@jeffguo7/s-loop

git clone https://github.com/JeffGuo7/s-loop.git cd s-loop npm install npm run tauri:dev

mcp_servermcp

Install

agr install @jeffguo7/s-loop --target claude

This artifact does not publish files for Claude.

Document

{ "type": "module", "dependencies": { "@earendil-works/pi-agent-core": "0.80.6", "@earendil-works/pi-ai": "0.80.6", "@earendil-works/pi-coding-agent": "0.80.6", "@modelcontextprotocol/sdk": "^1.29.0", "cheerio": "^1.2.0", "cron-parser": "^4.9.0", "jiti": "^2.7.0", "nodemailer": "^6.9.0", "puppeteer-core": "^24.0.0", "undici": "^6.0.0" } }

Repository README

Describes JeffGuo7/s-loop as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.

S-Loop

AI Desktop Workbench — chat, agent orchestration, scheduled tasks, desktop pet, all in one Tauri 2 app

中文文档

Quick Start

Development

git clone https://github.com/JeffGuo7/s-loop.git
cd s-loop
npm install
npm run tauri:dev

Prerequisites: Node.js ≥ 18, Rust ≥ 1.85 (MSVC), npm

When running Vite and pi-server as separate development processes, set the same temporary value in VITE_SNOTRA_API_TOKEN and SNOTRA_API_TOKEN.

Download (Windows)

Download the latest installer from the Releases page.

Format	File
Installer (recommended)	`S-Loop_<version>_x64-setup.exe`
Portable	`S-Loop_<version>_x64_en-US.msi`

Features

Module	Description
AI Chat	Streaming SSE output, reasoning visualization, tool call logs, Markdown + syntax highlighting, Mermaid / LaTeX
Agent Builder	Custom agents (instructions / model / Skills / MCP / permissions), slash commands, drag-and-drop assembly
MCP Servers	stdio MCP process management, auto tool discovery, Rust-managed lifecycle
Skills	Local SKILL.md scanning, remote install from ClawHub, CLI integration, ZIP drag-and-drop
Scheduled Tasks	Cron / interval / one-shot, bind Agent + Skills, deliver to chat or platform
Platform Hub	Telegram (bidirectional sync), Email, Webhook, Feishu, DingTalk, WeCom, Slack, Discord, QQ Bot
Desktop Pet	SVG animated pet, transparent overlay window, multi-state, theme packs
Web Search	Bing / Brave / SearXNG / Tavily / Exa — 5 engines, zero-config default
Themes	9 color palettes × dark/light, glassmorphism, CSS variable driven

Tech Stack

Layer	Stack
Desktop	Tauri 2
Frontend	React 19 + TypeScript + Vite
Styling	Tailwind CSS 4 + HeroUI v3
State	Zustand
Animation	Framer Motion
Icons	Lucide React
Syntax	Shiki
AI Engine	`@earendil-works/pi-agent-core` + `pi-ai` + `pi-coding-agent`
AI Runtime	pi-server (Node.js child process, HTTP + SSE)
Database	SQLite (tauri-plugin-sql)
i18n	i18next (English / Chinese)

Architecture

The security and permission invariants shared by chat, tasks, MCP, platforms, and sub-agents are documented in docs/security-model.md.

┌─ Tauri 2 ───────────────────────────────────────────────────┐
│                                                               │
│  Rust Backend                  Node.js AI Engine              │
│  ┌──────────────────┐        ┌──────────────────────────┐   │
│  │ pi_server.rs     │◄──────►│ pi-server (HTTP + SSE)    │   │
│  │ mcp_manager.rs   │        │   Agent sessions           │   │
│  │ commands.rs      │        │   delegate_task / subagent │   │
│  │ skill_installer  │        │   Goal Loop executor       │   │
│  │ skills_cli.rs    │        │   task-scheduler (cron)    │   │
│  │ system_tray      │        │   platform-center (hub)    │   │
│  │                  │        │   telegram-monitor         │   │
│  └──────────────────┘        └──────────────────────────┘   │
│                                                               │
│  React Frontend                                               │
│  ┌───────────────────────────────────────────────────────┐   │
│  │ ChatView │ AgentBuilder │ TasksPage │ PetPage         │   │
│  │ SettingsModal │ FileTree │ WorkspacePanel │ Sidebar   │   │
│  │ MCP │ Skills │ Platforms │ WebSearch │ i18n           │   │
│  └───────────────────────────────────────────────────────┘   │
│                                                               │
└───────────────────────────────────────────────────────────────┘

License

Trustgrade A

passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
warnType matchbest-effort: server code not analyzed
Whether the artifact is really the kind of thing its metadata claims it is.
passFreshness
How long since the source repository was last pushed to.
passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

Aevery check passed
Bone warning
Ctwo warnings
Dprompt injection or body integrity failed, or three warnings
Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

git-20696292456e2026-08-03