Skip to content

Releases: ratna3/theJoker

Experimental Build

17 Feb 17:33
@ratna3 ratna3
v1.1.1
f5cbeac

Choose a tag to compare

View all tags
Experimental Build

🃏 The Joker — Agentic Terminal v1.1.1

Pull Request: RK-Dev-Beta → main

Full-stack build of The Joker Agentic Terminal — an autonomous, AI-powered terminal that understands natural language, scrapes the web, generates complete projects, performs OSINT reconnaissance, and deploys applications.

📊 PR Stats

Metric Value
Commits 29
Files Changed 103
Lines Added 55,255+
Lines Removed 528
Test Suites 22
Tests Passing 980
Test Coverage 80%+
Version 1.1.1

🎯 What This PR Achieves

This PR delivers the complete implementation of The Joker Agentic Terminal across 20 development phases, taking the project from initial setup to a fully-featured, tested, Dockerized AI agent with 29 registered tools.

🏗️ Development Phases

Phase 1–4: Foundation

  • Project Setup — TypeScript + Node.js boilerplate, tsconfig.json, ESLint, Prettier
  • LLM Integration — LM Studio API client (src/llm/client.ts), prompt templates, response parsing
  • Web Scraping Engine — Puppeteer-based browser automation with stealth mode, anti-detection, and data extraction
  • Agent System — Core autonomous agent loop with planner, executor, and session memory

Phase 5: Tool System & Execution

  • Tool registry with category support (SEARCH, SCRAPE, PROCESS, FILE, CODE)
  • Parameter validation and error handling
  • Dependency resolution and chaining

Phase 6: Terminal Interface & UX

  • Enhanced CLI system with chalk-powered display
  • Command handler architecture
  • Real-time progress tracking with ora spinners

Phase 7: Autonomous Agent Loop

  • JokerAgent with Think → Plan → Act → Observe cycle
  • Self-correction and iterative refinement
  • Goal detection, action planning, and synthesis

Phase 8: Data Processing & Output Formatting

  • 5 data processing tools: transform, clean, extract_patterns, convert, summarize
  • Rich terminal output with markdown and code block rendering

Phase 9: Error Handling & Resilience

  • Custom error types and centralized handler
  • Retry logic with exponential backoff
  • Circuit breaker pattern for external service calls

Phase 10: Testing Infrastructure

  • Jest configuration with 80%+ coverage
  • Mock system for browser and LLM dependencies
  • 191 → 980 tests across all phases

Phase 11: Code Generation Engine

  • LLM-powered code generation with template system
  • Framework templates: React, Next.js, Vue, Express
  • Component, page, and style generation

Phase 12: Project Scaffolding System

  • Full project scaffolding from natural language
  • npm install automation and directory structure creation
  • Integration with code generation engine

Phase 14: File System Indexer

  • AST-like parser for TypeScript/JavaScript files
  • File watcher with chokidar for real-time change detection
  • Dependency graph construction

Phase 15: Code Understanding & Context

  • Static analysis with code complexity scoring
  • Import/export resolution and symbol tracking

Phase 16: Multi-File Operations

  • Batch file creation and manipulation
  • Import management and automated refactoring (721 tests)

Phase 17: Progress Tracking System

  • Auto-generated progress.md reports
  • Task tracking with file change and build monitoring (784 tests)

Phase 18: Build & Development Workflow

  • Build manager, dev server orchestration
  • Error parsing and auto-fix pipeline (836 tests)

Phase 19: Testing & Quality Assurance

  • Comprehensive test generator (test-generator.ts)
  • Integration workflow tests
  • Full regression suite

Phase 20: Deployment Automation

  • Deployer module for Docker, Kubernetes, and CI/CD
  • Packager for production bundling

🌟 Headline Features

🎨 Vibe Coding Mode — Natural Language → Running App

Describe an app in plain English and The Joker builds it end-to-end:

🃏 joker > vibe Build me a portfolio website with dark mode and a contact form
  • LLM-powered prompt analysis → structured project spec
  • Automatic framework detection (React, Next.js, Vue, Express)
  • Full code generation for components, pages, and styles
  • Automated npm install + dev server launch + browser open
  • Live session refinement via HMR

Key files: src/agents/vibe-coder.ts, src/project/dev-server.ts

🔍 Hack Mode (Recon) — Automated OSINT

One-command passive domain reconnaissance:

🃏 joker > recon example.com
  • DNS records (A, AAAA, MX, TXT, NS, CNAME, SOA)
  • WHOIS lookup (registrar, dates, nameservers)
  • SSL/TLS certificate analysis
  • HTTP security header inspection
  • Tech stack detection (25+ signatures: React, Next.js, Vue, WordPress, Cloudflare, Vercel, AWS…)
  • Email and social link extraction
  • Full-page screenshot capture
  • Security score (0–100) and markdown report saved to ./reports/

