Release notes from browser-operator-core

v0.6.0

2025-12-11T06:41:29Z

Browser Operator Core v0.6.0 Release Notes

🎯 Highlights

Browser Operator Core v0.6.0 introduces persistent user memory and universal LLM compatibility, transforming AI agents from stateless assistants into intelligent partners that remember, learn, and adapt across sessions.

✨ New Features

Cognitive Memory System

Persistent Agent Memory: AI agents now remember key information across sessions, building accumulated knowledge over time
Automatic Memory Extraction: Important details automatically captured and indexed from conversations
Searchable Memory Blocks: Natural language search across all stored memories
Memory Management UI: Full control over what agents remember with privacy-first design

Browser.Operator.Memory.mp4

Universal LLM Platform

7+ Provider Support: Native integration with Cerebras, Anthropic, Google AI, OpenAI, and any OpenAI-compatible endpoints
Custom Provider Registration: Connect to internal LLMs, Ollama, vLLM, or any compatible API
Dynamic Model Discovery: Automatically detect and list available models per provider

Browser.Operator.Custom.Provider.mp4

Conversation Intelligence

Persistent History: All conversations automatically saved with IndexedDB backend
Quick Resume: Continue any previous conversation with full context

Streamlined User Experience

Multi-Step Onboarding: Guided setup wizard for initial configuration
Panel Visibility Controls: Hide/show DevTools UI panels

What's Changed

Fix the agent runner bug by @tysonthomas9 in #67
Cleanup eval-server and renamed to agent-server by @olesho in #62
fix LiteLLM model issue by @tysonthomas9 in #68
Added OpenAI compatible "input" field support in /v1/responses API by @olesho in #69
Refactored Settings UI by @olesho in #65
Feat/eval js by @olesho in #70
Feat/capture iframes by @olesho in #72
Add support for more providers and conversation history by @tysonthomas9 in #71
Memory and Onboarding Updates by @tysonthomas9 in #76
Add ability to show or hide other panels by @tysonthomas9 in #77

Full Changelog: v0.5.0...v0.6.0

v0.5.0

2025-11-12T15:48:10Z

Browser Operator v0.5.0 Release Notes

This release introduces visual intelligence overlays, comprehensive session management, and structured workflow orchestration - transforming AI agents from black boxes into auditable, manageable business tools.

Key Capabilities

Visual Intelligence Layer

Real-Time Progress Tracking: Live visualization of multi-step workflows with completion status
Guided Workflows: Interactive overlays guide users through AI-assisted processes

Intelligent Task Orchestration

Built-in TODO Management: Hierarchical task tracking for multi-step workflows
Progress Monitoring: Track completion of complex, multi-step operations

Enhanced File Management

File Browser Interface: Navigate and manage all generated documents
Syntax-Highlighted Viewer: Preview code, reports, and documents in-browser
Export Pipeline: Streamlined artifact extraction for downstream systems

What's Changed

Fix Config Propagation in Automated Mode by @olesho in #61
Add Browser Operator Provider and improvements by @tysonthomas9 in #66

Full Changelog: v0.4.0...v0.5.0

v0.4.0

2025-10-14T19:46:03Z

Browser Operator Core v0.4.0 Release Notes

Browser Operator Core v0.4.0 represents a transformative leap in AI agent capabilities. By introducing a virtual file system and web rendering engine, agents can now handle complex, multi-step workflows that were previously impossible. Agents can manage their own temporary state across long-running tasks, generate rich interactive content like reports and presentations, and create learning materials such as interactive flashcards - all within the browser environment.

