@XFreeze Grok Build is truly a development operating / development ecosystem now. Never in the history of humankind have we had so much development power in a terminal. Who needs a GUI when you have this much power? Learn command line Linux. Grok Build doesn't need a bloated desktop app.
@dihusaysomthin@BabyD1111229 THIS! I have a 1992 Goodman (outdoor A/C + furnace combo) STILL going strong. Has never had a drop of freon leak out of it. Only thing replaced since then was a compressor fan motor and the heat blower. I will go to the grave before it dies.
@arthurkatcher 1) Yes! Use `.grok/agents` or config.toml (see below), adding to the docs site right now.
2) Yes: Agents can spawn background subagents, or try /dashboard, to move your agent to the background and create another. I've been using /dashboard as my default.
Today, we're releasing @XMoney to a subset of US Premium+ users to collect feedback and iron out issues ahead of a broader launch. As appreciation for being an early user, we're extending our internal perks to this group for a limited time. Notifications going out now!
@twtayaan I just run @portainerio as a docker container on my Mac and connect to localhost:9443. Not tearing it down just because @Apple is finally getting on the bandwagon. Portainerio will give you a 3-node business license to manage a fleet of containers on 3 Macs for free.
Grok Build just got another update with many new features, improvements, and bug fixes
Release Notes: 0.2.61 – 2026-06-22
Features:
• Closing a terminal tab with a running process now shows a confirmation dialog instead of killing it immediately.
• /usage now shows prepaid credits balance and auto top-up status.
• Clipboard copy on Wayland now also tries wl-copy; per-leg outcomes are now logged for diagnostics.
• Goal mode toggles and limits can now be set in config.toml under the [features] table.
• All /goal options (toggles, limits, role models) are now configurable together in a [goal] table.
• Clipboard copies from VS Code over SSH now warn when non-ASCII text may be garbled.
Bug Fixes:
• Focus reports no longer leak as literal text when split across reads over SSH.
• --disable-web-search now honored in grok -p and grok agent; auxiliary model routing respects catalog overrides.
• Focus events now fire correctly for SSH-split focus reports.
• Boolean tool flags now accept "true"/"false"/"yes"/"no"/1/0 strings and numbers in addition to native booleans.
• Session last-active timestamps and message counts no longer regress under concurrent writers.
• iTerm2 now always uses text/metadata image fallback instead of broken OSC 1337 overlays.
• Model switches no longer leave the prompt queue stuck after a reconnect.
• Closing a terminal tab with a running process no longer shows a confirmation dialog.
• Custom agent profiles now correctly use the harness required by their pinned model.
• Subagents under custom profiles now adopt the correct harness from the parent's model.
• Changelog and release-notes modals now scroll with the mouse wheel and arrow keys.
@elonmusk I'm letting it rip. I created a goal to polish and enhance a custom UI and test every change using Playwright. It executed perfectly (3 weeks worth of work in 20min with end to end testing).
How many in this town hall have created an actual bitcoin? I mean actually spun up a linux box, loaded the almighty Phoenix python miner and pointed it at an AMD Radeon GPU using OpenCL (not CUDA) and stayed in https://t.co/UmsyTvekhW all day long (as we did in 2011)? Anyone that has done that knows the true value of a bitcoin no matter what the market says.
After playing a while with Grok Build, I noticed 2 important missing features still : reasoning level control and project-specific agent file. I created a custom AGENTS.md configuration.
This results in more consistent, thorough, and high-quality agentic coding behavior.