AnythingLLM

AIDesktop

An all-in-one desktop and Docker app for chatting with your own documents.

Latest v1.15.0 · · Desktopby Mintplex LabsWebsiteMintplex-Labs/anything-llm

Release activity

Release activity — 10 releases across 10 days since Jan 22, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before Jan 22, 2026. Older weeks are hidden at this screen width.
MayJunJulAug
SundayNo releases on Apr 26, 2026No releases on May 3, 2026No releases on May 10, 2026No releases on May 17, 2026No releases on May 24, 2026No releases on May 31, 2026No releases on Jun 7, 2026No releases on Jun 14, 2026No releases on Jun 21, 2026No releases on Jun 28, 2026No releases on Jul 5, 2026No releases on Jul 12, 2026No releases on Jul 19, 2026No releases on Jul 26, 2026No releases on Aug 2, 2026No releases on Aug 9, 2026
MondayNo releases on Apr 27, 2026No releases on May 4, 2026No releases on May 11, 2026No releases on May 18, 2026No releases on May 25, 2026No releases on Jun 1, 2026No releases on Jun 8, 2026No releases on Jun 15, 2026No releases on Jun 22, 2026No releases on Jun 29, 2026No releases on Jul 6, 2026No releases on Jul 13, 2026No releases on Jul 20, 2026No releases on Jul 27, 2026No releases on Aug 3, 2026No releases on Aug 10, 2026
TuesdayNo releases on Apr 28, 2026No releases on May 5, 2026No releases on May 12, 2026No releases on May 19, 20261 release on May 26, 2026No releases on Jun 2, 20261 release on Jun 9, 20261 release on Jun 16, 2026No releases on Jun 23, 2026No releases on Jun 30, 2026No releases on Jul 7, 2026No releases on Jul 14, 2026No releases on Jul 21, 2026No releases on Jul 28, 2026No releases on Aug 4, 2026No releases on Aug 11, 2026
WednesdayNo releases on Apr 29, 2026No releases on May 6, 2026No releases on May 13, 2026No releases on May 20, 2026No releases on May 27, 2026No releases on Jun 3, 2026No releases on Jun 10, 2026No releases on Jun 17, 2026No releases on Jun 24, 2026No releases on Jul 1, 2026No releases on Jul 8, 2026No releases on Jul 15, 2026No releases on Jul 22, 2026No releases on Jul 29, 2026No releases on Aug 5, 2026
ThursdayNo releases on Apr 30, 2026No releases on May 7, 2026No releases on May 14, 2026No releases on May 21, 2026No releases on May 28, 2026No releases on Jun 4, 2026No releases on Jun 11, 2026No releases on Jun 18, 20261 release on Jun 25, 2026No releases on Jul 2, 2026No releases on Jul 9, 2026No releases on Jul 16, 2026No releases on Jul 23, 2026No releases on Jul 30, 2026No releases on Aug 6, 2026
FridayNo releases on May 1, 2026No releases on May 8, 2026No releases on May 15, 2026No releases on May 22, 2026No releases on May 29, 2026No releases on Jun 5, 2026No releases on Jun 12, 2026No releases on Jun 19, 2026No releases on Jun 26, 2026No releases on Jul 3, 2026No releases on Jul 10, 2026No releases on Jul 17, 2026No releases on Jul 24, 2026No releases on Jul 31, 2026No releases on Aug 7, 2026
SaturdayNo releases on May 2, 2026No releases on May 9, 2026No releases on May 16, 2026No releases on May 23, 2026No releases on May 30, 2026No releases on Jun 6, 2026No releases on Jun 13, 2026No releases on Jun 20, 2026No releases on Jun 27, 2026No releases on Jul 4, 2026No releases on Jul 11, 2026No releases on Jul 18, 2026No releases on Jul 25, 2026No releases on Aug 1, 2026No releases on Aug 8, 2026

10 releases since Jan 22, 2026

Changelog

v1.15.0

AnythingLLM v1.15.0

Added 5
  • Magic Echo, a voice-to-text dictation feature that works anywhere on the OS with custom dictionary support and voice commands
  • 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
  • Magic Tab, an autocomplete feature that suggests text as you type in any app, aware of context and available on-device
  • AnythingLLM Pro subscription tier with free daily limits for all Magic Features and no signup required for free tier
  • Query and passage prefix environment variables for the GenericOpenAi embedder
Changed 2
  • Intelligent Tool Selection (ToolReranker) is now enabled by default
  • Chat history cap has been unlocked
Fixed 1
  • 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.

Magic Echo - Docs

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

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

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
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.2...v1.15.0

View originalPermalink
How v1.15.0 went
v1.14.1

AnythingLLM v1.14.1

Added 9
  • Support for Intel, AMD, and NVIDIA GPUs in Meeting Assistant
  • Developer API for transcription on audio via POST /v1/transcription/transcribe
  • Basic Speaker Identification feature for Meeting Assistant
  • Dual channel stereo recordings support for meetings
  • Copy chat link functionality to quickly re-open a chat in the desktop/self-hosted app via deeplinking
  • Audio and video uploads via chat UI using Tinyscribe engine
Changed 4
  • Meeting Assistant binary is 92% smaller and processing times are 15% faster
  • Meeting Assistant context window overflow handling improved for better summarization of longer meetings
  • Linux AppImage size reduced by 91% and now caches Ollama engine downloads for faster startup
  • Cohere SDK removed and ported to OpenAI SDK for compatibility
Fixed 6
  • Meeting Assistant title now auto-updates in UI after summary
  • Text clearing bug when dragging and dropping files into chat with existing prompt text
  • Memory leak in embedder from constantly reloading in server process
  • Desktop Assistant Capture Area not showing on Windows multi-monitor setups
  • Strip thinking from fork thread name when forking a chat that had thoughts
  • Toast light mode always showing regardless of system theme
Removed 1
  • 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.

  • 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.

  • Support for Developer API for transcription on audio (POST: /v1/transcription/transcribe)

  • Meeting Assistant context window overflow handling is much better now - so small models can summarize longer meetings.

  • Introduction of Basic Speaker Identification for 60% better summarizes from any audio.

  • Dual channel stero recordings for meetings now - leading to 80% better speaker identification in "Full Diarization" mode.

Improvements
  • Linux AppImage now 91% smaller in size and caches Ollama engine downloads for faster startup times.
  • Meeting Assistant title fix on meetings post-summary now auto-updates in UI
  • AgentFLow variable highlight so its clear what is and is not a valid variable
  • "Copy chat link" in UI to quickly re-open a chat in the desktop/self-hosted app via deeplinking.
  • Re-enabled audio and video uploads via chat UI - uses Tinyscribe engine now.
  • Export Chat as (PDF, JSON, Markdown, etc) from chat UI.
  • Desktop Assistant Setting - HD screenshots now available for screenshot capture area.
  • Request approval internal function is now available for custom skills.
Bug Fixes
  • Removed DPAIS and HuggingFace providers from AnythingLLM (unmaintained)
  • Fixed memory leak in embedder from it constantly reloading in server process
  • Fixed text clearing bug when dragging and dropping files into the chat and text was already present in prompt.
  • Massive performance improvements to the frontend UI for long running chats.
  • Cohere SDK removed and ported to OpenAI SDK for compatibility.
  • Desktop Assistant Capture Area not showing on windows multi-monitor setups.
  • Strip thinking from fork thread name when forking a chat that had thoughts.
  • Fix toast light mode always showing regardless of system theme.
  • Mistral embedder encoding issue fixed.
  • Better error messages for API
  • Omit temp in Claude Bedrock for Claude 4.8
  • Fixed event emitter leak in server process for web-scraping and summarize process
What's Changed
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.0...v1.14.1

View originalPermalink
How v1.14.1 went
v1.14.0

AnythingLLM v1.14.0

Added 6
  • Cerebras provider support
  • Speech-to-text support for Deepgram, GenericOAI, Lemonade, and OpenAI
  • Text-to-speech support for KokoroTTS
  • 24-hour system variable formats
  • Document sync stale-after interval is now configurable
  • Opt-in deny-by-default for embeds with no allowlist
Changed 6
  • Default chat thread is now killed when creating a new thread, though existing chats on the default thread remain available
  • All model providers are now opt-out of tool calling by default
  • Web-scraping now converts to markdown for better parsing and chat followup tasks with minimal context bloat
  • Summary tool overhauled with better summaries, improved transparency, and confirmation prompts for longer summaries
  • Improvements to the GenericOAI provider
  • Better LaTeX rendering support
Fixed 7
  • Context limit detection issue for agents
  • SearXNG double encoding in search queries
  • Timeouts for all fetch requests
  • Escape illegal XML control characters in word documents and generated documents
  • Windows uninstall now includes checkbox to remove all AnythingLLM data
  • Tray fixes when app starts in background or Desktop Assistant feature is toggled
  • Support Azure and Dell Pro AI Studio providers in agent summarization fallback
Improvements
  • Cerebres provider
  • 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.
  • 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
  • STT Support for Deepgram, GenericOAI, Lemonade, & OpenAI
  • TTS Support for KokoroTTS
  • Web-scraping now will convert to markdown for better parsing and chat followup tasks with minimal context bloat
  • Summary tool was overhauled. Now it will so better summaries with transparency as well as ask before continuing for longer summaries
  • Improvements to the GenericOAI provider
  • 24hour system variable formats
  • Better LaTex rendering support
Bug Fixes
What's Changed
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.13.0...v1.14.0

View originalPermalink
How v1.14.0 went
v1.13.0

AnythingLLM v1.13.0 - A Hybrid AI Experience

Added 8
  • 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
  • Scheduled Jobs feature that automates recurring AI agent tasks on user-defined schedules with visual Cron Builder and no technical knowledge required
  • Automatic memory extraction and personalization that stores memories in a memory bank to personalize AI assistant responses
  • Workspace-specific and global memories that are injected into the system prompt to enhance personalization
  • Support for LLM-classified rules in Model Router that understand intent in plain English
  • Push notifications when scheduled jobs finish execution
  • Complete run history logging for scheduled jobs including agent reasoning, tool calls, and generated files
  • 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 that trigger on keywords, token counts, time of day, or image attachments instantaneously. Or use 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 →

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 platforms require you to trust your data to third parties. AnythingLLM gives you scheduled AI agents that run entirely on your machine, with your data, under your control.

Wake up to a summary of overnight emails. Get weekly progress reports written automatically. Monitor websites for changes. The possibilities are endless, and it all happens while you focus on what matters.

Learn how to create your first scheduled job →

Automatic Memories & Personalization

AnythingLLM now supports automatic memory extraction and personalization so your AI assistant can remember what you've talked about and use that knowledge to personalize its responses.

AnythingLLM runs a background job to extract memories from your chats and store them in a memory bank. This memory bank is then used to personalize the responses of your AI assistant - you have full control over what is remembered and how it is used you can even add memories manually to the memory bank if you dont want to have the model spend cycles reviewing chat history.

There are two types of memories:

  • Workspace memories: These are memories that are specific to the current workspace (like what you are working on, projects-specific information, etc.)
  • Global memories: These are memories that are specific to the entire AnythingLLM instance (like your name, preferences, etc.)

Memories are injected into the system prompt of your AI assistant so it can use them to personalize its responses and are a welcome addition to your AI assistant's knowledge base.

Learn how to enable and manage memories →

Agent Surveys (special tool)

Agent Surveys is a special tool that allows your AI assistant to ask clarifying questions before proceeding. This is useful when you are working with a complex task and the agent needs more information to proceed.

This is off by default and must be enabled in the agent settings. Answers to the questions are saved alongside the chat message so the agent can use them in future turns.

Learn how to enable and manage agent surveys →

What's Changed
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.1...v1.13.0

View originalPermalink
How v1.13.0 went
v1.12.1

AnythingLLM v1.12.1

Added 12
  • Report document embedding process per-document during upload with ability to add, remove, and queue documents without losing progress
  • Built-in Gmail integration for Agent skills
  • Built-in Outlook integration for Agent skills
  • Built-in Google Calendar integration for Agent skills
  • Image lightbox in main UI for chat attachments
  • Korean, Chinese, and Japanese character support for PDF generation
Changed 5
  • Better citations for app integrations
  • DDG default web-search in agent skills
  • Ollama bumped to 0.20.7 with Qwen3.5 and Gemma 4 support
  • Update Lemonade to support 1.10.0 changes
  • Chat ID reported in agent sessions to allow regenerate chats, TTS, and more actions without page reloads
Fixed 11
  • Lemonade throw on embedding failures instead of returning empty
  • Light mode docgen page display
  • Agent flow menu visibility in narrow windows
  • Agent flow toggle state sync
  • Remove illegal characters for Windows on files
  • Preserve Confluence context paths
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:

Other Improvements
  • Image Lightbox in main UI
  • Enabled Korean, Chinese, & Japanese character support for PDF generation via custom mdpdf fork
  • Better citations for app integrations
  • DDG default web-search in agent skills
  • Open documents in native application on machine when generated by Document Generation Agent
  • Auto approve agent skill via ENV setting
  • Ollama bumped to 0.20.7 (Qwen3.5 support, Gemma 4, etc)
  • New Customization > Chat setting for Unload model when closed to unload the model when the user closes the chat window.
  • Generic OpenAI Capability detection/ENV setting
  • Update Lemonade to support 1.10.0 changes
  • Catalan translations
  • Name field added to API keys
  • Chat ID reported in agent sessions so now you can regenerate chats, TTS, and more actions without page reloads.
What's Changed
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.0...v1.12.1

View originalPermalink
How v1.12.1 went
v1.12.0

AnythingLLM v1.12.0

Added 8
  • Automatic mode for native tool calling that uses tools without requiring @agent prefix for supported providers
  • Intelligent Tool Selection feature to load unlimited tools into context with up to 80% token usage reduction
  • Filesystem Agent feature to search files and directories on the host machine
  • Document Generation Agent to create text files, PDFs, Excel files, Docx, and PowerPoint presentations
  • Telegram bot support for Docker and Desktop with text chat, image understanding, voice messages, and workspace selection
  • Lithuanian locale support
  • User-Agent header for Anthropic API calls
  • Optional API key support for Lemonade provider
Changed 6
  • Automatic mode for workspace with Agent mode as default
  • Dynamic max_tokens retrieval for Anthropic models
  • Refactored onboarding welcome screen to v2 design
  • Auto-select newly uploaded documents and URLs in my documents list
  • Redesigned Telegram bot settings UI
  • Updated Exa search provider description
Fixed 3
  • File extension inference from Content-Type for URLs without explicit extensions
  • Firefox LaTeX rendering
  • Chat UI event listener bloat
Major Features
Automatic Mode for native tool calling

For Select providers 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. 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. 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. 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 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
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.2...v1.12.0

View originalPermalink
How v1.12.0 went
v1.11.2

AnythingLLM v1.11.2

Added 9
  • New prompt input in the main chat UI
  • Ability to toggle Agent skills on/off from the prompt
  • Ability to select the provider and model for the workspace without leaving the page
  • Metrics for Agent calls
  • Report document and web-search citations during Agent calls
  • Automatic chat mode with native tool calling support
Changed 3
  • Better Citations UI and reporting
  • Implement v2 chat layout designs
  • Improve zh_TW Traditional Chinese locale
Fixed 5
  • Bug where yarn setup:envs fails if any .env file already exists
  • Show actionable error when LMStudio model listing fails or returns empty
  • Azure OpenAI model key collision
  • Add missing /wiki to Confluence cloud citation URLs
  • Strip thinking from copy message outputs
Removed 2
  • Google web-search Programmable SERP
  • 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.

