Grok Build Updates Workflow and Stability
mark_k · x · 2026-07-13
Grok Build released versions 0.2.98 and 0.2.99, focusing on improving agent workflows and reliability.
Key updates include:
- The Agent panel supports multi-line input, with paging keys for scrolling within the session
- Vim-style navigation added to keyboard shortcuts
- /context now displays the token costs for skills and MCP servers
- Sub-agents can specify optional models in the CLI
- Double-pressing Enter will immediately send queued prompts
- Authentication can be pinned to an API key or OIDC
- Plan mode more strictly restricts modifications outside the plan file
- Stability enhancements for search, session restoration, SQLite on NFS, and queued prompt editing
Related event: Grok Build Improves Agent Dashboard in v0.2.98/0.2.99(3 posts)→
More from coding & agent
- Building a Secure AI Agent Gateway: Self-Hosting OAuth for Multiple SaaS Apps — Defiant_Cod_2654 · 2026-07-22
- Rowboat launches as an open-source, local-first AI coworker with memory — ycombinator · 2026-07-22
- Scoble says AI “loops” really means long-running multi-agent workspaces — Scobleizer · 2026-07-22
- Kimi Code opens a waitlist as Moonshot rolls out its coding product — Fabulous_Bonus_8981 · 2026-07-22
- Open-source runtime lets each repo define its own AI code reviewer — ibabufrik · 2026-07-22
- Indie Dev Asks: What's Actually Broken in Your AI Agent's Memory Today? — AcceptableTime7937 · 2026-07-22