AndlerRL

AndlerRL/ollama-portable

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

0 stars 0 forks 0 watchers Shell MIT License

amd apple-silicon backup bash cpu-only devops docker gpu inference llm monitoring nvidia ollama open-webui portable taskfile

17 Open Issues Need Help Last updated: Jul 21, 2026

Open Issues Need Help

View All on GitHub

bug: Taskfile backup task doesn't forward --tag flag about 2 hours ago

bug good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

bug: run.sh uses docker exec -it unconditionally, fails in non-TTY contexts about 2 hours ago

bug good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: add --dry-run flag to backup.sh about 2 hours ago

enhancement good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

performance: add model quantization recommendations to README about 2 hours ago

documentation good first issue performance

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

security: .env file should never be committed — add pre-commit hook about 2 hours ago

good first issue security

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

docs: add CODE_OF_CONDUCT.md about 2 hours ago

documentation good first issue

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

docs: add CONTRIBUTING.md with development setup and guidelines about 2 hours ago

documentation good first issue

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: add theme toggle to Rust TUI about 2 hours ago

enhancement good first issue rust-tui

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: add model size and parameter count to list.sh output about 2 hours ago

enhancement good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: add shellcheck linting to CI about 2 hours ago

enhancement good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

bug: status.sh uses curl which may not be available on all systems about 2 hours ago

bug good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

bug: backup.sh and restore.sh fail on macOS due to Docker Desktop volume mount paths about 2 hours ago

bug good first issue scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: add multi-server dashboard support about 2 hours ago

enhancement help wanted monitoring

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: add Grafana/Prometheus metrics export endpoint about 2 hours ago

enhancement help wanted monitoring

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: implement bollard streaming stats API in Rust TUI about 2 hours ago

enhancement help wanted rust-tui

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

enhancement: organize scripts into subdirectories about 2 hours ago

enhancement help wanted scripts

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile

bug: session JSON field name mismatch between record.sh and sessions.sh about 2 hours ago

bug good first issue

AndlerRL/ollama-portable

0

Portable Ollama inference server in Docker. Auto-detects NVIDIA/AMD/Apple Silicon/CPU-only hardware. Includes Open WebUI with pre-cached embeddings, live TUI monitoring, session recording with peak analysis, and automatic backup/restore on destructive commands. Pure bash, zero Python dependencies.

Shell

#amd#apple-silicon#backup#bash#cpu-only#devops#docker#gpu#inference#llm#monitoring#nvidia#ollama#open-webui#portable#taskfile