Key file: src/tools/recon.ts

🖥️ TUI Dashboard — Real-Time Agent Visualization

Full-screen interactive terminal dashboard built with blessed:

  • Split-pane UI: Agent Thinking (left) + Tool Execution (right)
  • Live stats bar: state, elapsed time, message count, step progress, active model
  • Interactive input pane with key bindings (Tab, q, c, i, Esc)

Key file: src/cli/dashboard.ts

🧠 AirLLM Integration — 70B Models on 4GB RAM

Run 70B-parameter LLMs on commodity hardware via layer-wise inference:

  • Python sidecar server (airllm_server.py) wrapping models via OpenAI-compatible API
  • TypeScript bridge (src/llm/airllm-bridge.ts) with health checks and process management
  • LLM client factory (src/llm/factory.ts) for seamless backend switching
  • Backend selection prompt at startup (LM Studio vs AirLLM)
  • Configuration via .env: model, port, compression (none/4bit/8bit), max length

🐳 Docker Support

Production-ready containerization:

  • Multi-stage Dockerfile with Puppeteer + Chromium support
  • docker-compose.yml with volume mounts, host networking, and AirLLM sidecar port
  • .dockerignore for optimized builds
  • host.docker.internal for LM Studio communication from container

🔧 29 Registered Tools

Category Tools
Search web_search
Scrape scrape_page, extract_links, take_screenshot
Process transform, clean, extract_patterns, convert, summarize
File read_file, write_file, append_file, delete_file, list_dir, copy_file, move_file, file_exists, create_dir
Code generate_code, modify_code, scaffold_project, analyze_code
Recon recon (DNS, WHOIS, SSL, headers, tech stack, emails, socials, screenshot)
Vibe vibe (NL → running app pipeline)

📁 Architecture

theJoker/
├── src/
│   ├── index.ts                 # Entry point & CLI command registration
│   ├── agents/                  # Agent loop, planner, executor, memory, vibe-coder
│   ├── cli/                     # Terminal, dashboard, commands, display, progress, formatter
│   ├── llm/                     # LM Studio client, AirLLM bridge, factory, prompts, parser
│   ├── scraper/                 # Puppeteer browser, navigator, extractor, stealth
│   ├── tools/                   # Registry + search, scrape, recon, code, file, process tools
│   ├── project/                 # Scaffolder, builder, deployer, dev-server, packager
│   ├── coding/                  # Generator, analyzer, indexer, parser, templates, test-gen
│   ├── filesystem/              # Multi-file ops, tracker, watcher, operations
│   ├── errors/                  # Handler, retry, circuit-breaker
│   ├── utils/                   # Logger, config, cache, cleaner, links, validators
│   └── types/                   # TypeScript types and error types
├── tests/
│   ├── unit/                    # 22 test suites (980 tests)
│   └── integration/             # Workflow integration tests
├── airllm_server.py             # AirLLM Python sidecar
├── Dockerfile                   # Multi-stage Docker build
├── docker-compose.yml           # Compose with volumes & networking
├── DOCUMENTATION.md             # Full API reference (1,305 lines)
├── CONTRIBUTING.md              # Contribution guidelines (544 lines)
├── SECURITY.md                  # Security policy (288 lines)
└── LICENSE.md                   # TJCL v1.0 license

🧪 Test Coverage

Test Suite Tests File
Agent Executor 120+ tests/unit/agents/executor.test.ts
Agent Memory 80+ tests/unit/agents/memory.test.ts
LLM Parser 80+ tests/unit/llm/parser.test.ts
AirLLM Bridge 15 tests/unit/llm/airllm-bridge.test.ts
Code Analyzer 100+ tests/unit/coding/analyzer.test.ts
Code Generator 40+ tests/unit/coding/generator.test.ts
Code Indexer 60+ tests/unit/coding/indexer.test.ts
Code Parser 80+ tests/unit/coding/parser.test.ts
Templates 60+ tests/unit/coding/templates.test.ts
Test Generator 100+ tests/unit/coding/test-generator.test.ts
Circuit Breaker 70+ tests/unit/errors/circuit-breaker.test.ts
Error Handling 60+ tests/unit/errors/errors.test.ts
Retry Logic 60+ tests/unit/errors/retry.test.ts
Multi-File Ops 60+ tests/unit/filesystem/multi-file.test.ts
File Tracker 100+ tests/unit/filesystem/tracker.test.ts
File Watcher 50+ tests/unit/filesystem/watcher.test.ts
Project Builder 80+ tests/unit/project/builder.test.ts
Deployer 70+ tests/unit/project/deployer.test.ts
Packager 80+ tests/unit/project/packager.test.ts
Scaffolder 80+ `tests/unit/projec...
Read more
Loading

Experimental Build with Windows Setup

07 Mar 12:36
@ratna3 ratna3
v1.0.1
f5cbeac

Choose a tag to compare

View all tags
Experimental Build with Windows Setup Latest
Latest

🃏 The Joker Release: ENDj0K3R & Vibe Coding IDE (v1.0.0)

Welcome to the official release of The Joker! This release provides two powerful, AI-driven desktop applications built with Electron, React, and TypeScript.

