Running several coding agents shouldn’t mean hunting across terminal tabs.
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.
Running several coding agents shouldn’t mean hunting across terminal tabs. agentglass is a local control surface for developers running AI coding agents in tmux sessions and repositories already open on their machine. It helps you see what each agent is doing, costing, and waiting on by attaching to existing sessions instead of launching or replacing the agents. Key features: • Existing-agent support – tracks Claude Code, Codex, Gemini CLI, and OpenCode sessions already running in tmux • Live session context – shows tool calls, model, branch, cost, turns, errors, and files touched for each
Posted by Dan Kornas (99.1k followers) 1 h ago · 1 likes · 480 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 😂笑死，智普创始人唐杰亲自上小红书点举报，这波公关直接深入一线了！ — @NFT_Chen
- Coding agents are changing how software gets built. — @freeCodeCamp
- Did you know you can now put the text of almost all of arXiv on one cheap SSD. — @TeksEdge
- Generates citation-backed reports with source credibility scoring and automated… — @tom_doerr
- Join Happy Horse and create your own paper-cutting world. — @alibaba_cloud
- Removes AI tells from prose by teaching Claude or any LLM to detect and eliminate… — @tom_doerr
- Building LLM agents in Elixir shouldn’t mean adding a Python sidecar. — @DanKornas
- EVERYONE SAYS THEY USE AI. THIS WEBSITE SHOWS YOU HOW THEY ACTUALLY USE IT. — @heynavtoor
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. 17.6k posts from 4.9k X accounts over the last 21 days, 2k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 04:24 UTC. Full method.