grimvane.ai

Hearth

Your fire. Your conversation.

Self-hosted conversational AI. Backend-agnostic chat with model switching, session persistence, and automatic hardware detection. Your own ChatGPT, on your machine.

Architecture

Chat meets inference.

Hearth separates conversation from computation. The interface handles sessions and rendering. The backend handles tokens. Switch models mid-conversation without losing context.

LAYER HANDLES Interface (TUI / Web) Sessions, rendering, input Router (model switching) Backend detection, fallback Backend (inference) Crucible, llama.cpp, MLX Memory (persistence) Dahlia (session storage)

Capabilities

What Hearth does.

Conversational AI without the subscription.

Model Switching

Mid-conversation

Start with a fast model for brainstorming, switch to a larger one for deeper reasoning. Context carries over.

Hot-swap Context Carry

Session Persistence

Pick Up Where You Left Off

Conversations stored locally via Dahlia. Resume any session. Search across past conversations by content.

Dahlia Local Storage

Hardware Detection

Automatic Backend

Detects available GPUs and selects the right inference backend. Apple Silicon gets MLX, NVIDIA gets CUDA, CPU gets llama.cpp.

MLX CUDA CPU

Backend Agnostic

Any Engine

Crucible, llama.cpp, MLX, or frontier APIs via Pilot. Same interface regardless of what runs underneath.

Crucible llama.cpp MLX

System Prompts

Persona Library

Define reusable system prompts. Switch personas per conversation or per message. Store and version them locally.

Personas Templates

Fully Offline

Zero Cloud

No accounts. No API keys. No telemetry. No data leaves your machine. Every conversation stays on your hardware.

Private Local-only

Get started

Light the fire.

# Install Hearth pip install grimvane-hearth # Start chatting (auto-detects backend) hearth # Or specify a model hearth --model llama-3.2-3b # Resume a previous session hearth --resume last