# AnythingLLM changelog
> An all-in-one desktop and Docker app for chatting with your own documents.
- Vendor: Mintplex Labs
- Category: AI
- Platforms: Desktop
- Official site: https://anythingllm.com
- Tracked by: What's New (https://whatsnew.fyi/product/anythingllm)
- Harvested from: GitHub (Mintplex-Labs/anything-llm)
- Entries below: 10 (newest first)
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'.
## Releases
### v1.15.0 — AnythingLLM v1.15.0
- Date: 2026-06-25
- Version: v1.15.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.15.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.15.0
- Labels: Platforms: Desktop
- **added** — Magic Echo, a voice-to-text dictation feature that works anywhere on the OS with custom dictionary support and voice commands
- **added** — Magic Beacon, a feature to highlight text in any app and perform AI actions like summarization, translation, rewriting, and research with access to agent skills and MCPs
- **added** — Magic Tab, an autocomplete feature that suggests text as you type in any app, aware of context and available on-device
- **added** — AnythingLLM Pro subscription tier with free daily limits for all Magic Features and no signup required for free tier
- **changed** — Intelligent Tool Selection (ToolReranker) is now enabled by default
- **changed** — Chat history cap has been unlocked
- **added** — Query and passage prefix environment variables for the GenericOpenAi embedder
- **fixed** — API update-embeddings endpoint no longer fails with Prisma "filename is missing" error on Windows paths
#### AnythingLLM Is Now An AI Agent Across Your Os
With AnythingLLM 1.15.0 for Desktop we have been working *hard* on what it means to bring your agent **to you**. Something that is still local, but outside of the walls of an app or a browser. This release features our first 3 features about this effort - we hope you enjoy them.
##### Introducing Magic Features
Magic Features bring AI to your entire computer — not just inside AnythingLLM. Dictation, text actions, and autocomplete that work in any app, fully on-device.
All Magic Features are free to use — no signup required. Pro removes the daily limits.
###### AnythingLLM Pro
Nothing about AnythingLLM is changing. Pro is purely additive — no existing features are affected, nothing is being locked away.
Every Pro feature will always have a free daily tier, no signup required.
You can read more about what AnythingLLM Pro is [here](https://docs.anythingllm.com/pro/overview).
##### Magic Echo - [Docs](https://docs.anythingllm.com/pro/magic-echo)
> A smarter voice-to-text dictation that works anywhere on your OS. Can replace tools like SuperWhisper or WhisprFlow entirely. Fully on-device.
Speak naturally and your words appear right where your cursor is — transcribed, cleaned up, and punctuated. Echo can see what's on your screen to make dictations smarter and more contextual.
Includes custom dictionary support, voice commands, and more.
##### Magic Beacon - [Docs](https://docs.anythingllm.com/pro/magic-beacon)
> Highlight text in any app and instantly act on it with AI.
Highlight any text on your screen and instantly act on it — summarize, translate, rewrite, research, or run a custom action. Beacon works in any app without switching windows.
It also has full access to your agent skills, MCPs, and tools — AnythingLLM's entire capability set, available anywhere your cursor is.
##### Magic Tab - [Docs](https://docs.anythingllm.com/pro/magic-tab)
> Grammarly across your entire computer - fully on-device.
As you type, Magic Tab suggests what comes next — in any app, aware of what you're working on so suggestions actually fit. Click into a text field and it'll suggest something before you've typed a single letter.
If you use Grammarly, Tab can replace it entirely — privately, on your device.
----
##### What's Changed
* Unlock Chat History Cap by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5906
* fix: API update-embeddings fails with Prisma "filename is missing" on Windows paths by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5907
* Intelligent Tool Selection (`ToolReranker`) enabled by default by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5893
* feat: add query/passage prefix env vars to GenericOpenAi embedder by @jhsmith409 in https://github.com/Mintplex-Labs/anything-llm/pull/5589
* 1.15.0 tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5909
##### New Contributors
* @jhsmith409 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5589
**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.2...v1.15.0
### v1.14.1 — AnythingLLM v1.14.1
- Date: 2026-06-16
- Version: v1.14.1
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.14.1
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.14.1
- Labels: Platforms: Desktop
- **added** — Support for Intel, AMD, and NVIDIA GPUs in Meeting Assistant
- **added** — Developer API for transcription on audio via POST /v1/transcription/transcribe
- **added** — Basic Speaker Identification feature for Meeting Assistant
- **added** — Dual channel stereo recordings support for meetings
- **added** — Copy chat link functionality to quickly re-open a chat in the desktop/self-hosted app via deeplinking
- **added** — Audio and video uploads via chat UI using Tinyscribe engine
- **added** — Export Chat as PDF, JSON, Markdown, and other formats from chat UI
- **added** — HD screenshots option for Desktop Assistant Setting screenshot capture area
- **added** — Request approval internal function available for custom skills
- **changed** — Meeting Assistant binary is 92% smaller and processing times are 15% faster
- **changed** — Meeting Assistant context window overflow handling improved for better summarization of longer meetings
- **changed** — Linux AppImage size reduced by 91% and now caches Ollama engine downloads for faster startup
- **changed** — Cohere SDK removed and ported to OpenAI SDK for compatibility
- **fixed** — Meeting Assistant title now auto-updates in UI after summary
- **fixed** — Text clearing bug when dragging and dropping files into chat with existing prompt text
- **fixed** — Memory leak in embedder from constantly reloading in server process
- **fixed** — Desktop Assistant Capture Area not showing on Windows multi-monitor setups
- **fixed** — Strip thinking from fork thread name when forking a chat that had thoughts
- **fixed** — Toast light mode always showing regardless of system theme
- **removed** — DPAIS and HuggingFace providers removed from AnythingLLM due to being unmaintained
##### Meeting Assistant Overhaul
_Meeting Assistant is desktop app only_
We have overhauled a large portion of the Meeting Assistant to make it smaller, faster, and more efficient across all devices and platforms.
