$ buildwith info grok-build

Grok Build

#5 in Coding Agents · Freemium

sources differ by section

Grok Build (the grok command) is xAI's coding agent for the terminal. It runs as a full-screen, mouse-aware TUI that reads your codebase, edits files, runs shell commands, searches the web and manages long-running tasks. The same agent runs headlessly for scripts and CI, or inside other editors through the Agent Client Protocol (ACP). The Rust source for the CLI and its agent runtime is published on GitHub under Apache-2.0, synced periodically from xAI's internal monorepo.

for Developers who work in a terminal and want a vendor-run agent in the Claude Code and Codex mould, on the Grok models by default. It installs with one command on macOS, Linux and Windows, signs in through the browser, by device code over SSH, or with an API key for CI, and can be pointed at other models through its config file.

use this if you want a full-screen terminal agent with plan mode, parallel subagents in their own worktrees and a headless mode for CI, included in the X Subscription plans, with Apache-2.0 source you can read.

open x.ai ↗

Features

$ features --list

  • ›Plan mode: edits are blocked until you approve the plan, and you can comment on single steps or rewrite it
  • ›Subagents that run in parallel, each with its own context window, optionally in their own git worktrees
  • ›Skills (auto-invoked or called by name, and /skillify turns a session into a skill), hooks, MCP servers and AGENTS.md rules
  • ›Plugin marketplaces that bundle skills, agents, hooks and MCP servers, installable from a marketplace or any git repo
  • ›Clarifying questions as multiple-choice cards whose answers feed into the plan
  • ›Headless mode (grok -p) with streaming JSON output for scripts and CI pipelines
  • ›Agent Dashboard showing every session and which agents need input, plus background tasks and session memory
  • ›Sandboxed execution, and enterprise controls through system-level managed config files

Pricing

$ pricing --tiers

Free

$0/month

Grok Build is listed as Limited on the free tier. The product page says it is available to try for free; no exact cap is published.

Plus

$8/month

Grok Chat, Voice, Imagine and Build, Grok API access and Cursor, drawing on one shared AI usage pool that refreshes weekly.

Premium

$30/month

4x the usage of Plus, plus Grok Bot, the latest Grok models, cloud agents and automations, and AI code reviews.

Super / Ultra

$100/month / $200/month

15x and 50x the usage of Plus. Teams plans start at $30 per user per month. Prices exclude taxes; top-ups are available when the pool runs out.

API key

Billed per token

Set XAI_API_KEY to run Grok Build on xAI API credits instead of a plan, which the docs recommend for CI and scripts.

Why this rank

$ diff --rank 5

Ranked #5 in coding agents, new to the list this week. Grok Build is a vendor-run terminal agent included with a plan, like Claude Code, Codex, Devin and Factory, so it sits with them and above the agents you run yourself. It is the newest of the five and we have no usage measure for it yet, so it ranks last among them: Claude Code and Codex ride on plans many builders already pay for, Devin is the autonomous engineer, and Factory is the paid multi-surface agent. OpenCode ranks just below it as the leader of the open-source agents where you choose and pay for the model yourself. These ranks are editorial; the scores are unmeasured placeholders and are not shown.

Strengths

$ strengths

  • ›Source is public under Apache-2.0: the GitHub repository had 27,821 stars on 2026-11-21.
  • ›Fast release pace: the public changelog lists 75 releases, from v1.0.11 on 2026-08-26 to v1.0.89 on 2026-11-17.
  • ›Agent features that match the leading terminal agents out of the box: plan mode, parallel subagents with worktrees, skills, hooks, MCP, plugins and headless mode.
  • ›Free to try, and on paid plans the same usage pool also covers Grok chat, image and voice and Cursor.

Limitations

$ limits

  • ›The repository is a periodic sync from xAI's monorepo and does not accept external contributions, so it is open source to read and build, not a community project.
  • ›No exact usage caps are published for any tier; the pricing page gives only multiples of the Plus pool, and on Plus a long coding session draws on the same pool as chat, voice and images.
  • ›Needs an xAI account to sign in, or API credits bought separately from the subscription.
  • ›The docs list macOS and Linux as requirements and point Windows users to PowerShell, Git Bash or WSL; the README calls Windows source builds best-effort and untested.

Sources

$ sources --verified

$ buildwith alternatives grok-build

  • #1 Claude CodePaid

    use this if you live in the terminal and want an agent that works across your whole repo.

  • #2 OpenAI CodexPaid

    use this if you want to hand off tasks to a cloud agent or run one locally via CLI.

  • #3 DevinPaid

    use this if you want an autonomous engineer that picks up tickets and opens PRs.

  • #4 FactoryPaid

    use this if you want a paid coding agent, Droid, that can run in the terminal, the IDE, the desktop app, or Slack, with team plans when you need them.

  • #6 OpenCodeFree / OSS

    use this if you want an open-source coding agent in the terminal, desktop or IDE that runs on any model, including the Claude, ChatGPT or Copilot plan you already pay for.

  • #7 ClineFree / OSS

    use this if you want an open-source agent in the editor and the terminal, with plan-then-act approval, and you want to bring any model.

  • #8 gooseFree / OSS

    use this if you want an Apache-2.0 agent with a desktop app, a CLI and an API that runs on your machine, works with any model, and goes beyond code into research and automation.

  • #9 Kilo CodeFreemium

    use this if you want one open agent in VS Code, JetBrains, the terminal, and the cloud, and you want to choose the model or bring your own key.

  • #10 Qwen CodeFree / OSS

    use this if you want an Apache-2.0 coding agent that runs in the terminal, your editor, a desktop app, a browser and chat apps, and can use Qwen, OpenAI, Anthropic, Gemini or local models.

  • #11 CrushUsage-based

    use this if you want Charm's terminal UI as a coding agent and you will bring Hyper or your own model key.

  • #12 AiderFree / OSS

    use this if you want an open-source, git-native pair programmer and bring your own model.

  • #13 Trail-codeFree / OSS

    use this if you already use Claude Code, Cursor or Codex and want it to find the right code faster and remember what your team decided.

sponsor this spot →