Around 3 months ago, my partner and I were thinking why none of the iPhone apps running an LLM are built as a full harness (as in inference + agentic loop + context management + tools + MCP servers and etc.). It became more interesting when we noticed even the new Siri is not fully on device (and not available in EU anyways). Having built a few agentic products with custom harnesses before, we thought this shouldn't be that hard. well, we underestimated how "dumb" a 4B model can be, especially when it comes to tool calling. We used every trick we knew to make this model behave. It can now do actual useful work and it really is an on device, private, full agentic harness. That said, you can still connect your OpenRouter or OpenAI API keys if that's what you prefer. Please go check it out

Orvena

Private assistant on your phone with voice and MCP support

Private assistant on your phone with voice and MCP support