- [x] Now supports Intel, AMD, and NVIDIA GPUs for a 92% smaller binary and 15% faster processing times.
- If you already have the NVIDIA GPU binary installed, you can safely delete it if you want. It will still work and is backwards compatible.
- [x] Support for Developer API for transcription on audio (POST: `/v1/transcription/transcribe`)
- [x] Meeting Assistant context window overflow handling is much better now - so small models can summarize longer meetings.
- [x] Introduction of [Basic Speaker Identification](https://docs.anythingllm.com/meeting-assistant/features#speaker-identification) for 60% better summarizes from any audio.
- [x] Dual channel stero recordings for meetings now - leading to 80% better speaker identification in "Full Diarization" mode.
##### Improvements
- [x] Linux AppImage now **91%** smaller in size and caches Ollama engine downloads for faster startup times.
- [x] Meeting Assistant title fix on meetings post-summary now auto-updates in UI
- [x] AgentFLow variable highlight so its clear what is and is not a valid variable
- [x] "Copy chat link" in UI to quickly re-open a chat in the desktop/self-hosted app via deeplinking.
- [x] Re-enabled audio and video uploads via chat UI - uses Tinyscribe engine now.
- [x] Export Chat as (PDF, JSON, Markdown, etc) from chat UI.
- [x] Desktop Assistant Setting - HD screenshots now available for screenshot capture area.
- [x] Request approval internal function is now available for custom skills.
##### Bug Fixes
- [x] Removed DPAIS and HuggingFace providers from AnythingLLM (unmaintained)
- [x] Fixed memory leak in embedder from it constantly reloading in server process
- [x] Fixed text clearing bug when dragging and dropping files into the chat and text was already present in prompt.
- [x] Massive performance improvements to the frontend UI for long running chats.
- [x] Cohere SDK removed and ported to OpenAI SDK for compatibility.
- [x] Desktop Assistant Capture Area not showing on windows multi-monitor setups.
- [x] Strip thinking from fork thread name when forking a chat that had thoughts.
- [x] Fix toast light mode always showing regardless of system theme.
- [x] Mistral embedder encoding issue fixed.
- [x] Better error messages for API
- [x] Omit temp in Claude Bedrock for Claude 4.8
- [x] Fixed event emitter leak in server process for web-scraping and summarize process
----
##### What's Changed
* fix: prevent EventEmitter memory warning in AIbitat agent framework by @simongonzalezdc in https://github.com/Mintplex-Labs/anything-llm/pull/5790
* Remove unused providers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5793
* Patch reloading of embedder and lanceDB connection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5804
* Better API errors by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5805
* Mistral Embedding Encoding by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5806
* fix: omit temperature param for Bedrock Claude Opus 4.8 by @kimnamu in https://github.com/Mintplex-Labs/anything-llm/pull/5822
* feat: expose requestToolApproval to custom agent skills by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5795
* feat: highlight variable references in agent flow blocks by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5799
* chat link in chat settings by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5837
* WorkspaceChat refactor by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5833
* More Frontend optimizations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/58
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.14.1]_
### v1.14.0 — AnythingLLM v1.14.0
- Date: 2026-06-09
- Version: v1.14.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.14.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.14.0
- Labels: Platforms: Desktop
- **added** — Cerebras provider support
- **added** — Speech-to-text support for Deepgram, GenericOAI, Lemonade, and OpenAI
- **added** — Text-to-speech support for KokoroTTS
- **added** — 24-hour system variable formats
- **added** — Document sync stale-after interval is now configurable
- **added** — Opt-in deny-by-default for embeds with no allowlist
- **changed** — Default chat thread is now killed when creating a new thread, though existing chats on the default thread remain available
- **changed** — All model providers are now opt-out of tool calling by default
- **changed** — Web-scraping now converts to markdown for better parsing and chat followup tasks with minimal context bloat
- **changed** — Summary tool overhauled with better summaries, improved transparency, and confirmation prompts for longer summaries
- **changed** — Improvements to the GenericOAI provider
- **changed** — Better LaTeX rendering support
- **fixed** — Context limit detection issue for agents
- **fixed** — SearXNG double encoding in search queries
- **fixed** — Timeouts for all fetch requests
- **fixed** — Escape illegal XML control characters in word documents and generated documents
- **fixed** — Windows uninstall now includes checkbox to remove all AnythingLLM data
- **fixed** — Tray fixes when app starts in background or Desktop Assistant feature is toggled
- **fixed** — Support Azure and Dell Pro AI Studio providers in agent summarization fallback
##### Improvements
- [x] Cerebres provider
- [x] The default chat thread is now killed when you create a new thread. If you have chats on the default thread, it will be available still. New workspaces or workspaces with no chats on default will no longer show it.
