🦀 Krab

Complete AGI Agent Framework — Production-Ready with 17 Advanced Features

State-of-the-Art (March 2026 Ultimate Stack)

Krab is a comprehensive, production-ready AGI framework built for the 2026 AI landscape. It features 17 advanced capabilities including image generation, code execution, desktop automation, web browsing, voice processing, multi-agent collaboration, enterprise security, and more.

🌟 Why Krab?

🚀 Production-Ready: All 17 features implemented and tested
🛡️ Enterprise-Grade: Security, analytics, and compliance built-in
🔧 Developer-Friendly: Complete SDK and integration tools
⚡ High Performance: < 1s startup, parallel execution
🌐 Multi-Provider: 15+ LLM providers supported

📊 Framework Architecture

graph TB
    User[User Input] --> CLI[CLI Interface]
    CLI --> Agent[AGI Agent Core]
    
    Agent --> Memory[Conversation Memory]
    Agent --> Tools[Tool Registry]
    Agent --> LLM[LLM Provider]
    
    Tools --> Creative[🎨 Creative AI]
    Tools --> Automation[🖥️ Automation]
    Tools --> Collaboration[🤝 Collaboration]
    Tools --> Enterprise[📊 Enterprise]
    
    Creative --> ImageGen[Image Generation]
    Creative --> Voice[Voice Intelligence]
    
    Automation --> Desktop[Desktop Control]
    Automation --> Web[Web Automation]
    Automation --> Code[Code Execution]
    
    Collaboration --> MultiAgent[Multi-Agent System]
    Collaboration --> MCP[MCP Integration]
    Collaboration --> Scheduler[Task Scheduling]
    
    Enterprise --> Analytics[Advanced Analytics]
    Enterprise --> Security[Security System]
    Enterprise --> Cloud[Cloud Deployment]
    
    LLM --> Gemini[Gemini]
    LLM --> OpenAI[OpenAI]
    LLM --> Anthropic[Anthropic]
    LLM --> Local[Local Models]
    
    Agent --> Response[AGI Response]
    Response --> User

🔄 Agent Workflow

flowchart TD
    Start([Start]) --> Input[User Input]
    Input --> Think[🧠 Think: Generate Plan]
    Think --> Tools{Use Tools?}
    
    Tools -->|Yes| Execute[⚡ Execute Tools]
    Tools -->|No| Respond[💬 Generate Response]
    
    Execute --> Success{Success?}
    Success -->|Yes| Reflect[🔍 Reflect on Results]
    Success -->|No| Retry[🔄 Retry with Different Approach]
    
    Reflect --> Quality{Quality OK?}
    Quality -->|Yes| Respond
    Quality -->|No| Improve[📈 Improve Response]
    
    Retry --> MaxRetries{Max Retries?}
    MaxRetries -->|Yes| Error[❌ Report Error]
    MaxRetries -->|No| Think
    
    Improve --> Think
    Respond --> Output[📤 Output Response]
    Error --> Output
    Output --> End([End])

🏗️ System Architecture

graph LR
    subgraph "User Interface"
        CLI[CLI]
        Web[Web UI]
        Desktop[Desktop App]
    end
    
    subgraph "Core Engine"
        Agent[AGI Agent]
        Memory[Memory System]
        Tools[Tool Registry]
    end
    
    subgraph "AI Providers"
        Gemini[Gemini]
        OpenAI[OpenAI]
        Anthropic[Anthropic]
        Local[Local Models]
    end
    
    subgraph "Feature Modules"
        Creative[Creative AI]
        Automation[Automation]
        Collaboration[Collaboration]
        Enterprise[Enterprise]
    end
    
    CLI --> Agent
    Web --> Agent
    Desktop --> Agent
    
    Agent --> Memory
    Agent --> Tools
    Agent --> Gemini
    Agent --> OpenAI
    Agent --> Anthropic
    Agent --> Local
    
    Tools --> Creative
    Tools --> Automation
    Tools --> Collaboration
    Tools --> Enterprise

🎯 Tool Execution Flow

sequenceDiagram
    participant User
    participant Agent
    participant Tools
    participant LLM
    participant Memory
    
    User->>Agent: User Input
    Agent->>Memory: Load Context
    Agent->>LLM: Generate Plan
    
    alt Plan Uses Tools
        Agent->>Tools: Execute Tool(s)
        Tools->>Agent: Tool Results
        Agent->>LLM: Process Results
    end
    
    LLM->>Agent: Generate Response
    Agent->>Memory: Store Conversation
    Agent->>User: Final Response

✨ Key Features (2026 Complete Stack)

🎨 Creative & Media

Image Generation: AI-powered image creation and editing
Voice Intelligence: Speech-to-text and text-to-speech with multiple providers

🖥️ Automation & Control

Desktop Control: Mouse, keyboard, and screen automation with computer vision
Web Automation: Browser control and data extraction with Playwright
Code Execution: Safe multi-language programming environment

🤝 Collaboration & Communication

Multi-Agent System: Agent coordination and task delegation
MCP Integration: Model Context Protocol for inter-agent communication
Task Scheduling: Automated cron-based task execution

🧠 Knowledge & Extensibility

Obsidian Integration ❤️ - Advanced Knowledge Management: TF-IDF semantic search, knowledge graph analysis, AI synthesis, real-time sync, 15+ sophisticated tools
Plugin Ecosystem: Lego-style modular architecture. Add new tools, agents, or middleware without touching core code.

