# AnythingLLM v1.16.0 — AnythingLLM v1.16.0
- Product: AnythingLLM (https://whatsnew.fyi/product/anythingllm)
- Vendor: Mintplex Labs
- Date: 2026-08-13
- Version: v1.16.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.16.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.16.0
- Labels: Platforms: Desktop
What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.
Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.
---
- **added** — Generate images via /img when a supported provider is set up
- **added** — Support image attachments for edits, followups, or combination prompts in image generation
- **added** — Drag entire folders into the file picker with hierarchy preserved in the upload panel
- **added** — Drag and drop files into existing folders directly in the file picker
- **added** — Toggle tools on and off during agentic chats without reloading or starting a new session
- **added** — Add support for openai-compatible whisper API
- **added** — Create-scheduled-job agent tool
- **added** — Add You.com as web search provider for agents
- **added** — Add Windows x64 (WHPX) support to open-computer
- **added** — Add oMLX LLM Provider
- **added** — Add Lao (lo) language support
- **added** — Add Indonesian (id) language support
- **added** — Add Croatian (hr) language support
- **changed** — Increase the username character limit to 64
- **changed** — File picker no longer requires typing https in the URL fetcher and assumes https when left out
- **changed** — Lazy-load folders for improved performance with thousands of documents in a folder
- **changed** — Update default fallback models for OpenAI and Anthropic
- **changed** — Give Downloaded Models its own optgroup in Workspace Model Selector
- **fixed** — Aborting a response now fully kills the inference to prevent ghost inference continuing mid-stream
- **fixed** — Disable temperature for claude-sonnet-5 model
- **fixed** — Stream Anthropic non-streaming chat completions for REST API workspace chat
- **removed** — Remove workspace profile picture feature
##### Notable Changes
###### Image Generation
Now you can generate images via `/img` when a [supported provider is set up](https://docs.anythingllm.com/features/image-generation#supported-providers).
This flow also allows image attachments for edits, followups, or combination prompts if your provider supports image editing.
> Ability for an agent-tool to generate images is coming next update.
###### Better File Picker UX
Now in the file picker you can drag entire folders and their hierarchy will be preserved in the upload panel. This will only import the **top level** files in the folder — it will be deep and recursive in a later update.
You can also now drag and drop a file into an existing folder directly without needing to move it.
Lastly, you no longer need to type `https` in the URL fetcher - it will just assume https when left out.
We also made some large performance improvements, like lazy-loading of folders, for those with thousands of documents in a folder.
###### Tool Toggle Mid-Session
Now, during agentic chats you can freely toggle tools on/off at will without needing to reload or start a new session. Only tools that have been configured (if configuration is required) are available.
###### Stop Generation
A large improvement is now that `aborting` a response actually fully kills the inference as well so that ghost inference does not continue when no longer wanted mid-stream.
##### All Changes
* feat: increases the username character limit to 64 by @guilopesn in https://github.com/Mintplex-Labs/anything-llm/pull/5914
* Fixes typos and mistakes in Catalan translation by @jordimas in https://github.com/Mintplex-Labs/anything-llm/pull/5923
* Update default fallback models for OpenAI/Anthropic by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5949
* fix: disable temperature for claude-sonnet-5 model by @petre in https://github.com/Mintplex-Labs/anything-llm/pull/5947
* fix: stream Anthropic non-streaming chat completions for REST API workspace chat by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5941
* feat: add support for openai-compatible whisper api by @guilopesn in https://github.com/Mintplex-Labs/anything-llm/pull/5952
* fix: render kokoro-tts voice list for pre-0.3.x kokoro-fastapi servers by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5930
* OC readme bump by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5966
* fix: scope thread lookup to validated workspace in validWorkspaceAndThreadSlug by @Joshua-Medvinsky in https://github.com/Mintplex-Labs/anything-llm/pull/5784
* fix: MCP servers hidden from UI by post-connection errors and url-only definitions rejected by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5943
* Agent SQL Connector Fixes by @ss-rstocchi in https://github.com/Mintplex-Labs/anything-llm/pull/5922
* Fix scrollbar color on light mode by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5980
* (OpenComputer) Update model version in use case demos by @FI-Mihej in https://github.com/Mintplex-Labs/anything-llm/pull/5978
* Give Downloaded Models its Own `