Hey Product Hunt 👋 I built PeaBox AI Workbench because I kept running into the same problem: I was using more and more AI models, but each one lived in a different application. I might use Ollama locally for one task, a remote Ollama server for another, Claude or OpenAI for something else, and Gemini, Groq or OpenRouter when experimenting. PeaBox is my attempt to bring those environments together. v4 is an important step because it starts feeling less like a provider configuration tool and more like an actual AI workspace. You can configure providers separately, switch between local and cloud models, keep conversations, work with files and images, and use the model that makes sense for the task. I'm particularly interested in building PeaBox around three principles: 1. Local-first when possible, and connect via SSH instead of using APIs using self-hosted models completely free without any limits on tokens. 2. Provider-independent 3. Practical rather than AI for AI's sake I'd love feedback, especially from people who regularly switch between local models and cloud LLMs. Thanks for checking it out!

PeaBox AI Workbench

One workspace for local, remote, and cloud AI models

One workspace for local, remote, and cloud AI models