Skip to content

Commit 25283af

Browse files
spectopospectopo
authored
New version: kawayiYokami.P-ai version 0.13.1 (microsoft#390959)
1 parent f7e0e16 commit 25283af

4 files changed

Lines changed: 120 additions & 0 deletions

File tree

‎manifests/k/kawayiYokami/P-ai/0.13.1/kawayiYokami.P-ai.installer.yaml‎

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
# Created with YamlCreate.ps1 Dumplings Mod
2+
# yaml-language-server: $schema=https://aka.ms/winget-manifest.installer.1.12.0.schema.json
3+
4+
PackageIdentifier: kawayiYokami.P-ai
5+
PackageVersion: 0.13.1
6+
InstallerType: nullsoft
7+
Scope: user
8+
UpgradeBehavior: install
9+
ProductCode: P-ai
10+
ReleaseDate: 2026-06-20
11+
Installers:
12+
- Architecture: x64
13+
InstallerUrl: https://github.com/kawayiYokami/P-ai/releases/download/v0.13.1/P-ai_0.13.1_x64-setup.exe
14+
InstallerSha256: 7CAFCC086842720112D461C87C9A8B80F299855BE56023997366A146DB136E35
15+
ManifestType: installer
16+
ManifestVersion: 1.12.0

‎manifests/k/kawayiYokami/P-ai/0.13.1/kawayiYokami.P-ai.locale.en-US.yaml‎

Lines changed: 53 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
1+
# Created with YamlCreate.ps1 Dumplings Mod
2+
# yaml-language-server: $schema=https://aka.ms/winget-manifest.defaultLocale.1.12.0.schema.json
3+
4+
PackageIdentifier: kawayiYokami.P-ai
5+
PackageVersion: 0.13.1
6+
PackageLocale: en-US
7+
Publisher: yokami
8+
PublisherUrl: https://github.com/kawayiYokami
9+
PublisherSupportUrl: https://github.com/kawayiYokami/P-ai/issues
10+
PackageName: P-ai
11+
PackageUrl: https://github.com/kawayiYokami/P-ai
12+
License: GPL-3.0
13+
LicenseUrl: https://github.com/kawayiYokami/P-ai/blob/HEAD/LICENSE
14+
ShortDescription: A ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation.
15+
Description: |-
16+
A self-growing desktop AI work system — ready-to-use, with agent delegation, long-term memory, tool review, MCP, and high-concurrency workspace automation.
17+
PAI is an actively evolving desktop AI work system. It is not a chat client — it is a complete desktop system organized around conversations, tasks, memory, departments, tools, review, and remote messaging. The backend uses Rust async concurrency and streaming architecture to guarantee response speed; the frontend uses Vue 3 + DaisyUI for a clean interface. All data is stored locally, with no intermediate servers.
18+
19+
Entry & Efficiency
20+
Global hotkey summon, voice wakeup, background voice input, quick screenshot — PAI brings desktop AI access to "summon anytime, handle anything, continue anywhere." Supports local sessions, remote sessions, and multiple parallel sessions; quick commands can trigger common operations in one keystroke.
21+
Organization & Personas
22+
Multiple departments and personas can be independently configured, each with its own avatar and private memory. Tasks and sessions are separated by department, identity, and responsibility. Local sessions support multi-agent group chat; remote sessions support WeChat, Feishu, DingTalk, OneBot, and other protocols.
23+
Interface & Interaction
24+
UI, chat style, colors, and fonts are all customizable, with multiple windows running in parallel. Fast response, clean but not bare-bones.
25+
Capabilities & Tools
26+
A complete capability set is pre-built: LLM can execute operation scripts to control the computer and send reactions proactively; common Skills are built-in; full image-to-text, native PDF and Office reading are supported; tool modifications are reversible; tool execution and code changes can undergo multi-angle AI review. API provider onboarding is streamlined and ready to use.
27+
Memory & Context
28+
Long conversations are dynamically compressed and archived; a single session can persist indefinitely, with context staying effective through continuous compression and organization. The memory system is low-cost and comprehensive — the more you use it, the better the AI understands you.
29+
Engineering & Reliability
30+
High performance, concurrent, fast to respond. Local sessions support message delivery, session branching, and manual delegation; remote sessions support sending and receiving files and images. Built-in proactive planning mode, delegation system, and persona system; LLM can autonomously manage MCP, skills, personas, and departments. Tool execution has a review chain; code changes can be validated from multiple angles.
31+
32+
Real Usage Scenarios
33+
The following are not hypotheticals — they actually happened:
34+
- Starting from v0.8, PAI has been used to develop PAI itself for over 1 month, producing 407 commits and 496 file changes
35+
- Users have been using PAI continuously for financial analysis and news monitoring for over 3 months
36+
- Users have been using PAI via WeChat remote contacts to produce Xiaohongshu content for over 3 months, with over a thousand published posts
37+
- Users have been using PAI to analyze research papers for over 2 months and published multiple papers based on it
38+
- Users have been using PAI for scheduled web scraping, accumulating over 500M of data
39+
- A user ran PAI continuously for 20 hours on a programming task — it reviewed, resolved, researched online, and passed on its own
40+
- Users have been using PAI long-term to create game guides
41+
- Users have been using PAI long-term to operate games and complete daily tasks
42+
- Users run dozens of sessions simultaneously, using PAI to monitor multiple online channels at once
43+
- After extended use, users consistently report it gets smoother over time — the AI understands them better
44+
Tags:
45+
- agent
46+
- agentic
47+
- ai
48+
- large-language-model
49+
- llm
50+
ReleaseNotes: 'Full Changelog: https://github.com/kawayiYokami/P-ai/compare/v0.13.0...v0.13.1'
51+
ReleaseNotesUrl: https://github.com/kawayiYokami/P-ai/releases/tag/v0.13.1
52+
ManifestType: defaultLocale
53+
ManifestVersion: 1.12.0

