Warp Agent 命令行界面发布：可在任意终端使用的多模型智能体

新功能：Warp Agent CLI，一款全新独立的命令行工具，让你可以在任何地方使用 Warp Agent 了解更多：/agent-cli

面向代理式编程的现代终端

原生支持编排的编码智能体

在任何终端中运行的强大编程代理

为您的组织提供安全、合规的代理式开发

今天，我们很高兴推出 Warp Agent CLI，这是一款全新独立的命令行工具，让你可以在任何地方使用 Warp Agent。它是内置于 Warp Terminal 的同一多模型代理，现在可在 Ghostty、iTerm 2、VSCode、Windows 内置终端或你喜欢的任何终端中使用。

Warp Agent CLI 拥有你对现代 CLI 编程代理的所有预期功能：它是为专业开发者打造的多模型、成本优化管理工具。开箱即用，你就可以访问前沿模型和开源权重模型，并根据任务复杂度进行自动路由。

这款 CLI 的开发真正解决了我们在其他代理式 CLI 中看到的与终端自身集成相关的缺陷——对于在终端中进行实际工作的开发者尤为重要。

从技术上讲，我们通过将 CLI 代理构建在 Warp 独特的终端基础设施之上实现了这一点：可以将我们的 CLI 代理视为跨代理会话的内置多路复用器。这允许更自然的交互，例如能够在代理会话中切换目录，让代理执行全屏终端命令（如 sqlite 和 mysql），甚至无需在远程安装二进制文件即可跨 SSH 会话运行。

让我们深入了解使 Warp Agent CLI 对终端用户极其有用的功能。

Warp Agent CLI 拥有独特的多路复用架构。在一个代理会话中，我们实际上通过在代理和底层 shell 之间增加一层间接层来运行和管理 pty 连接，这种架构类似于 tmux 的运行方式。多路复用由 Warp 的终端基础设施管理，因此我们的代理能够原生感知终端输入和输出（在 Warp 中称为“块”）。这比其他任何 CLI 代理都提供了更丰富的体验。以下是它所解锁的一些功能。

Warp Agent CLI 让你在代理会话中切换目录，甚至可以在远程机器上运行代理而无需安装远程二进制文件。这一切都是因为即使会话的基础“状态”发生变化，代理会话仍会继续。

当你在多仓库项目中工作，或者希望在可能权限有限的云机器上获得代理帮助时，持久化会话非常有用。

你可以通过代理会话运行全屏和交互式终端应用，如 sqlite 和 python。Warp Agent 也可以控制这些应用。因此，在 REPL 中，你可以让我们的代理编写查询或交互式调试代码。或者你可以让代理退出 vim……

例如，你可以让 Warp Agent 执行以下操作：

和其他 CLI 代理一样，你可以使用 `!` 来运行 shell 命令。但 Warp CLI 也支持自然语言识别：我们提供了一个分类器，能够自动区分 shell 命令和提示，并相应地调用 shell 或代理。

Warp Agent CLI 拥有 Warp 终端的一项旗舰功能：标签补全。开始输入命令，按下 Tab 键，即可看到参数和标志的建议。

Warp Agent CLI 是为自主开发时代而构建的，而不仅仅是手动提示代理。因此，它完全支持运行云代理和编排多代理工作流。

Warp 的独特之处在于，当你将 Warp Agent 与我们的云平台结合使用时，我们的工具可以不仅在具有不同模型的子代理之间进行委派，还可以在完全不同的工具链之间进行委派，例如 Claude Code 和 Codex。

Warp 的代理是一个编排代理。它将复杂任务拆解委派给子代理，提供原生界面，使你轻松查看每个被编排的代理在做什么。你甚至可以使用箭头键在子代理和编排代理会话之间切换。

在 CLI 中开始工作，然后在希望关闭笔记本时将任务交给云端。所有云代理都集中跟踪，并可以通过网页进行监控和引导，以便你随时继续工作。

Warp Agent 是一个帕累托高效的工具，基于任务复杂度进行自动路由。开箱即用，它提供对前沿模型和开放权重模型的访问。

我们还投入了更多资源，使开放权重模型在我们的框架中表现出色，并提供对自定义模型路由器的一流支持，让你定义哪些模型处理哪些任务。

安装 CLI 后，你有三种方式开始使用：

预约演示，我们将带你了解与你的技术栈相匹配的工作流程。

学习如何将计算机和浏览器的使用添加到云软件工厂代理中，以重现问题并验证修复和新功能。

尽管我们现在生活在 2026 年，但感觉人们似乎已经忘记了 2006 年的教训：软件属于云端，而不是个人桌面。

今天我们发布了 Warp 社区最受欢迎的更新之一：更多推理控制。

通过 Warp Preview 获取未发布和实验性功能的早期访问：/download-preview

NEW: Warp Agent CLI, a new standalone CLI that lets you use the Warp Agent anywhere Learn More：/agent-cli

