xAI Ships Grok Build 1.0, Taking Its Terminal Coding Agent Out of Beta
xAI released Grok Build V1.0 on August 7, moving its terminal-based coding agent from beta to a stable release cadence and positioning it squarely against Claude Code and OpenAI's Codex.
xAI shipped Grok Build V1.0 on August 7, the first stable release of its terminal-based coding agent, with Elon Musk announcing the milestone in a short post on X telling users to "try it out" alongside an installation link. Grok Build had been in beta since early June; the version-1.0 tag marks xAI moving the tool from rapid iteration into a stable release cadence, and puts it in direct competition with Anthropic's Claude Code and OpenAI's Codex, both of which have been generally available for over a year.
What Grok Build does
Grok Build is a terminal-native coding agent: install it, point it at a project directory, and it reads the codebase, edits files, runs shell commands and iterates on tasks under developer supervision. It's usable three ways — an interactive, mouse-driven full-screen terminal UI; headlessly for scripts, bots and CI pipelines; or embedded inside other apps and editors through xAI's Agent Client Protocol (ACP), an open protocol for letting autonomous agents pass task requests and context to one another. xAI positions ACP as the agent-to-agent counterpart to the Model Context Protocol (MCP), which connects models to external tools. A distinguishing architectural choice is that Grok Build's parallel sub-agents each run in their own isolated Git worktree, and the project's source is published on GitHub rather than kept closed.
The tool runs on xAI's Grok models and ships prebuilt binaries for macOS, Linux and Windows. The V1.0 changelog focuses on stability and polish rather than new capabilities: fixes to prompts, session flow, formatting, and error handling; better theme detection and markdown-table rendering; streaming JSON output for headless use that includes tool calls, results and token usage; and a new /undo slash command to roll back files and chat state to an earlier turn.
Why it matters
Terminal coding agents have become one of the most competitive corners of the agentic-AI market over the past year, with Anthropic, OpenAI, Google and now Meta all shipping their own. A stable 1.0 release signals xAI intends Grok Build to be a durable part of that lineup rather than a side experiment, giving Tesla, SpaceX and third-party developers already inside the Grok ecosystem a production-ready option. Musk said hours after the launch that xAI is already working to make the CLI accessible to non-technical users, suggesting the current release is aimed squarely at developers comfortable working in a terminal, with a broader audience to follow.
Sources
AI-assisted reporting, overseen by the AgentsAI team. Spotted an error? Let us know.
Related agents
More agents news
Cognition Launches SWE-2, a Cheaper Coding Model Built Into Devin
Cognition released SWE-2, a coding model post-trained from Moonshot AI's open-weight Kimi K3, that it says nearly matches Claude Fable 5.1 on the FrontierCode 1.1 benchmark at roughly 64% lower cost, and shipped it immediately inside Devin.
Salesforce Launches Seven 'Job-Ready' Agentforce Agents and a Long-Horizon Runtime
Salesforce unveiled seven named Agentforce agents built for specific roles across sales, service, HR and supply chain, plus a new runtime that lets an agent pursue a goal over days or weeks instead of a single session.
OpenAI Opens Its Codex Agent Harness to Developers With New Agents API
OpenAI launched the Agents API in public beta, giving developers direct access to the same orchestration harness that powers Codex — session management, context compaction, subagents and sandboxed execution — behind a single API.
Cognition Closes $2B Series E for Devin at $48 Billion Valuation
The maker of autonomous coding agent Devin closed a Series E round of more than $2 billion at a $48 billion valuation, nearly doubling its worth four months after its last raise as run-rate revenue approached $900 million.