Focusing on the reason stated “pair programming” ask your employer if you can use live share for VSCode or teletype for atom instead. Pair programming works great in certain situations but screen sharing is the absolute worst way to get this done. Source: about 4 years ago

Teletype: this is one of the highlight features of Atom as it allows you to share your entire workspace and edit code together in real-time. Source: over 4 years ago

Some code editors have plugins to allow the developers to create collaboration sessions. Visual Studio has Live Share and Atom has Teletype. But the invitees need to install the editor to be able to join the session. Until today. - Source: dev.to / almost 5 years ago

Teletype for Atom might be what you're looking for. Also, haven't used yet, but a quick Google search shows me something like this also exists. Source: about 5 years ago

Hi there! I'd like to implement something similar to Teletype's way of connection. It briefly works this way: first the clients (peers) connect to an external server, then they somehow manage to establish a peer-to-peer connection to stop using the server and talk to each other. No need to open router ports in any of the peers. Source: over 5 years ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 20 days ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 23 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 24 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / about 1 month ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / about 1 month ago