v1.16.1 v1.16.2
Mintplex-Labs/anything-llmAug 27, 2026 → Sep 22, 202626 days between releases
What's New
LLMman replaces Docker Model Runner as the local LLM provider
Breaking Changes
- LLMman replaces Docker Model Runner as the local LLM provider
New Features
- Google Vertex AI is now available as a new LLM provider
- New 'generate-image' agent skill for creating images from chat
- You.com is now the default web search provider
- Agent flow variables now support optional arguments
- Expanded language support for Hindi, Bulgarian, and Swedish
Improvements
- Local providers now report model loading status in chat
- Ollama runtime bumped to 0.33.3 with an updated bundled model list
- Web browsing is now enabled by default for agents
- Scraped web pages now preserve tables, ordered lists, and code blocks
- PDF pages are now joined with newlines to prevent word fusion
Upgrade Notes
If you were using Docker Model Runner, you must switch to configuring LLMman. Additionally, the default web search provider has changed to You.com.
The Two Releases
AnythingLLM v1.16.1
Aug 27, 2026· 2 months ago
A major update focusing on UI overhauls for agent thinking, new hardware acceleration providers (Microsoft Foundry Local, Qualcomm GenieX), and cross-region AWS Bedrock support.
Full release notesAnythingLLM v1.16.2
Sep 22, 2026· 29 days ago
This release introduces significant updates including new LLM providers like Google Vertex AI and LLMman (replacing Docker Model Runner), enhanced web search capabilities with You.com as the default, and improved document handling. It also adds new features like an image generation agent skill and expanded language support.
Full release notes