📊 Enterprise Features

Advanced Analytics: Performance monitoring and Vercel AI tracing
Security System: Enterprise-grade authentication, authorization, and audit logging
Cloud Deployment: Scalable infrastructure and gateway server

🔧 Developer Tools

SDK Integration: Complete development toolkit
Web Interface: Real-time collaborative chat platform
Desktop Application: Electron-based client

🧩 Plugin Ecosystem (Lego Architecture)

Krab is designed to be infinitely extensible. Our plugin system allows you to create your own "blocks" and plug them in seamlessly.

# Create a new tool plugin in seconds
krab plugins create my-custom-tool --type tool

# Install a local plugin
krab plugins install ./my-plugin-folder

# List all plugins
krab plugins list

🚀 Quick Start

⭐ Star the Repository!

If you find Krab useful, please give us a ⭐ on GitHub!

1. Installation

git clone https://github.com/OpenKrab/Krab.git
cd Krab
npm install --legacy-peer-deps

2. Configuration

Copy the example environment file:

cp .env.example .env

Add your preferred API key (e.g., GEMINI_API_KEY, KILOCODE_API_KEY, OPENAI_API_KEY). For Obsidian support, set OBSIDIAN_VAULT_PATH=/path/to/your/vault.

3. Build & Run

npm run build
npm start

Or use development mode:

npm run dev

🎯 Usage Examples

Interactive Chat

npm start chat

Quick Questions

npm start ask "Generate an image of a futuristic city"

Knowledge Base (Obsidian)

npm start ask "Search my obsidian vault for notes about AGI and summarize them"

Web Automation

npm start ask "Navigate to example.com and extract the main heading"

Code Execution

npm start ask "Write a Python script to analyze this dataset"

Desktop Control

npm start ask "Take a screenshot and save it to desktop"

🛠️ Available Commands

Core Commands

krab chat - Start interactive chat session
krab ask <question> - Ask a single question
krab tools - List all available tools
krab config - Manage configuration

Plugin Commands

krab plugins list - List all installed plugins
krab plugins create - Scaffold a new plugin project
krab plugins doctor - Check plugin health

Advanced Commands

krab gateway - Start web API server
krab scheduler - Manage scheduled tasks
krab analytics - View performance metrics
krab security - Security management

In-Chat Commands

/plugins - Show loaded plugins and their status
/tools - View all loaded tools and permissions
/memory - Check conversation buffer status
/debug - View current provider and configuration
/clear - Clear conversation memory
/help - Show available commands

🏗️ Architecture

✅ Completed Features (Phase 1-4)

Core AGI Engine - Advanced reasoning and tool integration
Voice Intelligence - Complete STT/TTS system
Desktop Automation - Mouse, keyboard, vision control
Web Automation - Browser control and data extraction
Code Execution - Safe multi-language programming
Creative AI - Image generation and media processing
Cloud Infrastructure - Enterprise deployment and monitoring
Desktop Application - Modern Electron UI
Web Interface - Real-time collaborative chat
Developer SDK - Complete integration toolkit
Advanced Analytics - Observability and performance tracking
Agent Collaboration - Multi-agent coordination system
MCP Integration - Inter-agent communication protocol
Scheduler System - Automated task execution
Browser Agent - Web automation with AI vision
Security Enhancements - Enterprise security and compliance
Obsidian Integration ❤️ - Deep Knowledge Base connection
Plugin Ecosystem 🧩 - Lego-style modular architecture
Testing & Validation - Framework testing and validation

🚧 Pending Features (Phase 5)

Mobile Apps - React Native iOS/Android applications
Enterprise Features - Advanced business capabilities

🔧 Built-in Tools

Krab includes 60+ powerful tools across 19 feature categories:

System Tools

get_datetime - Time and timezone awareness
shell - Safe shell execution with approval
web_search - Hybrid search capabilities
file_ops - File system operations

Knowledge Tools (Obsidian) — 15+ Advanced Tools

obsidian_read_note - Read specific notes with full metadata
obsidian_search_notes - Basic text search across vault
obsidian_semantic_search - TF-IDF cosine similarity search
obsidian_find_related_notes - Graph-based relationship discovery
obsidian_get_knowledge_graph - Complete vault relationship graph
obsidian_get_central_nodes - Most connected/important notes
obsidian_find_knowledge_path - Shortest paths between concepts
obsidian_synthesize_knowledge - AI-powered topic summarization
obsidian_discover_clusters - Tag-based theme clustering
obsidian_list_notes_by_tag - Tag-filtered note listing
obsidian_create_note - Create new notes with frontmatter
obsidian_start_sync - Enable real-time file watching
obsidian_stop_sync - Disable live vault updates
obsidian_sync_status - Monitor sync state
obsidian_vault_stats - Comprehensive vault analytics