- [x] All model providers are now *opt-out* of tool calling by default. Everything will call tools by default unless you opt-out offering better performance for agents everywhere
- [x] STT Support for Deepgram, GenericOAI, Lemonade, & OpenAI
- [x] TTS Support for KokoroTTS
- [x] Web-scraping now will convert to markdown for better parsing and chat followup tasks with minimal context bloat
- [x] Summary tool was overhauled. Now it will so better summaries with transparency as well as ask before continuing for longer summaries
- [x] Improvements to the GenericOAI provider
- [x] 24hour system variable formats
- [x] Better LaTex rendering support
##### Bug Fixes
- [x] Context limit detection issue for agents: https://github.com/Mintplex-Labs/anything-llm/pull/5716
- [x] SEARXNG double encoding: https://github.com/Mintplex-Labs/anything-llm/pull/5723
- [x] Timeouts for all fetch requests https://github.com/Mintplex-Labs/anything-llm/pull/5721
- [x] Escape illegal XML in word docs, etc https://github.com/Mintplex-Labs/anything-llm/pull/5760
- [x] (Windows) On unisntall, checkbox to remove **all** AnythingLLM data is now present
- [x] Tray Fixes when app starts in background or Desktop Assistant feature is toggled.
##### What's Changed
* docs: list all cloud embedding providers by @narutamaaurum in https://github.com/Mintplex-Labs/anything-llm/pull/5701
* feat: add Cerebras as an LLM provider by @officialasishkumar in https://github.com/Mintplex-Labs/anything-llm/pull/5699
* fix provider override in agents by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5716
* docs: fix self-hosted terms wording by @Zhao73 in https://github.com/Mintplex-Labs/anything-llm/pull/5737
* fix: avoid double-encoding SearXNG search queries by @trick77 in https://github.com/Mintplex-Labs/anything-llm/pull/5723
* Kill `default` thread by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5739
* feat: add server-side speech-to-text with OpenAI provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5596
* Kokoro TTS provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5679
* add windows paths to isWithin by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5685
* apply universal sdk timeout by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5721
* fix: support Azure & Dell Pro AI Studio providers in agent summarization fallback by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5738
* Turn HTML scraped sites to Markdown for better research by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5742
* Improve agent summarizer tool by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5719
* Generic OpenAI improvements by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5746
* feat: make document sync stale-after interval configurable by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5747
* fix: strip XML-illegal control characters from generated documents by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5760
* feat(embed): opt-in deny-by-default for embeds with no allowlist by @dmitrymaranik in https://github.com/Mintplex-Labs/anything-llm/pull/5759
* add 24 hours date and time formats to SystemVariables by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5778
* Make native tool calling opt-out instead of opt-in by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5783
* better LaTex support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/577
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.14.0]_
### v1.13.0 — AnythingLLM v1.13.0 - A Hybrid AI Experience
- Date: 2026-05-26
- Version: v1.13.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.13.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.13.0
- Labels: Platforms: Desktop
- **added** — Model Router feature that enables intelligent hybrid AI routing between local and cloud models based on user-defined rules including keywords, token counts, time of day, and image attachments
- **added** — Scheduled Jobs feature that automates recurring AI agent tasks on user-defined schedules with visual Cron Builder and no technical knowledge required
- **added** — Automatic memory extraction and personalization that stores memories in a memory bank to personalize AI assistant responses
- **added** — Workspace-specific and global memories that are injected into the system prompt to enhance personalization
- **added** — Support for LLM-classified rules in Model Router that understand intent in plain English
- **added** — Push notifications when scheduled jobs finish execution
- **added** — Complete run history logging for scheduled jobs including agent reasoning, tool calls, and generated files
- **added** — Visual memory management interface with options to manually add memories to the memory bank
This release is focused on improving the agent experience and adding new features to the agent system as well as moving towards a more passive, personal, and **hybrid** AI experience.
##### Model Router: The First Consumer Hybrid AI Experience
The Model Router feature is the first-ever user-defined intelligent routing system that seamlessly blends local and cloud AI into a single, unified experience that is entirely under your control. Until now, you had to choose: run everything locally, or send everything to the cloud. That tradeoff is over.
With Model Router, you define the rules. Every message you send is automatically analyzed and routed to the perfect model for that specific task, whether that's a lightweight local model for quick questions, a reasoning model for complex math, or your most powerful cloud model for nuanced legal analysis. All from the same chat. All invisible to the user. All defined by you.
**What makes this so exciting:**
- **Hybrid AI.** Mix and match local models (Ollama, LM Studio, etc.) with cloud providers (OpenAI, Anthropic, Google) in a single conversation. No manual switching!
- **You're in complete control.** Create [calculated rules](https://docs.anythingllm.com/model-router/setup#calculated-rules) that trigger on keywords, token counts, time of day, or image attachments **instantaneously**. Or use [LLM-classified rules](https://docs.anythingllm.com/model-router/setup#llm-classified-rules) that understand intent in plain English.
- **Save money without sacrificing quality.** Route simple queries to cheap or local models. Reserve expensive API calls for the messages that actually need them.
- **Intelligent caching.** Our advanced sticky routing system keeps you on the same model during a conversation thread, so you're not bouncing between models on every message.
This is, we believe, a fundamental shift in how AI assistants work. For the first time, you get the privacy of local models, the power of cloud models, and the intelligence to know when to use each. And it's 100% open source.