Both applications are engineered to leverage local LLMs via LM Studio, ensuring your codebase, security logs, and conversations remain 100% local, private, and offline.

Below you will find the details for both .exe installers included in this release.

💻 1. The Joker - Vibe Coding IDE

A production-grade, AI-powered Desktop IDE built for "Vibe Coding." Simply describe what you want to build, and the application will scaffold, write, and debug the project for you.

✨ Key Features

  • Familiar VS Code-Style UI: A sleek, split-panel layout featuring a dynamic file explorer, Monaco-based code editor, and an integrated terminal.
  • Self-Correcting Autonomous Terminal: Powered by node-pty and xterm.js, the terminal does more than run commands. If an error occurs during a build or dependency installation, the AI automatically reads the terminal output, analyzes the stack trace, and applies the correct fix in real-time.
  • Persistent AI Copilot: A continuous chat interface that maintains context across your session, helping you generate code, explain files, and architect complex solutions.
  • Project Generation & Scaffolding: Describe your project, and the AI will automatically generate the directory structure, fetch and install the right dependencies (with intelligent fallbacks), and set up your environment.
  • Seamless Local AI: Connects directly to your local LM Studio instance via a built-in Setup Wizard. No API keys or cloud subscriptions needed.

Attached Asset: The_Joker_Vibe_Coding_IDE_Setup.exe

🕵️‍♂️ 2. The Joker - ENDj0K3R (Pentesting Edition)

A specialized build designed for security researchers and ethical hackers. It includes everything from the Vibe Coding IDE, but integrates a localized, TypeScript-native port of PentestGPT to act as your intelligent penetration testing co-pilot.

✨ Key Features

  • PentestGPT Architecture: Full feature parity with the core PentestGPT workflow, featuring dedicated Agent, Controller, and Session Management processes running locally.
  • Phase-Based Recon & Exploitation: The AI guides you through structured phases of a pentest (Information Gathering, Vulnerability Assessment, Exploitation, and Privilege Escalation) using specialized, battle-tested security prompts.
  • Automated Recon Tools: Features an integrated Web Scraping / Recon panel to quickly gather open-source intelligence and analyze target vectors.
  • Maximum Privacy: By routing all data through LM Studio, sensitive vulnerability data, payloads, and target environments are never sent to external APIs like OpenAI.
  • Ethical Guardrails: Features a mandatory, multi-checkbox Legal & Ethical verification modal to ensure responsible usage of the tool in authorized environments only.

Attached Asset: The_Joker_ENDj0K3R_Setup_1.0.0.exe

🚀 Installation & Setup

  1. Start LM Studio: Ensure you have LM Studio installed. Load your preferred model (e.g., Llama 3, Qwen, or Mistral) and click "Start Server" on the local server tab (usually http://localhost:1234).
  2. Download: Download the desired .exe installer from the Assets section below.
  3. Install: Run the setup executable and follow the standard Windows installation wizard.
  4. Connect: Upon launching the app, follow the Setup Wizard to connect to your LM Studio endpoint. Once the connection is verified, you are ready to begin!

⚖️ Legal & Ethical Disclaimer

The Joker - ENDj0K3R is intended strictly for educational purposes, authorized security auditing, and capture-the-flag (CTF) environments.
You MUST have written, explicit permission to test any target system. The developers assume no liability and are not responsible for any misuse, damage, or legal consequences caused by the utilization of this software.

Assets 4
Loading

v1.0.0

17 Feb 15:24
@ratna3 ratna3
v1.0.0
f5cbeac

Choose a tag to compare

View all tags
v1.0.0

🃏 The Joker v1.0.0 — Initial Release

An autonomous AI-powered terminal that understands natural language, scrapes the web intelligently, generates complete projects, and deploys applications.

