# Grok Build Terminal coding agent from SpaceXAI / xAI: it reads the codebase, edits files, runs commands and works interactively, headless or through ACP. Canonical profile: https://ki-agentenkompass.de/en/agents/grok-build/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Grok Build is not Grok Bot. Grok Build runs on your computer in the terminal. Grok Bot, listed separately in the catalog, works according to its docs with named Bots on a persistent cloud computer in Cursor's cloud and through desktop and mobile apps. The Grok Bot page does not mention Grok Build. According to the Grok FAQ, Grok Build replaces the no longer supported Grok Studio. - Provider: SpaceXAI / xAI - Product family: Grok Build - Profile type: Terminal coding agent with open source code - Environment: Fullscreen terminal interface on macOS, Linux and Windows; headless mode for scripts and CI; ACP for editors - Connections: ACP, MCP servers, skills, plugins with marketplaces, hooks, custom models through configuration, OpenTelemetry export to your own collector - Setup: Install the prebuilt binary with the install script, the npm package `@xai-official/grok` or WinGet. The first start opens the browser for sign-in; without a browser you set `XAI_API_KEY`. The source build needs Rust, DotSlash and protoc. - Pricing model: The code is under Apache-2.0. According to the FAQ, use draws from the weekly pool of the Grok products or runs through an API key. The readable pricing page does not confirm what each plan includes. ## Key features ### Fullscreen terminal According to the README, the interface understands the codebase, edits files, runs commands, searches the web and manages long-running tasks. Source: https://github.com/xai-org/grok-build/blob/main/README.md ### Headless and ACP `grok -p` runs without an interface in scripts and CI, optionally with JSON output. Through the Agent Client Protocol the agent can be embedded in other applications. Source: https://docs.x.ai/build/overview ### Plan mode and goals According to the docs, in plan mode only the plan file can be edited until you approve. `/goal` works toward an objective across rounds until reviewers consider it complete. Source: https://docs.x.ai/build/modes-and-commands ### Subagents Subagents are on by default and run as separate sessions with their own context. They report a summary back to the parent session. Source: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/16-subagents.md ### Recurring tasks `/loop` and the scheduler start prompts at intervals as background subagents. Recurring tasks expire after seven days, and at most 50 can be active at once. Source: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/20-background-tasks.md ### Permissions and sandbox Modes and rules control what runs without asking. The optional sandbox uses Landlock on Linux and Seatbelt on macOS. Source: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/22-permissions-and-safety.md ### Enterprise controls Managed configuration, enforced rules through `requirements.toml`, OIDC sign-in, team pinning and Zero Data Retention at team level. Source: https://docs.x.ai/build/enterprise ## Example workflows ### Implement a change with a plan - Your input: A project folder and a change description in plan mode. - Possible result: Grok Build writes a plan and implements it after your approval. - What to check: Read the plan and check the diff. `/rewind` only resets the conversation, not the files. ### Run a task in CI - Your input: `grok -p` with `XAI_API_KEY` and rules through `--allow` and `--deny`. - Possible result: The agent runs the task and writes the result to standard output. - What to check: Use `dontAsk` mode or deny rules and evaluate the exit code. ## Requirements and limits ### Account or API key Requirement: On first start you sign in through the browser; in CI you use `XAI_API_KEY`. You add custom models in `~/.grok/config.toml`. Source: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/02-authentication.md ### Requirements for the source build Requirement: Rust, DotSlash and protoc. macOS and Linux are supported build hosts; Windows builds are best effort and currently not tested from this tree. Source: https://github.com/xai-org/grok-build/blob/main/README.md ### Open code without open contributions Limitation: The code is under Apache-2.0 but is only synced periodically from an internal monorepo. External pull requests are excluded. The latest sync in the repository dates from 29 September 2026; the npm package was at 1.0.70 when fetched. Source: https://github.com/xai-org/grok-build/blob/main/CONTRIBUTING.md ### Experimental parts Limitation: Memory counts as experimental and is off by default, and OpenTelemetry monitoring has alpha status. The readable pages name no beta notice for the product as a whole. Source: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md ### Retention without Zero Data Retention Not yet confirmed: The enterprise page gives no periods for organizations without Zero Data Retention. The 30 days in the API FAQ apply there to API requests; the page does not say whether they also apply to subscription sign-in. Source: https://docs.x.ai/build/enterprise ## A good fit if … - you want a terminal agent with plan mode, subagents and CI use - you already use Grok models or a Grok subscription - your company wants to enforce rules centrally through configuration ## Less suitable if … - you want an agent that keeps running in the cloud without your computer; for that the provider describes Grok Bot - you want to contribute to the code yourself - you need to confirm location and retention commitments for Europe from public pages without reviewing a contract Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice Grok models from xAI are the default. According to the docs, Grok Build supports any custom model: you add the base URL and key in config.toml, and the guide shows Anthropic, OpenAI, Bedrock, Ollama, Together AI and local servers. In a company, a central policy can pin the list. - Model families named: