shinkai-local-ai-agents
Health Gecti
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 429 GitHub stars
Code Basarisiz
- rm -rf — Recursive force deletion command in .github/workflows/rollout-version.yml
Permissions Gecti
- Permissions — No dangerous permissions requested
This is a free, open-source platform that provides a visual, no-code interface for creating and orchestrating local or remote AI agents. It natively supports the Model Context Protocol (MCP) and includes built-in features for complex automations and decentralized crypto payments.
Security Assessment
Risk Rating: Medium. The tool explicitly handles highly sensitive data, including locally stored cryptocurrency private keys and financial transactions. From an operational standpoint, the automated scanning flagged a recursive force deletion command (`rm -rf`) inside a GitHub Actions workflow file. While common in deployment scripts, this represents an execution risk if modified or triggered improperly. No dangerous runtime permissions or hardcoded API secrets were detected. Its "local-first" design philosophy generally keeps user data and computations private, though the hybrid cloud capabilities mean network requests are inherently part of its architecture.
Quality Assessment
The project exhibits strong health and maintenance metrics. It is actively maintained, with recent repository pushes within the last few days. Backed by a growing community of over 400 GitHub stars, the tool is licensed under the permissive and standard Apache-2.0, making it highly accessible for developers.
Verdict
Use with caution: while the project is actively maintained and well-structured, developers should carefully review the workflow files and fully understand the inherent risks of a tool that autonomously handles both shell execution and cryptocurrency assets.
Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.
Shinkai
Create Powerful AI Agents using local or remote AIs
Build collaborative AI agents that work together, handle payments, and automate complex workflows
Shinkai is a free, open-source platform that democratizes AI agent creation.
No coding required – just drag, drop, and deploy intelligent agents that can work across platforms and handle real-world tasks.
Read this in: 简体中文 | 粵語 | 한국어 | 日本語 | Español
Features • Demo • Examples • Quick Start • Development • Documentation
🚀 Features
🎯 No-Code Agent Builder – Create specialized AI agents in minutes through an intuitive visual interface. No programming experience needed.
🤖 Multi-Agent Orchestration – Deploy teams of agents that collaborate, share context, and coordinate complex multi-step workflows automatically.
💰 Crypto-Native Architecture – Built-in support for decentralized payments, DeFi interactions, and autonomous economic agents that can transact independently.
🔗 Universal Protocol Support – Seamlessly integrates with Model Context Protocol (MCP), making your agents compatible with Claude, Cursor, and the broader AI ecosystem.
⚡ Hybrid Deployment – Run everything locally for maximum privacy, connect to cloud models for enhanced capabilities, or combine both approaches as needed.
🔐 Security-First Design – Your crypto keys, sensitive data, and computations remain under your control with local-first architecture.
🌐 Cross-Platform Compatibility – Works on Windows, macOS, and Linux with consistent performance and user experience.
🎬 Demo
Watch Shinkai agents collaborate to analyze market data, execute trades, and manage complex workflows autonomously.
📋 Examples
💹 Autonomous Trading Bot – Deploy an agent that monitors social sentiment, analyzes market trends, and executes trades based on predefined strategies.
📧 Intelligent Email Assistant – Create an agent that categorizes incoming emails, drafts contextual responses, and automatically schedules follow-ups.
📊 Data Intelligence Agent – Build agents that scrape web data, perform trend analysis, and generate comprehensive reports with actionable insights.
🔄 Workflow Automation Hub – Orchestrate multiple specialized agents that handle different components of complex business processes seamlessly.
🏦 DeFi Portfolio Manager – Set up agents that monitor your crypto investments, rebalance portfolios, and execute yield farming strategies.
