All activity
im.ai is a small chat app for iOS and macOS. It runs local models (Llama, Gemma, Qwen) on-device via llama.cpp, and can also connect to Google, Groq, OpenRouter, Cerebras, and GitHub Models using your own API keys. No accounts, no relay, no servers in the path. API keys live in the system Keychain. It's an early project — feedback welcome.
im.aiLocal LLMs and your own API keys, in one small app
Dmitry “Leo” Kuznetsovleft a comment
Hi everyone — maker here. im.ai is a side project I've been working on to scratch my own itch: I wanted a single chat app that could run local models offline (via llama.cpp) and also let me bring my own API keys for cloud providers, without any account, login, or middleman server. It's still early. There's no telemetry, no sign-in, and API keys stay in the Keychain. macOS supports Apple Silicon...
im.aiLocal LLMs and your own API keys, in one small app