xAI (Grok), Anthropic (Claude), OpenAI (GPT) · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes - Depends on: Admin approval Documented · Sources accessed on: 2026-11-05 - [Grok Build: Overview](https://docs.x.ai/build/overview) - [Grok Build: Custom models](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/11-custom-models.md) - [Grok Build: Authentication](https://raw.githubusercontent.com/xai-org/grok-build/main/crates/codegen/xai-grok-pager/docs/user-guide/02-authentication.md) ## Europe & regional availability The privacy policy and the Europe addendum on x.ai answered with HTTP 403 when fetched, so no statement from them is used here. The enterprise page, the API security FAQ and the Grok FAQ on docs.x.ai were read. Reviewed scope: Terminal agent with model calls through provider services Reviewed on: 2026-11-05 ### Availability and data location Availability still unclear The enterprise page names neither a data location nor regions. The Grok FAQ contains no regional privacy rules. The binding legal texts were not readable. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: Source blocked when fetched; please check directly with the provider. Official source: https://docs.x.ai/build/enterprise Official source: https://docs.x.ai/grok/faq ### Zero Data Retention Availability still unclear With Zero Data Retention at team level, according to the page, the inference layer stores no prompts, code or responses. The local history stays in `~/.grok/`. This is not a regional commitment. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: Only for teams with the feature enabled. Official source: https://docs.x.ai/build/enterprise ### API: no regional guarantee Availability still unclear According to the API FAQ, the default endpoint guarantees no processing region. Requests are stored encrypted for 30 days by default. The only regional endpoint named is in the United States; the page names no European one. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: The page concerns the API. It does not say whether the same applies to Grok Build's subscription sign-in. Official source: https://docs.x.ai/developers/faq/security ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Local agent with provider sign-in or API key Sources reviewed: 2026-11-05 ### Account used Documented: The default is browser sign-in through `auth.x.ai`, plus device code, API key and OIDC with your own identity provider. Companies can pin sign-ins to a team and block first-party API keys. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/02-authentication.md Evidence: https://docs.x.ai/build/enterprise ### Admin approval Documented: Modes range from asking through `acceptEdits` and `auto` to always-approve. Allow, ask and deny rules apply on top. Admins can lock off always-approve through a root-owned `requirements.toml`. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/22-permissions-and-safety.md Evidence: https://docs.x.ai/build/enterprise ### Data access & team sharing Documented with conditions: The agent works with your user's permissions on files, the shell and the web. The sandbox is off by default and only limits the file system and network once you turn it on. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/18-sandbox.md Evidence: https://github.com/xai-org/grok-build/blob/main/README.md ## Prices and included usage Pricing checked: 2026-11-05 The X Subscription pricing page lists plans and prices but does not mention Grok Build. According to the FAQ, Grok Build draws from the weekly pool of the Grok products. x.ai/pricing was blocked when fetched. ### The X Subscription: Free $0, limited usage The page does not say whether Grok Build is included. Price source: https://docs.x.ai/x-subscription/pricing ### The X Subscription: Plus $8 per month or $80 per year Base usage. Price source: https://docs.x.ai/x-subscription/pricing ### The X Subscription: Premium $30 per month or $300 per year 4x usage. Price source: https://docs.x.ai/x-subscription/pricing ### The X Subscription: Super $100 per month or $1000 per year 15x usage. Price source: https://docs.x.ai/x-subscription/pricing ### The X Subscription: Ultra $200 per month or $2000 per year 50x usage. Price source: https://docs.x.ai/x-subscription/pricing ### grok-4.7 (API) $2 input and $6 output per 1M tokens below 200,000 prompt tokens; $4 and $12 above Public API price for access through an API key. Price source: https://docs.x.ai/developers/pricing According to the API pricing page, Grok 4.7 Fast is only available in Cursor and Grok Build and is billed through the plan there. Third-party pricing was not used as evidence. Pricing details: https://docs.x.ai/x-subscription/pricing ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Local process; model calls through provider services or custom models Sources reviewed: 2026-11-05 ### Files and working state Documented: Grok saves each session automatically under `~/.grok/sessions/`, grouped by working directory. This includes history, tool calls, the plan and rewind points. `/delete` removes a session permanently. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/17-sessions.md ### Sign-ins Documented: Tokens live in `~/.grok/auth.json` with owner-only permissions. The docs advise full-disk encryption. In CI `XAI_API_KEY` applies, and an active session takes precedence. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/02-authentication.md ### Starting further runs Documented with conditions: `/loop` and `scheduler_create` start prompts at intervals. Tasks can persist across sessions, and recurring ones expire after seven days. For CI triggers you use headless mode in your own system. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/20-background-tasks.md Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/14-headless-mode.md ### Human intervention Documented: In default mode Grok asks before write actions and non-read-only commands. Plan mode waits for your approval. In `auto` mode a safety check decides, and dangerous calls may still prompt. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/22-permissions-and-safety.md Evidence: https://docs.x.ai/build/modes-and-commands ### Detecting errors Documented: Headless reports failures with an error object and a non-zero exit code. Companies can send events and decisions to their own collector through OpenTelemetry; this part has alpha status. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/14-headless-mode.md Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/24-monitoring-usage.md ### Resuming after failures Documented with conditions: `grok --resume` picks sessions back up, and `/fork` branches them. `/rewind` only resets the conversation; files stay unchanged. The reviewed page does not describe automatic retries after failures. Evidence: https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/17-sessions.md ### Editorial assessment Grok Build describes sessions, rules and enterprise controls at length in its guide. You have to turn on the sandbox and memory yourself. The state of the public repository can lag behind the shipped program, because it is only synced periodically. ## Memory and conversation continuity Scope: Experimental cross-session memory, off by default Sources accessed: 2026-11-05 Markdown files for global and per-repository scope; can be turned on, edited locally and searched. ### Storage and scope Documented: Experimental and off by default. Global and workspace notes live as Markdown locally under `~/.grok/`. Clones and worktrees of the same repository share one scope. - [Grok Build: Cross-Session Memory](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md) ### Selection and timing Documented: You tell Grok what to remember or use `/remember` with a review panel. At session end Grok saves a metadata summary, and `/flush` writes a model-generated one. New facts are captured as observations after each turn. - [Grok Build: Cross-Session Memory](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md) ### Inspect, edit and delete Documented: `/memory` shows all files and can delete notes. You can edit the files directly. According to the docs, forgetting by request is best effort only; deleting in the file is the reliable way. - [Grok Build: Cross-Session Memory](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md) ### Agent and channel boundaries Partly documented: The boundaries run between global and workspace. The page does not describe boundaries between individual agents or channels. - [Grok Build: Cross-Session Memory](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md) ### Retrieval Documented: Grok reads topics at session start. A bounded index of both scopes enters the context once per session, and memory tools search further when needed. - [Grok Build: Cross-Session Memory](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md) ### Session reset and compaction Documented: `/new` starts fresh. `/compact` and auto-compact shorten the history; `/flush` can save what matters beforehand. `/dream` consolidates observations into topics. - [Grok Build: Cross-Session Memory](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md) - [Grok Build: Session Management](https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/17-sessions.md) ## Context Sign-in with SpaceXAI or an API key, network access to provider services. The sandbox and memory are off by default. The repository accepts no external contributions and shows no releases. Several x.ai pages were blocked when fetched. Read the repository with its user guide through the GitHub API, docs.x.ai and the npm registry. x.ai/cli, x.ai/build, x.ai/open-source, x.ai/pricing, the privacy policy and the Europe addendum answered with HTTP 403 and are not used as evidence. Feature claims come from the provider; example tasks are editorial. Our own hands-on tests are pending. ## Open points Europe, availability still unclear: - Availability and data location - Zero Data Retention - API: no regional guarantee Requirements and limits, not yet confirmed: - Retention without Zero Data Retention ## Sources - https://github.com/xai-org/grok-build - https://github.com/xai-org/grok-build/releases - https://github.com/xai-org/grok-build/commits/main - https://registry.npmjs.org/@xai-official/grok - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/01-getting-started.md - https://docs.x.ai/x-subscription/overview - https://github.com/xai-org/grok-build/blob/main/README.md - https://docs.x.ai/developers/faq/security - [Grok Bot | SpaceXSI Docs](https://docs.x.ai/grok-bot/overview) - https://docs.x.ai/build/overview - https://docs.x.ai/build/modes-and-commands - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/16-subagents.md - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/20-background-tasks.md - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/22-permissions-and-safety.md - https://docs.x.ai/build/enterprise - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/02-authentication.md - https://github.com/xai-org/grok-build/blob/main/CONTRIBUTING.md - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/13-memory.md - https://docs.x.ai/x-subscription/pricing - https://docs.x.ai/developers/pricing - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/18-sandbox.md - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/17-sessions.md - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/14-headless-mode.md - https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-pager/docs/user-guide/24-monitoring-usage.md - https://docs.x.ai/grok/faq ## Provider The repository under xai-org names SpaceXAI as the developer, and parts of the docs on docs.x.ai write SpaceXSI. The company also offers Grok, Grok Bot and the Grok API. - Operator: SpaceXAI / xAI - Organization: Provider - Website: https://x.ai - Reviewed: 2026-11-05 - Provider source: https://github.com/xai-org/grok-build/blob/main/README.md - Provider source: https://docs.x.ai/developers/faq/security - Provider source: https://docs.x.ai/grok-bot/overview [Sources and method](https://ki-agentenkompass.de/en/sources/)