Chat
ARCA CORE

Your private intelligence.

Arca starts its local brain automatically. Attach documents and speak directly from Chat.

Starting local brain...
A
Arca Core v0.3.8 is ready. Ask a question or attach a document.CORE SYSTEM
Core routing: browser brain -> QVAC -> optional cloud

Connections

Arca Core can switch model providers without changing the rest of Arca.

BB Browser Brain

Runs an open-source model directly in this browser.

Checking
QL QVAC Local

OpenAI-compatible local endpoint for installed QVAC.

Optional
CL Cloud AI

Optional fallback provider for harder tasks.

Not configured
DF Document RAG

Local parsing, chunking and retrieval.

Ready
WP WordPress

Diagnostics and approved actions through Core tools.

Next
WS Website / Server

Health, logs and diagnostics through Core tools.

Next

Settings

Brain, model routing and optional fallback settings live here. The Browser Brain auto-starts when Arca opens.

CORE

Local Brain

Runs on this device with WebGPU. Model cache: IndexedDB.

Auto-start pending...

Local model

Core routing

...WEBGPU
OFFBRAIN
0MEMORY TURNS
0ATTACHMENTS
On first use, auto-start may download the local model. Later starts use the browser's IndexedDB cache.

Fallback engines

QVAC/local endpoint

QVAC model alias

Cloud API base URL

Cloud model

Cloud API key (session only)

Document context characters

Memory turns