[Learn how to set up your first router →](https://docs.anythingllm.com/model-router/setup)
##### Scheduled Jobs: Your AI That Works While You Don't
What if your AI assistant could work for you in the background, automatically, on a schedule you define, without you lifting a finger?
**Scheduled Jobs** turns AnythingLLM into an always-on AI workforce. Create recurring tasks that run themselves: morning briefings, weekly reports, data monitoring, research digests. Anything you'd normally ask an agent to do, but automated and hands-free. Has job specific skills you can set so the model is not overwhelmed with tools and outcomes are repeatable.
**Why this changes everything:**
- **Set it and forget it.** Define a prompt, pick your tools, choose a schedule, and walk away. Your agent runs exactly when you need it: every morning at 8 AM, every Monday at noon, every hour on the hour.
- **No technical knowledge required.** Our visual Cron Builder lets you schedule jobs with simple dropdowns. No cryptic cron syntax, no command line, no code. Just point and click.
- **Full agent power, fully automated.** Scheduled jobs have access to the same tools as your regular chats: web search, document analysis, custom skills, MCP integrations, and more. If an agent can do it in a conversation, it can do it on a schedule.
- **Complete run history.** Every execution is logged with the agent's full reasoning, tool calls, generated files, and final response. Review past runs anytime, or continue where the agent left off in a new thread.
- **Push notifications.** Get alerted the moment a job finishes, even when AnythingLLM is in the background. Click to jump straight to results.
Enterprise tools charge thousands for this kind of automation. Cloud-only pl
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.13.0]_
### v1.12.1 — AnythingLLM v1.12.1
- Date: 2026-04-22
- Version: v1.12.1
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.12.1
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.12.1
- Labels: Platforms: Desktop
- **added** — Report document embedding process per-document during upload with ability to add, remove, and queue documents without losing progress
- **added** — Built-in Gmail integration for Agent skills
- **added** — Built-in Outlook integration for Agent skills
- **added** — Built-in Google Calendar integration for Agent skills
- **added** — Image lightbox in main UI for chat attachments
- **added** — Korean, Chinese, and Japanese character support for PDF generation
- **added** — Open documents in native application on machine when generated by Document Generation Agent
- **added** — Auto approve agent skill via ENV setting
- **added** — Chat setting for Unload model when closed to unload the model when the user closes the chat window
- **added** — Generic OpenAI capability detection and ENV setting
- **added** — Catalan translations
- **added** — Name field added to API keys
- **changed** — Better citations for app integrations
- **changed** — DDG default web-search in agent skills
- **changed** — Ollama bumped to 0.20.7 with Qwen3.5 and Gemma 4 support
- **changed** — Update Lemonade to support 1.10.0 changes
- **changed** — Chat ID reported in agent sessions to allow regenerate chats, TTS, and more actions without page reloads
- **fixed** — Lemonade throw on embedding failures instead of returning empty
- **fixed** — Light mode docgen page display
- **fixed** — Agent flow menu visibility in narrow windows
- **fixed** — Agent flow toggle state sync
- **fixed** — Remove illegal characters for Windows on files
- **fixed** — Preserve Confluence context paths
- **fixed** — Omit temperature param for Bedrock Claude Opus 4.7
- **fixed** — Long-prompt bubble flicker and see more collapse on streaming or scroll
- **fixed** — Surface readable error messages in web-scraping agent and AI provider
- **fixed** — Streaming issue for LLM instruction blocks
- **fixed** — Retry handling to Telegram for transient failures
##### Notable Improvements
###### Streamed Document Embedding
Now, when you upload a document to the workspace the process per-document is now reported during embedding. This is a huge improvement in performance and user experience. During this process you can add and remove documents to the queue as well as even close and navigate away from the page without losing your progress.
###### App integrations
There are now built in integrations for the following apps with minimal to zero setup required for Agent skills:
- [Gmail](https://docs.anythingllm.com/agent/usage/gmail-agent)
- [Outlook](https://docs.anythingllm.com/agent/usage/outlook-agent)
- [Google Calendar](https://docs.anythingllm.com/agent/usage/google-calendar-agent)
##### Other Improvements
- [x] Image Lightbox in main UI
- [x] Enabled Korean, Chinese, & Japanese character support for PDF generation via custom mdpdf fork
- [x] Better citations for app integrations
- [x] DDG default web-search in agent skills
- [x] Open documents in native application on machine when generated by Document Generation Agent
- [x] Auto approve agent skill via ENV setting
- [x] Ollama bumped to 0.20.7 (Qwen3.5 support, Gemma 4, etc)
- [x] New Customization > Chat setting for `Unload model when closed` to unload the model when the user closes the chat window.
- [x] Generic OpenAI Capability detection/ENV setting
- [x] Update Lemonade to support 1.10.0 changes
- [x] Catalan translations
- [x] Name field added to API keys
- [x] Chat ID reported in agent sessions so now you can regenerate chats, TTS, and more actions without page reloads.
