させていただいています — @Tono_Ken3
- A coding agent that can install packages, start databases and run shell commands… — @agenticgirl
- Persistent agent sandboxes shouldn’t mean permanent cloud bills. — @DanKornas
- Done — @ajith_io
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.4k posts from 4.8k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 12:55 UTC. Full method.