 shawn
|
2b7a8290a5
|
feat: add Windows-MCP UI automation + full offline deps
- New start-windows-mcp.bat — starts Windows-MCP SSE server on :8000
- Windows-MCP auto-starts when Hermes CLI launches (options 1/2)
- Pre-downloaded wheels: hermes-agent (47), windows-mcp (95)
- Offline Python 3.13 embedded + get-pip.py bootstrapper
- Hermes config wired with mcp_servers.windows-mcp
- Updated Makefile with targets: wheels-hermes, wheels-windows-mcp,
python-portable, get-pip, deps
- Recreated: run-hermes.ps1, start-hermes-dashboard.bat
- Pure ASCII .bat files with CRLF line endings
|
2026-07-11 18:11:06 -04:00 |
|
|
shawn
|
4e0ab94ee2
|
feat: GPU detection for LLM server (NVIDIA/AMD/Intel/Vulkan + CPU fallback)
- Added start-llama-server.bat with cross-brand GPU auto-detection:
* Detection 1: nvidia-smi for NVIDIA
* Detection 2: WMIC for AMD, Intel Arc, Intel HD/Iris/UHD
* Detection 3: vulkaninfo as final fallback probe
* Falls back to CPU-only build when no GPU found
- Downloaded llama-server b9947 builds:
* Vulkan build (91 MB) - supports all GPU brands
* CPU build (45 MB) - fallback in cpu/ subdir
- Downloaded Qwen2.5-Coder-1.5B Q4_K_M model (1.1 GB)
- Fixed run-hermes.bat polling: replaces fixed 5s timeout with
curl-based readiness polling (up to 30 attempts, 1s apart)
- All .bat files verified: ASCII text, CRLF line terminators
- Added .gitignore for build artifacts and large binaries
|
2026-07-10 00:58:56 -04:00 |
|