Harbor

by harbor

Free Download 1 Visit Website

Versions:

  • 0.4.5
  • 0.4.4
  • 0.4.1
  • 0.3.41
  • 0.3.40
  • 0.3.39
  • 0.3.38
  • 0.3.37
  • 0.3.35
  • 0.3.34
  • 0.3.33
  • 0.3.30
  • 0.3.29
  • 0.3.28
  • 0.3.26
  • 0.3.25
  • 0.3.24
  • 0.3.23
  • 0.3.22
  • 0.3.21
  • 0.3.20
  • 0.3.19
  • 0.3.18
  • 0.3.16
  • 0.3.12
  • 0.3.11
  • 0.3.10
  • 0.3.9
  • 0.3.8
  • 0.3.7
  • 0.3.6
  • 0.3.5
  • 0.3.4
  • 0.3.3
  • 0.3.2
  • 0.3.1
  • 0.3.0
  • 0.2.28
  • 0.2.27
  • 0.2.26

Harbor 0.4.5 is a containerized large-language-model toolkit that streamlines the deployment, orchestration and day-to-day management of entire LLM stacks—backends, APIs, front-ends and auxiliary services—through a single CLI command and an optional graphical companion application. Aimed at developers, data scientists and DevOps teams who need repeatable, portable AI environments, the software wraps models, runtimes and dependencies into lightweight containers that can be spun up locally or on remote hosts without manual configuration of CUDA drivers, Python virtual environments or service mesh rules. Typical use cases include spinning up a private ChatGPT-like interface for internal testing, serving an embedding endpoint behind a REST gateway, chaining multiple models for retrieval-augmented generation, or benchmarking new quantized weights against existing production pipelines. Harbor’s CLI discovers available models from registries such as Hugging Face, pulls the correct image layers, exposes ports, mounts volumes and injects environment variables automatically, while the companion app provides a dashboard for start-stop control, resource monitoring and log aggregation. The project has iterated rapidly through forty numbered releases, adding support for AMD ROCm, Apple Metal, multi-GPU sharding, OpenAI-compatible routing and built-in SSL termination. Because every component runs inside containers, version conflicts between PyTorch, TensorRT-LLM or vLLM are eliminated and rollbacks are instantaneous. The software is offered under an open-source licence and is available for free on get.nero.com, where downloads are delivered through trusted Windows package sources such as winget, always providing the latest build and enabling batch installation alongside other applications.

Tags:

ai 159
large-language-model 75
llm 93
ollama 21