‎manifests/k/kawayiYokami/P-ai/0.13.1/kawayiYokami.P-ai.locale.zh-CN.yaml‎

Lines changed: 43 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,43 @@
1+
# Created with YamlCreate.ps1 Dumplings Mod
2+
# yaml-language-server: $schema=https://aka.ms/winget-manifest.locale.1.12.0.schema.json
3+
4+
PackageIdentifier: kawayiYokami.P-ai
5+
PackageVersion: 0.13.1
6+
PackageLocale: zh-CN
7+
ShortDescription: 开箱即用的自我成长型桌面 AI 助理，面向长期任务、记忆、部门协作、工具审查、MCP 与高并发工作区自动化。
8+
Description: |-
9+
一个可自我成长的桌面 AI 工作系统——开箱即用，支持智能体委派、长期记忆、工具评审、MCP（任务-能力-规划）、以及高并发的工作空间自动化。
10+
PAI 是一个持续进化的桌面 AI 工作系统。它不是一个聊天客户端——而是一个围绕对话、任务、记忆、部门、工具、评审和远程消息构建的完整桌面系统。后端采用 Rust 异步并发与流式架构，确保响应速度；前端使用 Vue 3 + DaisyUI 实现简洁界面。所有数据本地存储，无中间服务器。
11+
12+
入口与效率
13+
全局热键唤起、语音唤醒、后台语音输入、快速截图——PAI 将桌面 AI 的使用体验做到“随时召唤、随地处理、无缝延续”。支持本地会话、远程会话及多个并行会话；快捷命令一键触发常见操作。
14+
组织与角色
15+
可独立配置多个部门与角色，每个角色拥有独立头像与私有记忆。任务与会话按部门、身份与职责分离。本地会话支持多智能体群聊；远程会话支持微信、飞书、钉钉、OneBot 等多种协议。
16+
界面与交互
17+
UI、聊天样式、颜色与字体均可自定义，支持多窗口并行运行。响应迅速，界面清爽而不简陋。
18+
能力与工具
19+
内置完整能力体系：大模型可执行操作脚本以控制电脑，并主动发送反馈；常用技能已预置；全面支持图文理解、原生 PDF 与 Office 文件阅读；工具修改可逆；工具执行与代码变更支持多角度 AI 评审。API 提供商接入流程简化，即接即用。
20+
记忆与上下文
21+
长对话动态压缩归档；单一会话可无限延续，上下文通过持续压缩与整理保持有效。记忆系统成本低且覆盖面广——使用越久，AI 越懂你。
22+
工程与可靠性
23+
高性能、高并发、响应迅速。本地会话支持消息传递、会话分支与手动委派；远程会话支持文件与图片收发。内置主动规划模式、委派系统与角色系统；大模型可自主管理 MCP、技能、角色与部门。工具执行具备评审链路，代码变更支持多维度验证。
24+
25+
真实使用场景
26+
以下并非设想，而是真实发生的情况：
27+
- 自 v0.8 版本起，PAI 已用于自身开发超过一个月，产生 407 次提交和 496 个文件变更
28+
- 用户连续使用 PAI 进行金融分析与新闻监控超过三个月
29+
- 用户通过微信远程连接使用 PAI 创作小红书内容超过三个月，发布帖子超千篇
30+
- 用户使用 PAI 分析科研论文超过两个月，并基于其成果发表多篇论文
31+
- 用户使用 PAI 执行定时网页抓取，累计获取数据超 5 亿条
32+
- 一位用户让 PAI 连续运行 20 小时完成编程任务——自行审查、解决问题、在线调研并最终通过
33+
- 用户长期使用 PAI 制作游戏攻略
34+
- 用户长期使用 PAI 操作游戏并完成日常任务
35+
- 用户同时运行数十个会话，利用 PAI 同时监控多个线上渠道
36+
- 长期使用后，用户普遍反馈系统运行愈发顺畅——AI 对用户的理解日益深入
37+
Tags:
38+
- 人工智能
39+
- 大语言模型
40+
- 智能体
41+
- 自主智能
42+
ManifestType: locale
43+
ManifestVersion: 1.12.0

‎manifests/k/kawayiYokami/P-ai/0.13.1/kawayiYokami.P-ai.yaml‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
# Created with YamlCreate.ps1 Dumplings Mod
2+
# yaml-language-server: $schema=https://aka.ms/winget-manifest.version.1.12.0.schema.json
3+
4+
PackageIdentifier: kawayiYokami.P-ai
5+
PackageVersion: 0.13.1
6+
DefaultLocale: en-US
7+
ManifestType: version
8+
ManifestVersion: 1.12.0

0 commit comments

Comments
 (0)