LLM Harbor

v0.5.0 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 1mo LLM Frameworks

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai automation shell cli container docker

+10 more

self-hosted llm local mcp npm package pypi safetensors server tools

Affected surfaces

breaking_upgrade

ReleasePort's take

Moderate signal

editorial:auto 1mo

In v0.5.0 the default backend switches from Ollama to llamacpp.

Why it matters: Affects any use of `harbor up` that relies on Ollama; update configurations before upgrading.

Summary

AI summary

llamacpp replaces Ollama as the default backend.

Changes in this release

Type	Severity	Summary	CVE
Breaking	High	llamacpp becomes default backend, replacing Ollama. llamacpp becomes default backend, replacing Ollama. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature
Feature	Medium	Adds `harbor skills` CLI command for AI agent skill discovery. Adds `harbor skills` CLI command for AI agent skill discovery. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Introduces four new backends: DMR, MLX, oMLX, and Daytona. Introduces four new backends: DMR, MLX, oMLX, and Daytona. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Adds in-app guided setup flow for Docker detection, dependency installation, and CLI bootstrapping. Adds in-app guided setup flow for Docker detection, dependency installation, and CLI bootstrapping. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Adds shell tab completion for bash, zsh, and fish. Adds shell tab completion for bash, zsh, and fish. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Adds port conflict pre‑detection before `harbor up` fails. Adds port conflict pre‑detection before `harbor up` fails. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Adds smart pull routing to direct model downloads to the correct backend. Adds smart pull routing to direct model downloads to the correct backend. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Adds `harbor volumes` CLI for custom volume mounts. Adds `harbor volumes` CLI for custom volume mounts. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Medium	Adds fuzzy service name suggestions for mistyped handles. Adds fuzzy service name suggestions for mistyped handles. Source: llm_adapter@2026-06-14 Confidence: high	—
Feature	Low	Upgrades MiniMax default model to M3. Upgrades MiniMax default model to M3. Source: llm_adapter@2026-06-14 Confidence: high	—

Full changelog

TL;DR

Four new backends - DMR (Docker Model Runner), MLX, oMLX, and Daytona sandbox - with cross-service integrations rolled out to 26 services each. llamacpp replaces Ollama as the default backend (harbor defaults add ollama to restore the old behavior). The Tauri app now handles the entire install workflow in-app. New CLI features: tab completion, port conflict detection, smart pull routing, custom volume mounts, fuzzy service suggestions, and harbor skills for AI agent discovery.

llamacpp default backend (breaking change)

llamacpp is now the default backend, replacing Ollama. Running harbor up with no arguments starts llamacpp instead of Ollama. Existing users who rely on harbor up launching Ollama should explicitly run harbor up ollama or set their default via harbor defaults add ollama. Cross-service integrations for llamacpp have been rolled out to 38 services.

Agent Skills

New harbor skills command exposes agent-facing CLI documentation, letting AI coding agents discover and use Harbor commands without manual prompting.

harbor skills             # list available skills
harbor skills get <name>  # show a skill's content

In-App Install

The Tauri app now ships a full guided setup flow — Docker detection, dependency installation, platform-specific package management, and CLI bootstrapping all happen inside the app. Covers macOS, WSL, Fedora, openSUSE, and minimal environments with cancel-between-steps, error recovery, and disk space checks.

DMR (Docker Model Runner)

Run models through Docker Desktop's built-in Model Runner with OpenAI-compatible API, auto-bootstrapped on harbor up.

harbor up dmr

MLX

Apple Silicon native inference via mlx-lm, with auto-bootstrap and host component setup on first run.

harbor up mlx

oMLX

OpenAI-compatible MLX inference server for Apple Silicon.

harbor up omlx

Daytona

Self-hosted sandbox environment service for AI agent workloads.

harbor up daytona

Misc

Tab completion for bash, zsh, and fish shells.
Port conflict pre-detection warns before harbor up fails.
Smart pull routing automatically directs model downloads to the right backend.
Custom volume mounts via harbor volumes CLI.
Fuzzy service name suggestions when you mistype a service handle.
MiniMax default model upgraded to M3.
Comprehensive integration test suites added for CLI, config, and service lifecycle.

Full Changelog: https://github.com/av/harbor/compare/v0.4.19...v0.5.0

Breaking Changes

Default inference backend changed from Ollama to llamacpp; `harbor up` now starts llamacpp unless explicitly invoked with `ollama` or via `harbor defaults add ollama`.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track LLM Harbor

Get notified when new releases ship.

About LLM Harbor

Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI. `Apache-2.0` `Docker/Shell`