##### What's Changed
* German translation fixes by @neuhaus in https://github.com/Mintplex-Labs/anything-llm/pull/5319
* fix(lemonade): throw on embedding failures instead of returning empty by @nehaaprasad in https://github.com/Mintplex-Labs/anything-llm/pull/5325
* Fix light mode docgen page by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5347
* fix(agent-flows): keep flow menu visible in narrow windows by @suyua9 in https://github.com/Mintplex-Labs/anything-llm/pull/5341
* Fix Agent Flow toggle state sync by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5348
* Remove illegal chars for Windows on files by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5364
* feat: Document Embedding Status Events | Refactor Document Embedding to Job Queue and Forked Process by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5254
* Update Lemonade Integration to support v10.1.0 changes by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5378
* Enable final tool call in MAX_STACK to run by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5381
* Fix streaming issue for LLM instruction blocks by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5382
* Add retry handling to TG for transient failures by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5391
* Migrate to org-maintained mdpdf for lang support (Hangul, Simplified Chinese, Kanji) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5392
* feat: adds name field to api keys by @guilopesn in https://github.com/Mintplex-Labs/anything-llm/pull/5366
* Add automatic agent skill aproval via ENV Flag by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5405
* GMail Agent Skill by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5400
* Helm chart updates by @bustapipes in https://github.com/Mintplex-Labs/anything-llm/pull/5410
* feat: add Catalan translation by @jordimas in https://github.com/Mintplex-Labs/anything-llm/pull/5411
* fix: preserve Confluence context paths by @official
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.12.1]_
### v1.12.0 — AnythingLLM v1.12.0
- Date: 2026-04-02
- Version: v1.12.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.12.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.12.0
- Labels: Platforms: Desktop
- **added** — Automatic mode for native tool calling that uses tools without requiring @agent prefix for supported providers
- **added** — Intelligent Tool Selection feature to load unlimited tools into context with up to 80% token usage reduction
- **added** — Filesystem Agent feature to search files and directories on the host machine
- **added** — Document Generation Agent to create text files, PDFs, Excel files, Docx, and PowerPoint presentations
- **added** — Telegram bot support for Docker and Desktop with text chat, image understanding, voice messages, and workspace selection
- **added** — Lithuanian locale support
- **added** — User-Agent header for Anthropic API calls
- **added** — Optional API key support for Lemonade provider
- **changed** — Automatic mode for workspace with Agent mode as default
- **changed** — Dynamic max_tokens retrieval for Anthropic models
- **changed** — Refactored onboarding welcome screen to v2 design
- **changed** — Auto-select newly uploaded documents and URLs in my documents list
- **changed** — Redesigned Telegram bot settings UI
- **changed** — Updated Exa search provider description
- **fixed** — File extension inference from Content-Type for URLs without explicit extensions
- **fixed** — Firefox LaTeX rendering
- **fixed** — Chat UI event listener bloat
##### Major Features
###### Automatic Mode for native tool calling
For [Select providers](https://docs.anythingllm.com/features/chat-modes#available-chat-modes) that support native tool calling, you no longer need to use `@agent` to use tools. You can now just use the tools without asking.
If your prompt input does not have the "@" symbol, your chats will automatically use tools as needed.
https://github.com/user-attachments/assets/2ab6af9a-98d0-4d52-a3d3-849d70e64004
##### Intelligent Tool Selection
We have added a new feature called [Intelligent Tool Selection](https://docs.anythingllm.com/agent/intelligent-tool-selection). This feature allows you to load **unlimited** tools for your agent to use into context with better performance and save up to 80% on token usage every single chat.
##### Filesystem Agent
We have added a new feature called [Filesystem Agent](https://docs.anythingllm.com/agent/usage#file-system-agent). This feature allows you to use the filesystem of your host machine to search for files and directories.
##### Document Generation Agent
We have added a new built-in agent for [Document Generation](https://docs.anythingllm.com/agent/usage#document-generation-agent). With document generation, you can generate text files, PDFs, Excel files, Docx, and even entire PowerPoint presentations.
https://github.com/user-attachments/assets/493e27bb-4944-4a8d-8995-a7c8b3eaadd5
##### Telegram Bot
AnythingLLM Docker and Desktop now support a [Telegram bot](https://docs.anythingllm.com/channels/telegram) so you can connect to your AnythingLLM instance anywhere in the world.
**Supports**:
- Text chat (streaming & thinking)
- Image understanding
- Voice messages & Attachments
- Automatic mode and @agent support
- Workspace and thread selection
- Model selection
- Citations
- Any agent skill available in AnythingLLM
##### What's Changed
* update exa search provider description by @theishangoswami in https://github.com/Mintplex-Labs/anything-llm/pull/5225
* Automatic mode for workspace (Agent mode default) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5143
* MCP tool manager by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5230
* Intelligent Skill Selection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5236
* README updates by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5238
* fix(collector): infer file extension from Content-Type for URLs without explicit extensions by @Lyt060814 in https://github.com/Mintplex-Labs/anything-llm/pull/5252
* feat: add Lithuanian locale and register in resources by @arvydev in https://github.com/Mintplex-Labs/anything-llm/pull/5243
* Telegram bot connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5190
* Add User-Agent header for Anthropic API calls by @mikelambert in https://github.com/Mintplex-Labs/anything-llm/pull/5174
* add Dynamic `max_tokens` retreival for Anthropic models by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5255
* fix Firefox LaTeX rendering by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5258
* add ask to run prompt for tool calls (demo) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5261
* Refactor onboarding welcome screen to v2 design by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5262
* Filesystem Agent Skill overhaul by @timo
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.12.0]_
### v1.11.2 — AnythingLLM v1.11.2
- Date: 2026-03-18
- Version: v1.11.2
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.11.2
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.11.2
- Labels: Platforms: Desktop
- **added** — New prompt input in the main chat UI
- **added** — Ability to toggle Agent skills on/off from the prompt
- **added** — Ability to select the provider and model for the workspace without leaving the page
- **added** — Metrics for Agent calls
- **added** — Report document and web-search citations during Agent calls
- **added** — Automatic chat mode with native tool calling support
- **added** — Tooltip for paperclip attach button when no files are parsed
- **added** — Document count indicators to workspace document management modal
- **added** — Perplexity Search API as web search provider
- **changed** — Better Citations UI and reporting
- **changed** — Implement v2 chat layout designs
- **changed** — Improve zh_TW Traditional Chinese locale
- **fixed** — Bug where yarn setup:envs fails if any .env file already exists
- **fixed** — Show actionable error when LMStudio model listing fails or returns empty
- **fixed** — Azure OpenAI model key collision
- **fixed** — Add missing /wiki to Confluence cloud citation URLs
- **fixed** — Strip thinking from copy message outputs
- **removed** — Google web-search Programmable SERP
- **removed** — WelcomeMessages from app as it is no longer used
##### More UI Improvements
https://github.com/user-attachments/assets/9f2a0363-e905-420e-9c80-3b96fdb07368
Now, in the main chat UI we added some much desired UI improvements and fixes.
- [x] New prompt input
- [x] Better Citations UI and reporting
- [x] Metrics for Agent calls
- [x] Report document and web-search citations during Agent calls!
- [x] Ability to each toggle on/off Agent skills from the prompt
- [x] Ability to select the provider and model for the workspace without leaving the page.
----
##### What's Changed
* 5112 or stream metrics and finish reason by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5117
* Fix bug where `yarn setup:envs` fails if any .env file already exists. by @brianpursley in https://github.com/Mintplex-Labs/anything-llm/pull/5116
* fix: show actionable error when LMStudio model listing fails or returns empty by @elevatingcreativity in https://github.com/Mintplex-Labs/anything-llm/pull/5131
* Add automatic chat mode with native tool calling support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5140
* Sidebar updates by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5154
* Remove Google web-search Programmable SERP by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5156
* refactor: refactor agent skills settings page to use i18n translation keys by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5146
* chore: add ESLint to `/collector` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5128
* chore: add ESLint to `/server` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5126
* Fix: Azure OpenAI model key collision by @RALaBarge in https://github.com/Mintplex-Labs/anything-llm/pull/5092
* feat: Add tooltip for paperclip attach button when no files are parsed by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5139
* fix: add missing /wiki to Confluence cloud citation URLs by @MaxwellCalkin in https://github.com/Mintplex-Labs/anything-llm/pull/5167
* Strip thinking from copy message outputs by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5179
* Add custom fetch to embedder for Ollama by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5180
* chore: add script to detect and prune unused translation keys by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5141
* chore: add ESLint CI workflow by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5160
* Implement v2 chat layout designs by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5074
* Improve zh_TW Traditional Chinese locale by @PeterDaveHello in https://github.com/Mintplex-Labs/anything-llm/pull/5187
* Improve build times for tests and lint by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5193
* Support Agent stream metric reporting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5197
* Report citations for Agent call stacks by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5199
* Add FileRow Indentation on Documents Picker by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5201
* Remove `WelcomeMessages` from app - no longer used by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5206
* feat: Add document count indicators to workspace document management modal by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5207
* feat(agents): Add Perplexity Search API as web search provider by @kesku in https://github.com/Mintplex-Labs/anything-llm/pull/5210
##### New Contributors
* @brianpursley made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5116
* @elevatingcreativity made their first contribution in https://github.com/Mintplex-Labs
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.11.2]_
### v1.11.1 — AnythingLLM v1.11.1
- Date: 2026-03-02
- Version: v1.11.1
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.11.1
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.11.1
- Labels: Platforms: Desktop
- **changed** — Redesigned the main AnythingLLM homepage to be more modern and user-friendly for instant chatting after onboarding
- **changed** — Overhauled @agent tool calling to leverage native tool calling abilities of LLM providers and models
- **added** — Support for multi-step tool calls with native tool calling for local LLM providers
- **added** — First class support for Lemonade by AMD as a local model runtime for LLM, ASR, TTS, and image generation
- **changed** — Implemented safeguards for native tool calling with a maximum of 10 tool calls per response to prevent runaway tasks
- **fixed** — Resolve Gemini agent 400 error on tool call responses
- **fixed** — Fix GitLab connector infinite loop and rate limit crash for large repositories
- **added** — Add dedicated dark theme option with system preference support
- **changed** — Update light mode UI sidebar
- **fixed** — Fix event listener memory leak in useIsDisabled hook
- **fixed** — Prevent CMD/CTRL+Arrow scroll from overriding textarea cursor movement
- **fixed** — Add password character validation to onboarding single-user setup
##### Homepage Redesign
The main AnythingLLM homepage has been completely redesigned to be more modern and user-friendly so you can instantly start chatting the second you open the app after onboarding.
##### Native Tool Calling
Native tool calling is the best performance and experience for tool calling with your LLM provider and model. If you can enable it, you should.
_this only applies to local LLM providers. It has no impact on cloud LLMs like OpenAI, Anthropic, or Azure._
We have completely overhauled how `@agent` tool calling works. Now, we will leverage the new native tool calling abilities of your LLM provider and model.
**What this means for you:**
- You can now run complex, **multi-step** tool calls with your LLM provider and model.
- Your model will now continue to work until your final response is generated or determined to be complete.
- You will get 100x better responses from even small tool-calling models
We have implemented safeguards as well to prevent infinite loops with a maximum of 10 tool calls per response to prevent runaway tasks.
###### Limitations
Most providers do not allow us to probe for if a model supports native tool calling.
The following local LLM providers will automatically support native tool calling if your model supports it:
- Default Built in LLM Provider (AnythingLLM Default)
- Ollama
- LM Studio
For others, you will need to set an ENV variable to enable native tool calling for supported providers.
- Generic OpenAI
- Groq
- AWS Bedrock
- Lemonade
- LiteLLM
- Local AI
- OpenRouter
This can be set via the [`PROVIDER_SUPPORTS_NATIVE_TOOL_CALLING`](https://anythingllm.com/configuration#native-tool-calling-for-llm-providers) environment variable.
```
PROVIDER_SUPPORTS_NATIVE_TOOL_CALLING="bedrock,generic-openai,groq,lemonade,litellm,local-ai,openrouter"
```
##### Lemonade by AMD Integration
[Lemonade](https://lemonade-server.ai) by AMD is an [open-source](https://github.com/lemonade-sdk/lemonade) local model runtime that optimizes performance and efficiency for local models (LLM, ASR, TTS, Image Generation, etc.) for all types of hardware including AMD GPUs and NPUs.
We have added first class support so you can use your local models running via Lemonade within AnythingLLM for the best application experience on top of your local hardware.
-----
##### What's Changed
* fix: typo in contribution guidelines, update project metadata and pull_request_temp...md by @dipanshurdev in https://github.com/Mintplex-Labs/anything-llm/pull/5010
* feat: update light mode UI sidebar by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4996
* fix(frontend): fix event listener memory leak in useIsDisabled hook by @dipanshurdev in https://github.com/Mintplex-Labs/anything-llm/pull/5027
* feat: dedicated dark theme option with system preference support by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5007
* Implement new home page redesign by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4931
* fix: GitLab connector infinite loop and rate limit crash for large repos by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5021
* fix: add password character validation to onboarding single-user setup by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5037
* Native Tool calling by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5071
* fix: resolve Gemini ag
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.11.1]_
### v1.11.0 — AnythingLLM v1.11.0
- Date: 2026-02-18
- Version: v1.11.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.11.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.11.0
- Labels: Platforms: Desktop
- **added** — AnythingLLM Desktop now has an OS-level and application-aware panel that opens in a single keystroke to ingest current open applications alongside chat, document, RAG, and agent functionality
- **added** — Add keyboard shortcuts to scroll to top and bottom of chat history
- **added** — Support PrivateModeAI Integration
- **added** — Add ability to edit existing SQL agent connections
- **added** — SambaNova Integration
- **added** — Web push notifications
- **added** — UAE region support for bedrock models
- **added** — Add support for custom headers for LLM Generic OpenAI
- **changed** — Refine and standardize username constraints
- **changed** — New login page UI
- **changed** — Persist Ollama context preferences in LC tools
- **changed** — Refactor Ollama context window setting
- **changed** — Patch AzureOpenAI tool calling from function to tool
- **changed** — Manage onboarding decision via DB flag
- **changed** — Add provider field to chats
- **changed** — Migrate system preferences to field-based endpoint and remove deprecated endpoint
- **changed** — Set embedder output dimensions for LocalAI and Gemini (gemini-embedding-001)
- **changed** — Update LMStudio LLM and Embedder for API token support
- **fixed** — Fix sidebar thread layer
- **fixed** — Clean username already exists error
- **fixed** — Prevent Citations UI glitching during streaming chats
#### AnythingLLM Desktop overlay is live!
> _this is a free & desktop specific feature!_
Now, AnythingLLM Desktop has an OS-level and application aware panel that opens in a single keystroke. Seamlessly ingest your current open applications alongside all other chat functionality you use like document chat, RAG, agents, and more.
This panel is such a smoother and more convenient way to use AnythingLLM - we highly recommend this for daily use!
https://github.com/user-attachments/assets/0d3c260a-4d55-46e8-b11a-c6ecbf63e94d
-----
##### What's Changed
* Update common.js by @j0rDy in https://github.com/Mintplex-Labs/anything-llm/pull/4894
* Add keyboard shortcuts to scroll to top and bottom of chat history by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4870
* 4825 patch yt file collector api by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4904
* Refine and Standardize Username Constraints by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4828
* New login page UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4862
* [Chore] Autotranslation tool using DMR by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4907
* Persist Ollama context preferences in LC tools by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4908
* Refactor Ollama context window setting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4909
* Patch AzureOpenAI tool calling from `function` to `tool` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4922
* Thinking block persist toggle state by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4916
* Manage Onboarding decision via DB flag by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4926
* Fix sidebar thread layer by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4881
* Toggle switch component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4890
* Fix: Clean username already exists error by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4914
* fix: prevent Citations UI glitching during streaming chats by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4897
* Support PrivateModeAI Integration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4937
* feat: Add ability to edit existing SQL agent connections by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4848
* Fix double scroll container in agent flow builder by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4933
* feat: Enable essential ESLint rules and refactor frontend lint config by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4923
* SambaNova Integration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4943
* Update LMStudio LLM & Embedder for API token by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4948
* Web push notifications by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4942
* Fix agent workspace settings loading forever by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4956
* add provider field to chats by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4959
* UAE region support for bedrock models by @vigorous-ride in https://github.com/Mintplex-Labs/anything-llm/pull/4964
* fix: scroll active sidebar items into view by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4965
* refactor: Migrate system preferences to field-based endpoint and remove deprecated endpoint by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4958
* Refactor: Remove redundant message state sync in ChatContainer by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pul
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.11.0]_
### v1.10.0 — AnythingLLM v1.10.0
- Date: 2026-01-22
- Version: v1.10.0
- Original notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.10.0
- Permalink: https://whatsnew.fyi/product/anythingllm/releases/v1.10.0
- Labels: Platforms: Desktop
- **added** — AnythingLLM Desktop Assistant that records meetings without joining and summarizes arbitrary files, powered by NVIDIA Parakeet with custom summary templates, speaker identification, and no rate limits
- **added** — AnythingLLM Mobile app on Google Play that syncs with Cloud, Self-hosted, and Desktop versions
- **added** — Cohere as an agent provider
- **added** — Error Boundary to UI to prevent white-page crashes
- **added** — Auth Token to Ollama Embedding Client
- **changed** — Onboarding now goes straight to home with new workspace in user native language instead of showing Create workspace page
- **changed** — Refactored Workspace file picker to be more performant
- **changed** — Migrated Azure OpenAI to unified v1 API with full agent support and streaming for reasoning models
- **changed** — Upgraded Express.js from 4.18.2 to 4.21.2
- **changed** — Upgraded Multer to 2.0.0
- **changed** — Upgraded MCP SDK to 1.24.3
- **changed** — Migrated to bcryptjs from bcrypt
- **changed** — Docker base image upgraded to Ubuntu 24
- **fixed** — Pagination bug in paperless-ngx data connector
- **fixed** — YouTube scraper breakage caused by undocumented YouTube API changes
- **fixed** — XLSX files dragged and dropped into chat not visible to the model
- **fixed** — MCP paths on non-Windows machines
- **fixed** — Stale user permissions in UI by refreshing user data on app load
- **fixed** — Stale user session with proper fetch error handling
- **fixed** — Unnecessary scrollbar in workspace general appearance settings tab
##### Highlighted Changes
###### AnythingLLM Desktop Assistant is live!
Now, AnythingLLM Desktop is a drop-in replacement for paid tools like Granola, Otter, Fireflies, and more.
- Runs entirely on your device, can record meetings without joining or summarize arbitrary files
- Powered by NVIDIA Parakeet + AnythingLLM's on-device orchastration
- Can call any agent tool, MCP, or anything else you already use with AnythingLLM!
- Custom summary templates, chat with the transcript, and even speaker identification.
- "Joined Meeting" Desktop notification to start a new recording with a click. For any meeting software (Zoom, Slack, Discord, Teams, etc)
- **No rate limits, usage caps, or restrictions**
https://github.com/user-attachments/assets/355ad2fc-cca1-4e9d-8f08-4a1a08dac48d
###### AnythingLLM Mobile is live on Google Play
The [Android AnythingLLM Mobile App](https://play.google.com/store/apps/details?id=com.anythingllm) is live on Google Play now. This syncs with both Cloud/Self-hosted and Desktop versions of AnythingLLM.
https://github.com/user-attachments/assets/e4232dfa-e42e-4d15-af9e-d58f2f0245f9
##### Notable other changes
- Removed onboarding "Create workspace" page -> goes straight to home now with new workspace in user native language
- Refactored Workspace file picker to be more performant
- Migrated Azure OpenAI to unified `v1` api with full agent support
- Fixed Pagination bug in paperless-ngx
- Fixed issue where the undocumented YouTube API changed and broke the YT scraper
- Implemented `Cohere` as an agent provider
- A bump of dependency bumps
- Fixed bug where XSLX files dragged and dropped into chat weren't "visible" to the model
- MCP fixes for paths on non-Windows machines
- Docker image bumps and patches for a healthy Scout score (B)
- Added Error Boundary to UI to prevent white-page crashes
##### What's Changed
* bump `body-parser` patch version by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4746
* Remove bcrypt from collector - not used by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4747
* `jws` bump by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4748
* Refactor WorkspaceFileRow component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4740
* Fix stale user permissions in UI by refreshing user data on app load by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4751
* Docker base image upgrade to Ubuntu 24 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4754
* Bump expressJS from 4.18.2 -> 4.21.2 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4760
* Migrate Azure OpenAI Integration To v1 API | Enable Streaming for Reasoning Models in Azure OpenAI Basic Inference Provider by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4744
* Bump `form-data` version by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4761
* Lazy load Lancedb by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4764
* Migrate to `bcryptjs` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4767
* Refactor frontend legacy JSON.parse with safeJsonParse by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4759
* Fix pagination bug in paperless-ngx data connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4757
* Fix Stale User Session with Proper `fetch` Error Handling by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4770
* Add Auth Token to Ollama Embedding Client by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4766
* Upgrade to Multer 2.0.0 by @angelplusultra in https://github.com/Mintplex-Labs/anythi
_[Truncated at 4000 characters — full notes: https://github.com/Mintplex-Labs/anything-llm/releases/tag/v1.10.0]_