Powered by LM Studio's AI models

✨ Highlights

  • 🧠 Agentic AI Core — Natural language understanding with autonomous task planning, execution, and self-correction
  • 🌐 Intelligent Web Scraping — Puppeteer-based scraping with stealth mode, anti-detection, and user-agent rotation
  • 📁 Project Generation — Create complete projects from natural language descriptions
  • 🚀 Deployment Automation — Docker, Kubernetes, and CI/CD pipeline support
  • 💾 Persistent Memory — Context-aware sessions with intelligent summarization
  • 🎨 Beautiful CLI — Rich terminal UI with progress indicators, banners, and formatted output
  • 🔄 Resilient Error Handling — Retry logic, circuit breakers, and graceful degradation

🏗️ Architecture

Module Description
cli/ Terminal interface, command handlers, output formatting, progress tracking
agents/ Agent loop, action planner, tool executor, session memory
llm/ LM Studio API client, prompt templates, response parsing, summarization
scraper/ Puppeteer browser management, stealth navigation, data extraction
tools/ Tool registry, web search, page scraping, data processing
coding/ Code generation and project scaffolding
project/ Project management utilities
filesystem/ File system operations
errors/ Error handler, retry logic, circuit breaker
utils/ Logger, config, cache, data cleaning, link validation

80%+ code coverage across 22 test suites

📦 Tech Stack

  • Language: TypeScript 5.9
  • Runtime: Node.js 20+
  • LLM: LM Studio (local inference)
  • Browser Automation: Puppeteer + puppeteer-extra + stealth plugin
  • HTTP: Axios
  • HTML Parsing: Cheerio
  • Logging: Winston
  • Testing: Jest + ts-jest
  • Linting: ESLint + Prettier

🚀 Getting Started

git clone https://github.com/ratna3/theJoker.git
cd theJoker
npm install
cp .env.example .env
npm run build
npm start

Make sure LM Studio is running with a compatible model before starting.

📄 License

Licensed under The Joker Contribution License (TJCL) v1.0 — view source ✅ | contribute ✅ | personal use ✅ | clone/fork ❌ | redistribute ❌ | commercial use ❌

Made with ❤️ by Ratna Kirti

# 🃏 The Joker v1.0.0 — Initial Release

An autonomous AI-powered terminal that understands natural language, scrapes the web intelligently, generates complete projects, and deploys applications.

Powered by LM Studio's AI models

✨ Highlights

  • 🧠 Agentic AI Core — Natural language understanding with autonomous task planning, execution, and self-correction
  • 🌐 Intelligent Web Scraping — Puppeteer-based scraping with stealth mode, anti-detection, and user-agent rotation
  • 📁 Project Generation — Create complete projects from natural language descriptions
  • 🚀 Deployment Automation — Docker, Kubernetes, and CI/CD pipeline support
  • 💾 Persistent Memory — Context-aware sessions with intelligent summarization
  • 🎨 Beautiful CLI — Rich terminal UI with progress indicators, banners, and formatted output
  • 🔄 Resilient Error Handling — Retry logic, circuit breakers, and graceful degradation

🏗️ Architecture

Module Description
cli/ Terminal interface, command handlers, output formatting, progress tracking
agents/ Agent loop, action planner, tool executor, session memory
llm/ LM Studio API client, prompt templates, response parsing, summarization
scraper/ Puppeteer browser management, stealth navigation, data extraction
tools/ Tool registry, web search, page scraping, data processing
coding/ Code generation and project scaffolding
project/ Project management utilities
filesystem/ File system operations
errors/ Error handler, retry logic, circuit breaker
utils/ Logger, config, cache, data cleaning, link validation

🔧 Built-in Tools

Tool Description
web_search Search the web via Google with configurable result count
scrape_page Scrape page content with CSS selectors, scroll loading, and wait conditions
extract_links Extract and filter all links from a page
process_data Process and structure scraped data

💻 Built-in Commands

Command Aliases Description
help h, ? Show available commands
clear cls, c Clear terminal
exit quit, q Exit The Joker
history hist Show command history
status stat Check LM Studio connection
agent — Run a query through the agent
memory mem Show agent memory stats
version ver, v Show version info

🧪 Testing

Suite Tests
Agent System 120+
LLM Integration 80+
Web Scraper 90+
Tools 100+
CLI 80+
Error Handling 70+
Project Management 100+
Utilities 150+
Total 966 ✅

80%+ code coverage across 22 test suites

📦 Tech Stack

  • Language: TypeScript 5.9
  • Runtime: Node.js 20+
  • LLM: LM Studio (local inference)
  • Browser Automation: Puppeteer + puppeteer-extra + stealth plugin
  • HTTP: Axios
  • HTML Parsing: Cheerio
  • Logging: Winston
  • Testing: Jest + ts-jest
  • Linting: ESLint + Prettier

🚀 Getting Started

git clone https://github.com/ratna3/theJoker.git
cd theJoker
npm install
cp .env.example .env
npm run build
npm start

Make sure LM Studio is running with a compatible model before starting.

📄 License

Licensed under The Joker Contribution License (TJCL) v1.0 — view source ✅ | contribute ✅ | personal use ✅ | clone/fork ❌ | redistribute ❌ | commercial use ❌

Made with ❤️ by [Ratna Kirti](https://github.com/ratna3)

Loading