LLM Harbor
LLM FrameworksContainerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI. `Apache-2.0` `Docker/Shell`
Features
- Spins up a full local LLM stack with back‑ends (Ollama, llama.cpp, vLLM) and front‑ends (Open WebUI)
- Adds supporting services such as SearXNG for web search
- Provides speech capabilities via Speac
Recent releases
View all 28 releases →
v0.4.15
Security relevant
Security fixes
- CVE-2023-XXXXX — fixed HFDownloader command injection vulnerability (CWE-78) and added remote profile validation to prevent CWE-78 attacks
Notable features
- TabbyAPI now uses an official image with an updated default model
Full changelog
Lemonade
AMD Lemonade inference server for ROCm GPUs.
harbor up lemonade
Tokscale
Token-level autoscaling proxy for LLM backends.
harbor up tokscale
Misc
- TabbyAPI switched to official image with updated default model and hfdownloader fix
- fix(profile): validate remotely downloaded profiles to prevent command injection (CWE-78) by @sebastiondev in https://github.com/av/harbor/pull/236
- Lint exclusions for vendored third-party caches
Full Changelog: https://github.com/av/harbor/compare/v0.4.14...v0.4.15
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.
