Grok Build ships v1.0.30/31 updates focused on multi-agent session readability and MCP fixes
elonmusk · x · 2026-09-14
Grok Build received two quick releases, v1.0.30 and v1.0.31, centered on making busy multi-agent sessions easier to read and navigate:
- Subagent groups now show how many agents are still running versus finished, with corrected labels for folded groups
- Dashboard search and the resume picker behave more predictably, with clearer active-field indicators
- Cancellation banners show the actual cause; long-running sessions get hour-based timers (e.g. 3h14m)
- Dock Watchers and Loops rows show when the next run is due; workflow status is clickable from the dock
- MCP fix: tools with long server prefixes are no longer silently dropped
- tmux panes feel smoother after a per-frame rendering lag fix; long paths cleaned up across headers and dashboards
Related event: Grok Build ships rapid updates to improve multi-agent sessions(2 posts)→
More from coding & agent
- Gemini 4 tops public coding benchmarks but drops to bottom on private tasks — Hesamation · 2026-10-30
- User builds 20-bot Grok suite to track wins, prep 1:1s and close promises — NicoVerderosa · 2026-10-30
- Why 30-year-old BM25 beats vector embeddings for agentic search, per search vet Jo Kristian Bergum — jobergum · 2026-10-30
- LangChain CEO opens Interrupt London with keynote on why orgs should own their intelligence — LangChain · 2026-10-30
- Simlock: open-source control plane gives parallel coding agents their own iOS/Android simulators — Scobleizer · 2026-10-30
- Keyfleet launches open canvas where personal AI agents team up with a shared USDC treasury — seanwbren · 2026-10-30