AnythingLLM v1.16.0
- Generate images via /img when a supported provider is set up
- Support image attachments for edits, followups, or combination prompts in image generation
- Drag entire folders into the file picker with hierarchy preserved in the upload panel
- Drag and drop files into existing folders directly in the file picker
- Toggle tools on and off during agentic chats without reloading or starting a new session
- Add support for openai-compatible whisper API
- Create-scheduled-job agent tool
- Add You.com as web search provider for agents
- Add Windows x64 (WHPX) support to open-computer
- Add oMLX LLM Provider
- Add Lao (lo) language support
- Add Indonesian (id) language support
- Add Croatian (hr) language support
- Increase the username character limit to 64
- File picker no longer requires typing https in the URL fetcher and assumes https when left out
- Lazy-load folders for improved performance with thousands of documents in a folder
- Update default fallback models for OpenAI and Anthropic
- Give Downloaded Models its own optgroup in Workspace Model Selector
- Aborting a response now fully kills the inference to prevent ghost inference continuing mid-stream
- Disable temperature for claude-sonnet-5 model
- Stream Anthropic non-streaming chat completions for REST API workspace chat
- Remove workspace profile picture feature
Notable Changes
Image Generation
Now you can generate images via /img when a supported provider is set up.
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
<optgroup>in Workspace Model Selector by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5967 - Gate Workspace System Prompt Override in
Workspace.new()by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5971 - feat: add Windows x64 (WHPX) support to open-computer by @Varun-Patkar in https://github.com/Mintplex-Labs/anything-llm/pull/5982
- test: fix isoDeviceArgs unit test after usb-storage change by @Varun-Patkar in https://github.com/Mintplex-Labs/anything-llm/pull/5987
- Patch API Citations regression by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5994
- Patch Generic OpenAI bug for OSA with Magic Echo by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5995
- Add Translations for Create Scheduled Job Agent Tool by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5932
- feat: create-scheduled-job agent tool by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5916
- docs(bare-metal): fix env var name to match frontend/.env — VITE_API_BASE by @unusdon in https://github.com/Mintplex-Labs/anything-llm/pull/5996
- oMLX LLM Provider by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5973
- Toggle agent tools during an active agent session by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5856
- fix: preserve TTS audio content type by @ivan-digital in https://github.com/Mintplex-Labs/anything-llm/pull/6012
- Fix slash command presets not expanding into prompt text by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6038
- Update Italian translation by @albanobattistella in https://github.com/Mintplex-Labs/anything-llm/pull/6018
- i18n: add Lao (lo) language support by @bounkirdni-2025 in https://github.com/Mintplex-Labs/anything-llm/pull/6039
- feat(i18n): add Indonesian (id) language support - closes #4198 by @samlehoy in https://github.com/Mintplex-Labs/anything-llm/pull/6037
- Inline MCP tool $ref/$defs schemas for Anthropic agent tool calls by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5786
- 5846 auto scroll by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6046
- i18n: add Croatian (hr) language support by @devanonyme42 in https://github.com/Mintplex-Labs/anything-llm/pull/6052
- feat(agents): add You.com as web search provider by @Souravrajvi0 in https://github.com/Mintplex-Labs/anything-llm/pull/6058
- refactor: remove workspace profile picture feature by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6010
- Add datetime to default system prompts by @Adityai1411 in https://github.com/Mintplex-Labs/anything-llm/pull/6016
- Fix: Restore Stop Generation Button During Agent Session Execution Loop by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5970
- feat: folder upload with relative paths preserved in document manager by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6027
- fix: keep watched document re-syncs from breaking pinned document de-duplication by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6029
- Add input_audio support for audio attachments on generic OpenAI provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6055
- Start model router cooldown after inference completes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6047
- fix: validate workspace update payloads to prevent misleading 200 responses by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6070
- chore: route agent chats with no tools through native tooled completions by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6067
- fix Bedrock model workspace selection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6079
- fix empty agent skill section in MuM by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6080
- Reset agent clarifying-questions counter per turn by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6083
- AWS Bedrock overhaul by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6081
- feat: abort agent sessions end-to-end when the user stops generation by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6063
- docs: fix broken service links in open-computer README by @richboyneedcash in https://github.com/Mintplex-Labs/anything-llm/pull/6088
- feat: add image generation via /img command by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5904
- 6089 milvus count by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6095
- feat: add Gitea data connector by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6087
- Fix generic openai thinking parsers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6105
- fix(i18n): correct zh-TW scheduled job labels by @nrps9909 in https://github.com/Mintplex-Labs/anything-llm/pull/6112
- feat: stream PiperTTS playback + harden long-message TTS by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6114
- FoundryLocal overhaul by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6119
- feat: support GitHub Enterprise URLs in the GitHub data connector by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6117
- v1.16.0 tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6122
New Contributors
- @Joshua-Medvinsky made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5784
- @ss-rstocchi made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5922
- @FI-Mihej made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5978
- @Varun-Patkar made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5982
- @unusdon made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5996
- @ivan-digital made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6012
- @albanobattistella made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6018
- @bounkirdni-2025 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6039
- @samlehoy made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6037
- @devanonyme42 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6052
- @Souravrajvi0 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6058
- @Adityai1411 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6016
- @ArslanRasheed60 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6029
- @richboyneedcash made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6088
- @nrps9909 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6112
Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.15.0...v1.16.0