HuLa

TextGen provides portable desktop builds and a web interface for loading local models, including GGUF files, and using them for chat, vision, document questions, and free-form generation. It can switch among several inference backends and expose OpenAI- and Anthropic-compatible endpoints with tool calling and MCP support. Core use can remain fully offline with no telemetry, while training, additional backends, image generation, and some extensions require the full installation.

Meetily records and transcribes meetings on your device, keeping recordings, transcripts, and transcription models local for privacy-sensitive work. Summaries can stay fully local through Ollama or use Claude, Groq, OpenRouter, or a custom OpenAI-compatible endpoint. Installers are available for macOS and Windows, while Linux users build from source.

Mailspring brings a unified inbox, snoozing, send later, rules, and templates into a desktop client for macOS, Windows, and Linux. Email credentials are not sent to the cloud. Link tracking, read receipts, mailbox analytics, and contact or company profiles are reserved for the paid Pro subscription.

Hermes Desktop provides a streaming chat workspace and guides first-time users through either installing Hermes locally or connecting to a remote Hermes API server. The same interface manages sessions, profiles, skills, model providers, memory, tools, and scheduled jobs, making Hermes usable without staying in the command line.