✨ New Features

Extended Agent Intelligence & Persistence

Stateful Long-Running Tasks: Agents can now use the file system to maintain context and temporary states across extended workflows, breaking through previous memory limitations
Complex Task Orchestration: Multi-step processes that require intermediate data storage and retrieval are now possible
Persistent Working Memory: Agents can save, retrieve, and update information throughout lengthy operations without losing context

Virtual File System & Web Asset Management

In-Browser File Storage: New virtual file system enables creation, storage, and management of code files directly in the browser using IndexedDB
Session-Scoped Storage: Files are properly isolated per DevTools session, ensuring clean workspace separation
8 New Development Tools:
- Create, read, update, and delete files
- List and check file existence
- Render web applications in sandboxed iframes
- Retrieve form data and user interactions from rendered apps

Web Application Rendering

Live Preview Capability: Instantly render HTML/CSS/JavaScript applications within isolated iframes
Interactive Reports: Agents can generate full HTML/CSS/JavaScript reports with charts, graphs, and interactive elements
Dynamic Presentations: Create slide decks and presentation materials that can be viewed and navigated in real-time
Sandboxed Execution: Secure iframe implementation with proper content isolation
Data Retrieval: Automated collection of user interactions and form submissions from rendered applications

Browser.OperatorWebApp.mp4

Development Infrastructure

Dockerized Evaluation Server: New local Docker setup for simplified testing and evaluation workflows
Improved Development Environment: Streamlined setup process for contributors
Better Isolation: Container-based approach ensures consistent behavior across different development machines

🔗 Links

[Full Changelog](v0.3.4...v0.4.0)
[Pull Request #55](#55) - Web Asset Rendering & Virtual File System
[Pull Request #52](#52) - Docker Evaluation Server

Browser Operator Core continues to evolve as a powerful general AI agent platform. We're excited about the possibilities these new features unlock and look forward to your feedback!

v0.3.4

2025-09-22T07:13:10Z

🎉 Major Update: Specialized Search Agent & MCP Enhancement

✨ New Features

Introducing the Specialized Search Agent
A powerful new agent designed for deep research and discovery tasks that regular search can't handle.

What It Does:

Finds niche professional lists (content writers, VC partners, industry experts)
Aggregates data from multiple sources automatically
Builds comprehensive databases from scattered information
Navigates through LinkedIn, directories, and professional networks

Example Use Cases:

"Find all Series A venture partners in Silicon Valley focused on AI"
"Create a list of technical content writers with SaaS experience"
"Compile contact information for sustainability consultants in Europe"
"Find all podcast hosts in the crypto/web3 space"Introducing the Specialized Search Agent
A powerful new agent designed for deep research and discovery tasks that regular search can't handle.

MCP Connectors Catalog

Browse and discover available MCP connectors in one place
Add, enable, and configure connectors with one click OAuth login.

AI-Powered Tool Selection

LLM automatically selects the best tools for your task
Expanded agent capabilities with Search, Web Task, and Action variants

🔧 Improvements

Rock-Solid MCP Connections

Automatic retry logic for failed connections
Real-time connection status updates
Improved tool naming and resolution
Better error handling and recovery

MCPOAuthExample2.-.SD.480p.mov

What's Changed

MCP OAuth Support and more updates by @tysonthomas9 in #51

Full Changelog: v0.3.3...v0.3.4

v0.3.3

2025-09-13T22:55:31Z

What's New

Model Context Protocol (MCP) Support

Added support for initial MCP implementation
Improved integration capabilities with external tools

Enhanced Agent Framework

Updated agent architecture for better performance
Improved reliability and extensibility of agent

🐛 Bug Fixes

OpenRouter OAuth: Fixed authentication issues with OpenRouter
Model Configuration: Resolved model selection and refresh problems

MCP_Small.mp4

What's Changed

Update agent framework structure by @tysonthomas9 in #43
Fix the model config issue, OpenRouter Oauth issue and model refresh … by @tysonthomas9 in #45
Feat/automation build by @olesho in #48
Add initial MCP version with SDK imports by @tysonthomas9 in #44
fix: build issue with latest main merge by @tysonthomas9 in #49

Full Changelog: v0.3.2...v0.3.3

v0.3.2

2025-08-30T00:35:49Z

Release Notes

🚀 New Features

🪟 Windows Support

Native Windows 10/11 builds now available
Easy installation with MSI installer

🔌 Browser Agent API

Control Browser Operator programmatically via REST API
Integrate browser agent into your applications

🐳 Docker Support

Run Browser Operator in containers
Perfect for CI/CD and cloud deployments
Headless automation at scale

This release establishes Browser Operator as a universal web agent platform. You can now integrate via API, deploy with Docker, and run natively on Windows.

What's Changed

Add Claude Code GitHub Workflow by @tysonthomas9 in #36
Feat/evals ready by @olesho in #37
Extended tracing to all tool calls by @olesho in #38
Dockerize devtools frontend by @olesho in #39
Add Docker configuration and documentation by @olesho in #40

Full Changelog: v0.3.1...v0.3.2

v0.3.1

2025-08-08T23:24:09Z

🚀 GPT-5 Support Now Available!

🧠 What's New

Full support for OpenAI's GPT-5 model
Automatic detection for existing OpenAI API users
Seamless model switching in the UI

v0.3.0

2025-08-07T15:15:02Z

🎯 Major Release: Enhanced Intelligence & Observability

🔔 Version Management

Automated Update Notifications

Stay current with automatic version checking
Get notified when new releases are available
Direct GitHub release integration for seamless updates
Never miss important features or security patches

🎨 UI/UX Enhancements

Redesigned AI Chat Panel

Streamlined model selection interface
Modern, responsive styling
Improved conversation flow and readability

🧠 New Agent Capabilities

Thinking Tools 💭

High-level strategic planning for complex tasks
Sequential reasoning for multi-step operations
Improved decision-making capabilities
More human-like problem-solving approach

Intelligent Wait Tool ⏱️

Smart waiting for dynamic content
Content analysis to determine optimal wait times
Handles modern JavaScript-heavy applications
Reduces timeout errors and improves reliability

Robust Error Handling 🛡️

Comprehensive error recovery mechanisms
Intelligent retry logic with exponential backoff
Graceful degradation for partial failures
Detailed error reporting for debugging

🔍 Advanced Observability

Hierarchical Distributed Tracing

Deep visibility into agent execution flows
Track actions across complex automation sequences
Identify bottlenecks and optimize performance
Debug issues with comprehensive execution traces

💡 What This Means For You

Better Reliability: Visual verification and smart waiting reduce automation failures
Easier Debugging: Hierarchical tracing shows exactly what your agent is doing
Smarter Agents: New thinking tools enable more complex automation scenarios
Professional Polish: UI improvements and accessibility make the tool enterprise-ready

This release represents a significant step forward in making Browser Operator more intelligent, observable, and reliable. We're committed to building the most powerful browser platform available.

v0.2.1

2025-07-26T01:17:02Z

🚀 What's New

One-Click Setup with OpenRouter

Streamlined integration with OpenRouter model provider
Simplified configuration process - get up and running in seconds
No more manual API endpoint configuration required
Automatic model discovery and selection

Default Model Configuration

Pre-configured optimal models for each supported provider
Intelligent defaults based on provider capabilities
Reduces setup friction for new users
Still fully customizable for advanced users

These improvements are part of our ongoing commitment to making Browser Operator more accessible while maintaining the power and flexibility our users expect.

OpenRouterConnectDemo.mp4

v0.2.0

2025-07-10T03:44:21Z

🚀 What's New

🤖 Expanded LLM Provider Support

Added OpenRouter integration - Access a diverse marketplace of AI models through a single API, giving you flexibility to choose the best model for your specific use case
Added Groq support - Leverage Groq's ultra-fast inference for real-time AI interactions and reduced latency in your workflows

🌐 Web Agent for Task Delegation

Introducing our new Web Agent capability that can autonomously handle delegated web tasks
Seamlessly delegate complex web interactions while maintaining control and visibility
Perfect for automating repetitive browsing tasks and multi-step web workflows

📊 Enhanced Observability with Langfuse

Tracing integration with Langfuse (contributed by @olesho)
Monitor and debug your AI agent interactions with detailed execution traces
Gain insights into agent behavior, performance metrics, and decision paths

💾 Vector Database Integration

Website snapshot storage - Automatically save and index website snapshots in VectorDB for future reference
Semantic document search - Powerful semantic search capabilities across your stored documents and web content
Build a searchable knowledge base from your browsing sessions

🛠️ Platform Improvements

Universal Mac builds - Full compatibility with both ARM (Apple Silicon) and x86 architectures
Numerous enhancements and bug fixes for improved stability and performance

OpenRouter.Demo.mp4

GroqDemo.mp4

Full Changelog: v0.1.5...v0.2.0