🚀 Quick Start
One-Click Installation
- Download the latest release for your platform from our releases page
- Install and launch Shinkai
- Create your first AI agent using our step-by-step guided interface
System Requirements
- Memory: 4GB RAM minimum (8GB recommended)
- Storage: 2GB free space
- OS: Windows 10+, macOS 10.15+, or Linux (Ubuntu 20.04+)
🛠 Development
Architecture Overview
Shinkai is built as a modern monorepo using NX for orchestration and dependency management. The architecture consists of:
Core Applications:
- shinkai-desktop – Cross-platform Tauri application with React frontend
Shared Libraries:
- shinkai-message-ts – Message protocols and network communication with Shinkai Node
- shinkai-node-state – React Query-based state management for node data
- shinkai-ui – Reusable React components with design system
- shinkai-artifacts – Styled UI primitives built on Radix and Tailwind CSS
- shinkai-i18n – Internationalization utilities powered by i18next
Technology Stack:
- Frontend: React 18, TypeScript, Tailwind CSS, Radix UI
- Desktop: Tauri (Rust + React)
- State Management: Zustand (UI state) + React Query (server state)
- Build System: Vite, NX monorepo
- Testing: Vitest, React Testing Library
🚀 Getting Started
1. Clone and Setup
git clone https://github.com/dcSpark/shinkai-apps
cd shinkai-apps
nvm use
npm ci
2. Download Required Side Binaries
Before running Shinkai, you'll need to download the embedded Shinkai Node binary that powers the application's core functionality. This can be done with a single command based on your platform:
macOS (Apple Silicon):
ARCH="aarch64-apple-darwin" \
SHINKAI_NODE_VERSION="v1.1.20" \
OLLAMA_VERSION="v0.12.3" \
npx ts-node ./ci-scripts/download-side-binaries.ts
Linux:
ARCH="x86_64-unknown-linux-gnu" \
OLLAMA_VERSION="v0.12.3" \
SHINKAI_NODE_VERSION="v1.1.20" \
npx ts-node ./ci-scripts/download-side-binaries.ts
Windows:
$ENV:OLLAMA_VERSION="v0.12.3"
$ENV:SHINKAI_NODE_VERSION="v1.1.20"
$ENV:ARCH="x86_64-pc-windows-msvc"
npx ts-node ./ci-scripts/download-side-binaries.ts
📦 Essential Commands
Development Server
# Run desktop app (recommended for development)
npx nx serve:tauri shinkai-desktop
Building
# Build desktop application
npx nx build shinkai-desktop
# Create development build
NODE_OPTIONS="--max_old_space_size=8192" npx nx build shinkai-desktop --config="./src-tauri/tauri.conf.development.json"
# Build all projects
npx nx run-many --target=build
Third party data and repository management
# Update the built-in Ollama models repository. This repository contains model definitions, tags and metadata for all supported AI models. The command below regenerates the repository files to ensure compatibility with the latest Ollama version and model updates
npx ts-node ./ci-scripts/generate-ollama-models-repository.ts
# Generate Composio apps repository - This script regenerates the repository of pre-built Composio apps and templates that users can import into Shinkai. It ensures the app catalog stays up-to-date with the latest official releases.
deno run -A ./ci-scripts/composio-repository/main.ts
# Generate translations for all languages (EN, ES, etc.)
# This command uses AI to automatically generate translations for all supported languages based on the primary i18n source file (English).
# It ensures consistent translations across the entire application while maintaining natural language quality.
npx nx run shinkai-i18n:i18n
Testing & Quality
# Run tests
npx nx test [project-name]
npx nx run-many --target=test
# Lint code
npx nx lint [project-name]
npx nx run-many --target=lint
🏗 Project Structure
shinkai-apps/
├── apps/
│ └── shinkai-desktop/ # Main desktop application
├── libs/
│ ├── shinkai-message-ts/ # Core messaging protocol
│ ├── shinkai-node-state/ # State management
│ ├── shinkai-ui/ # Component library
│ ├── shinkai-artifacts/ # UI primitives
│ └── shinkai-i18n/ # Internationalization
├── ci-scripts/ # Build and deployment scripts
└── tools/ # Development utilities
🎨 UI Development Guidelines
Component Libraries:
- Radix UI – Unstyled, accessible component primitives
- Tailwind CSS – Utility-first styling and responsive design
- Shadcn/ui – Pre-built component patterns
State Management:
- Zustand – Client-side UI state management
- React Query – Server state, caching, and synchronization
🌍 Internationalization
Shinkai supports multiple languages through our i18n system:
# Add new translation keys
# Edit files in libs/shinkai-i18n/locales/
# Generate updated translation types
npx nx run shinkai-i18n:i18n
# Supported languages: en-US, es-ES, zh-CN, zh-HK, ko-KR, ja-JP, id-ID, tr-TR
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
📚 Additional Resources
- Official Documentation – Comprehensive guides and API reference
- Discord Community – Get help and connect with other developers
- Twitter Updates – Latest news and announcements
Built with ❤️ by the Shinkai community
Apache License •
Report Bug •
Request Feature
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi
