This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+10 more
ReleasePort's take
Light signalML Intern v0.4.16 introduces auto‑mode for ranking and selecting text/code models from the router catalog.
Why it matters: If you use ML Intern in automated workflows, test the new model‑selection behavior before deploying to production.
Summary
AI summaryML Intern auto mode selects ranked text/code models from the router catalog.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
New ML Intern Hugging Face agent for research, training, code shipping New ML Intern Hugging Face agent for research, training, code shipping Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Feature | Medium |
New facts CLI enables fact-driven development with agent verification New facts CLI enables fact-driven development with agent verification Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Feature | Medium |
New mi agentic CLI for coding against OpenAI-compatible APIs New mi agentic CLI for coding against OpenAI-compatible APIs Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Feature | Medium |
ML Intern supports GitHub token override via environment variable ML Intern supports GitHub token override via environment variable Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Feature | Medium |
ML Intern reports unhealthy LLM backends with HTTP 503 status ML Intern reports unhealthy LLM backends with HTTP 503 status Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Feature | Medium |
ML Intern auto-selects ranked text/code models, rejects unsuitable ones ML Intern auto-selects ranked text/code models, rejects unsuitable ones Source: llm_adapter@2026-05-21 Confidence: low |
— |
| Bugfix | Medium |
Harbor config search matches hyphenated service handles like ml-intern Harbor config search matches hyphenated service handles like ml-intern Source: llm_adapter@2026-05-21 Confidence: low |
— |
Full changelog
ML Intern
Hugging Face ML engineering agent for researching papers, inspecting Hugging Face resources, training models, and shipping ML-related code with local or cloud LLM backends.
harbor up ml-intern ollama --open
facts
Fact-driven development CLI for project specs that agents can verify and implement from inside Harbor.
harbor facts list
mi
Minimal agentic coding CLI that runs against OpenAI-compatible local or cloud model APIs.
harbor mi -p "inspect this project and summarize it"
Misc
- ML Intern llama.cpp auto mode selects ranked text/code models from the advertised router catalog and rejects unsuitable non-chat models.
- ML Intern can use GitHub token override env and reports unhealthy LLM backends with HTTP 503.
- Harbor config search now matches hyphenated service handles such as
ml-internagainst normalized config keys.
Full Changelog: https://github.com/av/harbor/compare/v0.4.15...v0.4.16
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
About LLM Harbor
Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI. `Apache-2.0` `Docker/Shell`
Related context
Related tools
Beta — feedback welcome: [email protected]