Pi 1.0

Pi 1.0

Today we are proudly shipping Pi 1.0: a hardened, minimal, extensible agent harness that you can make your own. Hundreds of thousands of people around the world use Pi every week. Many of you submit issues and pull requests. Over the course of many months, we have used that feedback to improve, harden and evolve Pi into a stable piece of software that people and businesses can depend on.

今天,我们自豪地发布 Pi 1.0:一个经过强化、极简且可扩展的智能体框架,你可以根据自己的需求对其进行定制。全球每周有数十万人使用 Pi,你们中的许多人提交了问题反馈和拉取请求(Pull Requests)。在过去的几个月里,我们利用这些反馈不断改进、强化并演进 Pi,使其成为一款个人和企业都能信赖的稳定软件。

Pi is known for being minimal. We care about holding that line. While agentic tooling changes every week, many of the changes do not last. Pi does not work that way. We wait until something has proven itself, and only then do we consider adopting it; weighing its true functionality against its inherent added complexity. We spoke more about that process and how it relates to Codemode and MCP earlier this week here. The Pi 1.0 we are shipping today is a result of that process.

Pi 以极简著称,我们非常在意坚守这一原则。虽然智能体工具每周都在变化,但许多变化往往转瞬即逝。Pi 的运作方式并非如此。我们坚持等待某项技术经过验证后才考虑采用,并权衡其真实功能与随之带来的复杂性。本周早些时候,我们在这里详细讨论了这一过程以及它与 Codemode 和 MCP 的关系。今天发布的 Pi 1.0 正是这一过程的成果。

Pi already ran the latest models from every major provider, became a daily driver coding agent for people around the world, and provided a supermalleable substrate on which to build agentic applications. With Pi 1.0 we are adding the following into Pi:

  • Codemode (native support for MCP, and non-LLM models like Jev and image models)
  • Extension support for virtual models
  • Deferred tool loading
  • Cache warming for anthropic models
  • Mid-conversation system messages (transcript-aware prompt and tool changes)
  • A new TUI theme
  • Full-screen mode by default

Pi 已经能够运行各大主流厂商的最新模型,成为了全球用户日常使用的编程智能体,并提供了一个极具可塑性的底层架构,用于构建各种智能体应用。在 Pi 1.0 中,我们新增了以下功能:

  • Codemode(原生支持 MCP,以及 Jev 和图像模型等非大语言模型)
  • 虚拟模型的扩展支持
  • 工具延迟加载
  • Anthropic 模型的缓存预热
  • 对话中系统消息(支持感知对话记录的提示词和工具变更)
  • 全新的 TUI 主题
  • 默认全屏模式

We have thought about many of these features for months. They were thrown up against the wall and stuck. The list of things that fell off the wall is much longer. When we use Pi with all these new features it feels like a major step forward, but it also still feels simple, like Pi.

我们对其中许多功能已经构思了数月。它们经过了严格的筛选与测试,而那些被淘汰的功能清单则要长得多。当我们使用搭载了这些新功能的 Pi 时,感觉它迈出了一大步,但同时它依然保持着简洁,依然是那个我们熟悉的 Pi。

Alongside this work of continually refining and evolving Pi, we also began to understand that there were aspects of Pi that did not fit the shape of how many people wanted to use it. At Earendil, we want to bring Pi’s minimalism and the way it allows you to wield AI outside of the coding agent and outside of the terminal. It needs to be reachable from different surfaces and support longer-running conversations and tasks. In short, Pi must become more durable.

在不断打磨和演进 Pi 的过程中,我们也意识到 Pi 的某些方面并不符合许多用户的使用习惯。在 Earendil,我们希望将 Pi 的极简主义及其操控 AI 的方式带到编程智能体和终端之外。它需要能够从不同的界面访问,并支持更长时间的对话和任务。简而言之,Pi 必须变得更加“持久”(Durable)。

Rather than stray from our minimal roots and try to make Pi something it wasn’t, we combined that work into a new experimental package that we are shipping today, Pi Durable. Pi Durable is a new substrate for building long-running agentic applications that lets the builders and the users of those applications wield and steer the underlying intelligence with tremendous dexterity. It shares Pi’s key principles, minimalism and supermalleability, but it extends those principles into new dimensions. Mario writes in more detail about how we crafted Pi Durable here.

我们没有背离极简主义的初衷,也没有试图将 Pi 改造成它本不该成为的样子,而是将这些工作整合进了一个今天发布的新实验性包——Pi Durable。Pi Durable 是一个用于构建长效智能体应用的新架构,它让开发者和用户能够极其灵活地操控和引导底层的智能。它共享了 Pi 的核心原则——极简与超强可塑性,并将这些原则扩展到了新的维度。Mario 在这里详细介绍了我们是如何打造 Pi Durable 的。

Earendil was formed to craft software and open protocols that strengthen human agency. Today we are shipping tools to you all to help do just that. We’re eager to hear feedback from you and to harness the future out in the open together.

Earendil 的成立旨在打造能够增强人类自主权的软件和开放协议。今天,我们向大家发布这些工具,正是为了实现这一目标。我们期待听到你们的反馈,并共同在开源环境下驾驭未来。


Pi 1.0 is available today: curl -fsSL https://pi.dev/install.sh | sh or on Windows powershell -c "irm https://pi.dev/install.ps1 | iex"

Pi 1.0 现已发布: curl -fsSL https://pi.dev/install.sh | sh Windows 用户请使用: powershell -c "irm https://pi.dev/install.ps1 | iex"

Pi Durable is available today as an experimental package: npm install @earendil-works/pi-durable @earendil-works/pi-ai @earendil-works/chord

Pi Durable 现已作为实验性包发布: npm install @earendil-works/pi-durable @earendil-works/pi-ai @earendil-works/chord

Both are MIT licensed. Documentation is at pi.dev. Code is at github.com/earendil-works/pi.

两者均采用 MIT 协议开源。文档请访问 pi.dev,代码请访问 github.com/earendil-works/pi。


Codemode:

  • Pi writes a script that boils a week of commits down to a short summary
  • Pi writes itself an extension: a virtual model that plans with Claude Opus and implements with GPT, with Jev deciding when to switch
  • Reload, start a new session, and pick the new router/auto model
  • Planning runs on Claude Opus
  • Jev spots the switch to implementation and hands over to GPT
  • 6 Luna ! runs the finished script
  • /session breaks down cost per model and cache use

Codemode 示例:

  • Pi 编写脚本,将一周的提交浓缩为简短摘要
  • Pi 为自己编写扩展:一个使用 Claude Opus 进行规划、使用 GPT 进行实现的虚拟模型,并由 Jev 决定切换时机
  • 重新加载,开始新会话,并选择新的路由/自动模型
  • 规划任务在 Claude Opus 上运行
  • Jev 检测到切换至实现阶段,并移交给 GPT
  • 6 Luna ! 运行完成后的脚本
  • /session 命令可查看每个模型的成本和缓存使用情况明细