SpaceXAI 开源 Grok Build：Rust 智能体框架、TUI 与工具层

Aioga Editorial Team

AI资讯 / 产品更新

返回 AI资讯

SpaceXAI 开源 Grok Build：Rust 智能体框架、TUI 与工具层

MarkTechPost（RSS）Aioga 编辑团队2026-07-16T06:35:54.000Z热度 60

SpaceXAI 于 2026 年 7 月 15 日开源 Grok Build，其 Apache 2.0 许可的 Rust 代码库涵盖智能体循环、工具调度、TUI 及扩展系统。...

产品更新MarkTechPost（RSS）

今日 AI 情报摘要

SpaceXAI 于 2026 年 7 月 15 日开源 Grok Build，其 Apache 2.0 许可的 Rust 代码库涵盖智能体循环、工具调度、TUI 及扩展系统。

Grok 4.5 仍保持闭源，且不接受外部贡献。

中文正文 · AI 翻译

SpaceXAI 已开源 Grok Build：https://github.com/xai-org/grok-build，这是其 grok CLI 背后的基于终端的 AI 编码代理。源代码今天已发布到 GitHub。该版本涵盖了代理框架、TUI、CLI shell 和开发者工具，并采用 Apache 2.0 许可协议。

框架是模型周围的支撑结构。它负责组装上下文、调用模型、解析回复并调度工具调用。

Grok Build 于 2026 年 5 月 25 日作为早期测试版发布。它是一个能够理解你的代码库、编辑文件、执行 shell 命令以及搜索网络的代理。它还可以管理长时间运行的任务。它以全屏、支持鼠标互动的 TUI 运行。

存在三种界面。包括交互式 TUI、用于脚本和 CI 的无头模式。编辑器通过代理客户端协议（ACP）嵌入它。

在此基础上，SpaceXAI 列出了四个已发布的领域。代理循环涵盖上下文组装、响应解析和工具调用调度。工具涵盖了代理如何读取、编辑和搜索代码。终端 UI 涵盖渲染、输入处理、计划审查和内联差异查看器。扩展系统涵盖技能、插件、钩子、MCP 服务器和子代理。

将该表格作为阅读顺序。从 xai-grok-shell 开始了解循环，然后是 xai-grok-tools。一个容易忽略的构建注意事项是，根目录下的 Cargo.toml 是自动生成的，README 中建议将其视为只读。

除了检查功能之外，SpaceXAI 提出了一种实用结果。Grok Build 现在可以完全本地优先运行。自行编译，指向本地推理，并从 config.toml 驱动一切。

grok inspect 会打印框架在当前目录中发现的内容。包括配置来源、指令、技能、插件、钩子和 MCP 服务器。

综上所述，今天有四种使用方法是可行的。

查看 GitHub 仓库：https://github.com/xai-org/grok-build，公告链接：https://x.ai/news/grok-build-open-source，文档：https://docs.x.ai/build/overview。

SpaceXAI 开源 Grok Build：Rust 智能体框架、TUI 与工具层

Michal Sutter 是一名数据科学专业人士，拥有帕多瓦大学的数据科学理学硕士学位。凭借扎实的统计分析、机器学习和数据工程基础，Michal 擅长将复杂数据集转化为可操作的洞察。

Patter SDK Guide to Building a Restaurant Booking Phone Agent with Dynamic Variables, Guardrails, Latency Dashboards, and Eval Checks

Soofi Consortium Releases Soofi S 30B-A3B

Building a Gin Config Controlled PyTorch Pipeline with Configurable MLP Variants, Cosine Scheduling, and Runtime Parameter Overrides

SpaceXAI has open-sourced Grok Build：https://github.com/xai-org/grok-build , the terminal-based AI coding agent behind its grok CLI. The source landed on GitHub today. The release covers the agent harness, TUI, CLI shell, and developer tooling under the Apache 2.0 license

A harness is the scaffolding around a model. It assembles context, calls the model, parses the reply, and dispatches tool calls.

Grok Build was launched as an early beta on May 25, 2026. It is an agent that understands your codebase, edits files, executes shell commands, and searches the web. It also manages long-running tasks. It runs as a full-screen, mouse-interactive TUI.

Three surfaces exist. There is the interactive TUI, headless mode for scripting and CI. Editors embed it through the Agent Client Protocol (ACP) .

Building on that framing, SpaceXAI lists four published areas. The agent loop covers context assembly, response parsing, and tool-call dispatch. The tools cover how the agent reads, edits, and searches code. The terminal UI covers rendering, input handling, plan review, and the inline diff viewer. The extension system covers skills, plugins, hooks, MCP servers, and subagents.

Read that table as a reading order. Start at xai-grok-shell for the loop, then xai-grok-tools . One build note is easy to miss. The root Cargo.toml is generated, and the README says to treat it as read-only.

Beyond inspection, SpaceXAI frames one practical outcome. Grok Build can now run fully local-first. Compile it yourself, point it at local inference, and drive everything from config.toml .

grok inspect then prints what the harness discovered in the current directory. That covers config sources, instructions, skills, plugins, hooks, and MCP servers.

Given all of that, four uses hold up today.

Check out the GitHub Repo：https://github.com/xai-org/grok-build, the announcement：https://x.ai/news/grok-build-open-source, and the documentation：https://docs.x.ai/build/overview.

Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights.