Your Own AI v0.1.0-beta.15

Your Own AI v0.1.0-beta.15

Private AI on your own machine - offline by default, online only when you choose.

Added

• A "Reading ..." notice appears the moment any file is attached, so a
  large document never looks like nothing happened while it's read in.

Changed

• The signed-export dialogs (Export AI and knowledge packs) now know
  whether Flowsta Vault is installed and unlocked, and guide you to the
  right next step for each case - including a direct link to get the
  Vault when it isn't installed. Exporting unsigned is always available.

Downloads

See assets below for platform-specific installers. Verify any download against SHA256SUMS.txt.

Your Own AI v0.1.0-beta.14

Your Own AI v0.1.0-beta.14

Private AI on your own machine - offline by default, online only when you choose.

Fixed

• The monthly-allowance and sign-in notices now appear as proper cards in
  normal chat as well - the last remaining path that printed the raw error
  into the reply.

Downloads

See assets below for platform-specific installers. Verify any download against SHA256SUMS.txt.

llama.cpp b9637 - GPU Accelerated Binaries

Static llama-server binaries compiled from llama.cpp b9637

Built for:

• Linux x86_64 (Vulkan GPU + CPU fallback)
• macOS Apple Silicon (Metal GPU)
• macOS Intel (CPU only)
• Windows x64 (Vulkan GPU + CPU fallback)

GPU Support:

• Linux & Windows: Vulkan — works with NVIDIA, AMD, and Intel GPUs
• macOS ARM: Metal — native Apple Silicon acceleration
• macOS Intel: CPU only (no GPU acceleration)
• All platforms fall back to CPU if no compatible GPU is found

Optional CUDA engine (llama-server-cuda-*.zip):

• Faster generation on NVIDIA GPUs, CUDA runtime included (Linux: CUDA 12.2, drivers R525+; Windows: CUDA 12.9, drivers R560+)
• Downloaded on demand from Settings — never bundled in installers

Configuration:

• WebUI excluded (-DLLAMA_SERVER_WEBUI=OFF)
• No CURL dependency (-DLLAMA_CURL=OFF)

Built on: $(date -u)