MyPhiloEngine
Run local LLMs without guessing what your hardware can run
2 followers
Run local LLMs without guessing what your hardware can run
2 followers
PhiloEngine checks your hardware and recommends a local LLM setup that will actually run. If a model does not fit, it automatically tries a smaller context, another runtime, or CPU fallback instead of crashing with an out-of-memory error. It also brings local and API models, AI agents with controlled file access, planning, web search, and memory into one free, self-hosted, open-source desktop app.
Free
Launch Team
AWS Startup AdvisorPersonalized AWS guidance that meets you where you’re already building
Promoted
Hey Product Hunt 👋
I'm David. PhiloEngine started as a side effect: I was trying to fine-tune a model myself and kept hitting the same wall no way to know upfront if a config would actually fit my hardware, so runs OOM'd halfway through or burned tokens on setups that were never going to work. Realized that gap isn't just my problem nobody's made this simple for people who aren't already deep in ML.
So the core of PhiloEngine is that layer: it checks your GPU/VRAM/RAM, proposes a context size and runtime that'll really load, and steps down gracefully instead of crashing saving compute and tokens instead of wasting them.
Fine-tuning made simple is actually next on the roadmap (not in the app yet, but that's where this is heading). Right now it also has local + API models, a bot system with scoped file access, planning mode for big tasks, web search, and memory all self-hosted, AGPL-3.0.
Alpha, built solo. Would love feedback, especially from macOS/Windows users since Linux gets the most testing from me. Ask me anything 🙂