Creative Tools

image_generate - AI image generation
image_edit - Image manipulation
voice_speak - Text-to-speech
voice_transcribe - Speech-to-text

Automation Tools

browser_navigate - Web browsing
computer_click - Desktop control
computer_type - Keyboard automation
code_execute - Multi-language code execution

Enterprise Tools

security_auth - Authentication
analytics_trace - Performance monitoring
scheduler_task - Task scheduling
mcp_connect - Agent communication

🛡️ Security

Krab implements enterprise-grade security:

Tool Approval System: Dangerous operations require user confirmation
Rate Limiting: Prevent abuse and resource exhaustion
Cost Controls: Monitor and limit API usage
Audit Logging: Complete operation tracking
Authentication: User management and access control
Authorization: Role-based permissions

📊 Performance

Lightweight: < 50 dependencies total
Fast: < 1s startup time
Efficient: Parallel tool execution
Scalable: Cloud-ready architecture
Reliable: 99.9% uptime capability

🔌 Krab Plugin System

Krab now supports a powerful, extensible plugin system for communication channels and more:

Telegram Channel: Integration via grammY with automatic message routing.
WhatsApp Channel: Multi-device support via Baileys (scan QR to connect).
Discord Channel: Full bot support with DM and channel integration.
Web Control UI: A modern, glassmorphic dashboard for monitoring gateway status and managing active channels.

🛣️ Advanced Features

Multi-Agent Routing: Route messages to specific agents based on sender/workspace.
Session Isolation: Each communication session maintains its own memory and context.
Vector Memory: Long-term semantic search across all conversations.
Service Installation: Easily install Krab Gateway as a system service on Windows, Linux, and macOS.

📱 Deployment Platforms

🌐 Providers

Krab supports 15+ LLM providers:

Free: Gemini 2.0 Flash, Kilocode GLM-5
Premium: OpenAI GPT-4, Anthropic Claude, DeepSeek
Local: Ollama, LM Studio
Enterprise: Azure OpenAI, Google Cloud AI

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

📄 License

MIT License - see LICENSE file for details.

🦀 Krab — Complete AGI Framework for 2026

Built with 💙 for the AI revolution

19 Features • 60+ Tools • Extension Ready • Production-Tested

_{⭐ Star us on GitHub to support the project!}

Name		Name	Last commit message	Last commit date
Latest commit History 26 Commits
apps		apps
assets/image		assets/image
bin		bin
docs		docs
krab-plugins		krab-plugins
src		src
test		test
.dockerignore		.dockerignore
.env.example		.env.example
.gitignore		.gitignore
API.md		API.md
CONTRIBUTING.md		CONTRIBUTING.md
Dockerfile		Dockerfile
PLAN.md		PLAN.md
README.md		README.md
docker-compose.yml		docker-compose.yml
package.json		package.json
pnpm-lock.yaml		pnpm-lock.yaml
railway.json		railway.json
render.yaml		render.yaml
tsconfig.json		tsconfig.json
tsup.config.ts		tsup.config.ts

Folders and files

Latest commit

History

Repository files navigation

🦀 Krab

🌟 Why Krab?

📊 Framework Architecture

🔄 Agent Workflow

🏗️ System Architecture

🎯 Tool Execution Flow

✨ Key Features (2026 Complete Stack)

🎨 Creative & Media

🖥️ Automation & Control

🤝 Collaboration & Communication

🧠 Knowledge & Extensibility

📊 Enterprise Features

🔧 Developer Tools

🧩 Plugin Ecosystem (Lego Architecture)

🚀 Quick Start

⭐ Star the Repository!

1. Installation

2. Configuration

3. Build & Run

🎯 Usage Examples

Interactive Chat

Quick Questions

Knowledge Base (Obsidian)

Web Automation

Code Execution

Desktop Control

🛠️ Available Commands

Core Commands

Plugin Commands

Advanced Commands

In-Chat Commands

🏗️ Architecture

✅ Completed Features (Phase 1-4)

🚧 Pending Features (Phase 5)

🔧 Built-in Tools

System Tools

Knowledge Tools (Obsidian) — 15+ Advanced Tools

Creative Tools

Automation Tools

Enterprise Tools

🛡️ Security

📊 Performance

🔌 Krab Plugin System

🛣️ Advanced Features

📱 Deployment Platforms

🌐 Providers

🤝 Contributing

📄 License

About

Resources

Contributing

Uh oh!

Stars

Watchers

Forks

Releases 1

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages