anything-llm version history

# 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 yo

## 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 au

## 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/Mintple

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](h

## 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. <img width="1745" height="1011" alt="queue-embedding" src="https://github.com/user-attachments/assets/ffbd06ad-cd2c-480a-89ba-bb7a0068abbc" /> ### 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 machin

## 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. <img width="1713" height="898" alt="settings-menu-icon-location" src="https://github.com/user-attachments/assets/06d2eb83-6eff-4ab2-92ba-43ecda5e7523" /> ## 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 di

## 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-

## 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. <img width="3680" height="2212" alt="homepage" src="https://github.com/user-attachments/assets/b7b202b1-3a22-42c9-b46e-434b694c2ec5" /> ## Native Tool Calling <Callout type="info"> 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._ </Callout> 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 w

# 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

<img width="2560" height="700" alt="v1 10 0 (1)" src="https://github.com/user-attachments/assets/39285372-787a-4b2d-b493-06e9d8044932" /> ## 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://