- Add x-hermes-worker YAML anchor template in compose.yml
(CPU-only workers, no GPU passthrough, OpenCode Go provider)
- Add commented worker example with env vars placeholder
- Create scripts/provision-hermes-worker.sh for automated worker
provisioning (generates port, API key, volume dir, appends service)
- Workers connect to Discord only, isolated per container
- Volumes under /mnt/HoardingCow_docker_data/Hermes/<name>/
- Switch Dockerfile to clone from gortium/hermes-agent (Gitea fork)
- Add SSH agent forwarding for private repo clone at build time
- Set CHROME_EXECUTABLE for Playwright Chromium
- Remove patch_tts_tool.py (Piper patch now in fork source)
- Enable Gitea Actions in versioncontrol compose
- Add ollama/Dockerfile that builds ollama from source with AMDGPU_TARGETS=gfx906
- Uses ROCm 6.1 (rocm/dev-ubuntu-22.04:6.1.2-complete) for MI50 support
- Builds llama.cpp runner with HIPBLAS for gfx906 architecture
- Updates compose.yml to build from this Dockerfile instead of pulling ollama/ollama:latest