v0.4

🚀 Big Release Alert: Full-Stack Web Agent Are Live! 🌐

We’re thrilled to announce a major milestone for the Intelligent Internet Agent project! Say hello to v0.4, packed with powerful new features, integrations, and real-world full-stack demos. This is our biggest release yet!

---

🔧 New Features – Full-Stack Web Agent Showcases

Experience the magic of autonomous full-stack development:

• 🌟 Live Showcases → View on GitHub
• ⚙️ Parallel Shell Execution: Enhanced tooling via Tmux sessions – agents can now access and execute multiple shell sessions
• 🧠 AI + DB + Web Integration: Native support for NeonDB and Vercel for website deployment
• 📦 Sandbox Deployments: Easily deploy full-stack apps in Docker or E2B environments

II-Agent.Node.Media.Generator.1.mp4

II-Agent.Crypto.Analysis.1.mp4

---

👥 New Contributors

• 🎉 @SK1989sL made their first contribution in #140
• 🎉 @Fried-Squid made their first contribution in #135

---

📜 Full Changelog

Compare v0.3...v0.4 →

v0.3

Release v0.3 - Simplified Setup & Enhanced Experience

We've made significant improvements to make ii-agent easier to set up and use, while adding powerful new features for a better AI agent experience.

🚀 Easier Setup

• Streamlined Configuration: Simplified settings dialog with intuitive options that make initial setup much faster
• Removed Complex Dependencies: Eliminated the need for Anthropic base URL configuration, reducing setup complexity
• Better Default Settings: Intelligent defaults that work out of the box for most users

✨ Enhanced User Experience

• Visual Input Support: You can now paste images directly into the chat input for seamless multimodal conversations
• Improved Chat Performance: Significant database optimizations deliver faster response times and smoother interactions
• Better Message Handling: Fixed duplicate message issues and improved real-time chat reliability with enhanced WebSocket implementation

🔧 New Capabilities

• Reviewer Agent: Added intelligent review capabilities to help validate and improve AI responses
• Async Tool Support: Enhanced tool execution with asynchronous processing for better performance
• Chat Replay: Ability to replay and analyze previous conversations

🎨 Polish & Refinements

• Updated Typography: Refreshed font choices for better readability and modern appearance
• Bug Fixes: Resolved various frontend issues and missing function errors

This release focuses on removing friction from the setup process while delivering a more robust and feature-rich AI agent platform. Getting started with ii-agent is now simpler than ever!

Full Changelog: v0.2...v0.3

v0.2

🛠 ii-agent v0.2 Release Notes

We’re excited to announce the v0.2 release of the ii-agent! This update brings major feature upgrades, critical bug fixes, improved tooling, and support for more powerful LLM backends such as Gemini-2.5-pro. Here's what’s new:

🚀 What's Changed

✨ New Features

• Prompt Enhancements & User Controls
  • Improved prompt generation logic and message handling.
  • Users can now cancel or edit prompts during interactions.
• Tooling Enhancements
  • Introduced Message Tool and Return Control Tool for better user-agent interaction.
  • Added new Slide Deck Completion Tool with enhanced image usage.
  • Support for long video generation and Google Drive integration.
  • Added settings tool for easier runtime control.
• Model & Backend Support
  • Default model updated to Claude Sonnet 4.
  • Added support for:
    • Gemini 2.5 Pro
    • Anthropic interleaved thinking
    • OpenAI Azure endpoints
    • Local LLMs via LMStudio (OpenAI-compatible API)

🐛 Fixes & Refinements

• Resolved prompt looping in history runs.
• Improved error handling in tools like BrowserPressKeyTool.
• Addressed frontend bugs in message state and Docker persistence.
• Simplified the Slide Deck Tool and removed redundant logic in history initialization.
• Reduced token usage in message output to optimize performance.

🧹 Code Cleanup & Refactors

• Refactored global styles and frontend logic for better maintainability.
• Replaced context managers and enhanced internal messaging workflows.

📦 DevOps & Infrastructure

• Dockerized the entire project for seamless deployment.
• Fixed Docker-related issues with yarn and event DB persistence.

👥 New Contributors

• 🎉 @GokuDoku made their first contribution with local LLM support: #72

📈 Full Changelog

Compare the full diff here: v0.1...v0.2

Release v0.1: II-Agent

II-Agent: a new open-source framework to build and deploy intelligent agents

🚀 Overview

II-Agent is a powerful open-source autonomous assistant designed to streamline workflows across research, content generation, software development, data analysis, and automation. Built around the advanced reasoning capabilities of Claude 3.7 Sonnet, II-Agent offers a transparent and extensible alternative to proprietary agents like Manus and GenSpark.

This release introduces a production-level performing, modular system capable of multi-step reasoning, tool-based execution, and real-time interaction.

---

🧠 Core Features

• Structured Reasoning Engine

  • Multistep planning, hypothesis formation, and reflection
  • Explicit “thought” logging for debugging and transparency

• Tool-Integrated Execution

  • 🗂 File system editing with intelligent formatting
  • 💻 Shell command execution via persistent shell
  • 🌐 Web search and automation browsing (Tavily, SerpAPI, FireCrawl, Playwright)
  • 🧾 PDF parsing (pymupdf)
  • 🗣 Audio transcription & speech synthesis (OpenAI on Azure)
  • 🖼 Image generation (Imagen 3)
  • 🎞 Video generation (Veo 2)

• Browser Automation

  • Tab control, form filling, screenshot capture
  • Visual understanding via Claude Sonnet 3.7 or GPT-4o

• Context Management

  • Token usage estimation and strategic truncation
  • File-based archival for large content

• Real-Time Communication

  • WebSocket-based live interaction
  • Session isolation and file uploads