A modern terminal for agentic coding

The orchestration-native coding agent

A powerful coding agent that works in any terminal

Secure, compliant agentic development for your org

Today we are excited to launch the Warp Agent CLI, a new standalone CLI that lets you use the Warp Agent anywhere. It’s the same multi-model agent that’s built into Warp Terminal, now available in Ghostty, iTerm 2, VSCode, the built-in Windows terminal, or whatever terminal you prefer.

The Warp Agent CLI has everything you’d expect from a modern CLI coding agent: it’s a multi-model, cost-optimizing harness built for pro developers. Out of the box, you get access to frontier and open-weight models and auto-routing based on task complexity.

The CLI was truly built to fix gaps we were seeing with other agentic CLIs related to how well they integrate with the shell itself— especially important for developers doing real work in the terminal.

Technically, we accomplished this by building the CLI agent on top of Warp’s unique terminal infrastructure: think of our CLI agent as a built-in mux’er across agent sessions. This allows more natural interactions, like being able to switch directories in agent sessions, have the agent drive full-screen terminal commands (e.g. sqlite and mysql), and even run across ssh sessions with no remote binary install.

Let’s dive into the features that make the Warp Agent CLI extremely useful for folks who live in the terminal.

The Warp Agent CLI has a unique mux’ing architecture. Within an agent session, we are actually running and managing pty connections with a layer of indirection between the agent and the underlying shell, a similar architecture to how tmux works. The mux’ing is managed by Warp’s terminal infrastructure, so our agent is natively aware of terminal inputs and output (what we call “blocks” in Warp). This allows for a richer experience than any other CLI agent. Here are some of the features it unlocks.

The Warp Agent CLI lets you switch directories while in an agent session, and even run agents on remote machines without installing remote binaries. This is all because the agent session continues even when the base “state” of the session changes.

Persistent sessions are useful when you are working across multi-repo projects, or when you want agent assistance on cloud machines where you might have limited permissions to install software.

You can run full-screen and interactive terminal apps like sqlite and python through the agent session. Warp Agent can also control those apps. So within a REPL you can ask our agent to write queries or interactively debug code. Or you can ask the agent to quit vim…

For example, you can ask the Warp Agent to:

As with other CLI agents, you can use `!` to run a shell command. But Warp CLI also supports natural language detection: we ship with a classifier that automatically distinguishes shell commands from prompts, and invokes either the shell or agent accordingly.

The Warp Agent CLI has one of Warp Terminal’s flagship features: tab completions. Start typing a command, hit tab, and see suggestions for arguments and flags.

The Warp Agent CLI is built for the age of autonomous development, not just manually prompting agents. As such, it has full support for running cloud agents and orchestrating multi-agent workflows.

Unique to Warp, when you couple the Warp Agent with our cloud platform, our harness can delegate not just across subagents with different models, but with entirely different harnesses like Claude Code and Codex.

Warp’s agent is an orchestration agent. It delegates to subagents to break apart hard tasks, with a native interface that makes it easy to see what each orchestrated agent is doing. You can even use arrow keys to switch between subagent and orchestrator agent sessions.

Start work in the CLI, then hand it off to the cloud when you want to close your laptop. All cloud agents are tracked centrally and can be monitored and steered via the web so you can continue work on the go.

Warp Agent is a pareto-efficient harness with auto-routing based on task complexity. Out of the box, it comes with access to frontier models and open-weight models.

We also have invested more to make open weight models great within our harness, with first class support for custom model routers where you define which models handle which tasks.

Once you’ve installed the CLI, you have three ways to get started:

Book a demo and we’ll walk you through the workflows that map to your stack.

Learn how to add computer and browser use to cloud software factory agents to reproduce issues and verify fixes and new features.

Even though we are living in 2026, it feels like folks have forgotten the lessons of 2006: software belongs in the cloud, not on individuals’ desktops.

Today we’re releasing one of the most requested updates from the Warp community: more control over inference.

Get early access to unreleased and experimental features with Warp Preview：/download-preview