Beyond Better 0.12.1

Latest Release - Available Now

🚀 Application Downloads

🪟Windows

Windows Installer (MSI)
BB-app-0.12.1-windows-x64.msi
10.0 MB
Download
Windows Installer (Setup)
BB-app-0.12.1-windows-x64-setup.exe
7.2 MB
Download

🍎macOS

macOS Application (Universal DMG)
BB-app-0.12.1-macos-universal.dmg
16.9 MB
Download
macOS Application (Universal Tarball)
BB-app-0.12.1-macos-universal.app.tar.gz
16.6 MB
Download

🐧Linux

Linux Application (AppImage)
BB-app-0.12.1-linux-x64.AppImage
91.0 MB
Download

⚙️ Server Components

Server components are automatically installed by the application. Manual installation is available for advanced users.

Server Components (Linux x64 - zip)
bb-x86_64-unknown-linux-gnu-v0.12.1.zip
Download
Server Components (Linux x64 - tarball)
bb-x86_64-unknown-linux-gnu-v0.12.1.tar.gz
Download
Server Components (Linux ARM64 - zip)
bb-aarch64-unknown-linux-gnu-v0.12.1.zip
Download
Server Components (Linux ARM64 - tarball)
bb-aarch64-unknown-linux-gnu-v0.12.1.tar.gz
Download
Server Components (Windows x64)
bb-x86_64-pc-windows-msvc-v0.12.1.zip
Download
Server Components (macOS Intel - zip)
bb-x86_64-apple-darwin-v0.12.1.zip
Download
Server Components (macOS Intel - tarball)
bb-x86_64-apple-darwin-v0.12.1.tar.gz
Download
Server Components (macOS Apple Silicon - zip)
bb-aarch64-apple-darwin-v0.12.1.zip
Download
Server Components (macOS Apple Silicon - tarball)
bb-aarch64-apple-darwin-v0.12.1.tar.gz
Download

📝 Release Notes

Added

  • support for ChatGPT 5.6
  • support for DeepSeek 4
  • support for Grok 4.6
  • organization scoped dynamic model discovery
  • support OpenRouter as LLM provider
  • model selection for for providers with dynamic model discovery
  • copy model ID from model system card
  • support caching and context compaction for Grok models
  • browsable API docs (using Swagger UI)

Changed

  • LWB uses Happy Eyeballs dual-stack connection racing
  • added support for additionalPaths to LWB
  • switch to Responses API for ChatGPT models
  • switch to Responses API for Grok models
  • pooled instances for fetchManager (webpages and screenshots)
  • explicit provider for model ID
  • organization scoped model registry
  • updated ingestion endpoint to accept collaborationConfig
  • report config validation errors for data sources

Fixed

  • ensure hydrated Supabase session for service accounts
  • auth calls for LWB pairing
  • safe updates for LWB connections
  • LWB auth checks against agent user
  • avoid onboarding for ‘special’ user accounts
  • database string collation
  • high CPU load in LWB
  • exposure of provider API keys in browser
  • Ollama Cloud model discovery
  • including background and resources for delegated agent tasks
  • sticky sessions for prompt caching for OpenAI models
  • grouping of auxiliary log entries for agent tasks
  • separation of parent vs related log entries
  • model selection for delegated agent tasks
  • auth error handling for llm-proxy requests
  • prevent fatal error when config validation fails for data sources