  • New prompt input
  • Better Citations UI and reporting
  • Metrics for Agent calls
  • Report document and web-search citations during Agent calls!
  • Ability to each toggle on/off Agent skills from the prompt
  • Ability to select the provider and model for the workspace without leaving the page.
What's Changed
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.1...v1.11.2

View originalPermalink
How v1.11.2 went
v1.11.1

AnythingLLM v1.11.1

Added 3
  • Support for multi-step tool calls with native tool calling for local LLM providers
  • First class support for Lemonade by AMD as a local model runtime for LLM, ASR, TTS, and image generation
  • Add dedicated dark theme option with system preference support
Changed 4
  • Redesigned the main AnythingLLM homepage to be more modern and user-friendly for instant chatting after onboarding
  • Overhauled @agent tool calling to leverage native tool calling abilities of LLM providers and models
  • Implemented safeguards for native tool calling with a maximum of 10 tool calls per response to prevent runaway tasks
  • Update light mode UI sidebar
Fixed 5
  • Resolve Gemini agent 400 error on tool call responses
  • Fix GitLab connector infinite loop and rate limit crash for large repositories
  • Fix event listener memory leak in useIsDisabled hook
  • Prevent CMD/CTRL+Arrow scroll from overriding textarea cursor movement
  • 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

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 environment variable.

PROVIDER_SUPPORTS_NATIVE_TOOL_CALLING="bedrock,generic-openai,groq,lemonade,litellm,local-ai,openrouter"
Lemonade by AMD Integration

Lemonade by AMD is an open-source 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
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.0...v1.11.1

View originalPermalink
How v1.11.1 went
v1.11.0

AnythingLLM v1.11.0

Added 8
  • 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
  • Add keyboard shortcuts to scroll to top and bottom of chat history
  • Support PrivateModeAI Integration
  • Add ability to edit existing SQL agent connections
  • SambaNova Integration
  • Web push notifications
  • UAE region support for bedrock models
  • Add support for custom headers for LLM Generic OpenAI
Changed 10
  • Refine and standardize username constraints
  • New login page UI
  • Persist Ollama context preferences in LC tools
  • Refactor Ollama context window setting
  • Patch AzureOpenAI tool calling from function to tool
  • Manage onboarding decision via DB flag
Fixed 3
  • Fix sidebar thread layer
  • Clean username already exists error
  • 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
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.10.0...v1.11.0

View originalPermalink
How v1.11.0 went
v1.10.0

AnythingLLM v1.10.0

Added 5
  • 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
  • AnythingLLM Mobile app on Google Play that syncs with Cloud, Self-hosted, and Desktop versions
  • Cohere as an agent provider
  • Error Boundary to UI to prevent white-page crashes
  • Auth Token to Ollama Embedding Client
Changed 8
  • Onboarding now goes straight to home with new workspace in user native language instead of showing Create workspace page
  • Refactored Workspace file picker to be more performant
  • Migrated Azure OpenAI to unified v1 API with full agent support and streaming for reasoning models
  • Upgraded Express.js from 4.18.2 to 4.21.2
  • Upgraded Multer to 2.0.0
  • Upgraded MCP SDK to 1.24.3
  • Migrated to bcryptjs from bcrypt
  • Docker base image upgraded to Ubuntu 24
Fixed 7
  • Pagination bug in paperless-ngx data connector
  • YouTube scraper breakage caused by undocumented YouTube API changes
  • XLSX files dragged and dropped into chat not visible to the model
  • MCP paths on non-Windows machines
  • Stale user permissions in UI by refreshing user data on app load
  • Stale user session with proper fetch error handling
  • 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 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
New Contributors

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.1...v1.10.0

View originalPermalink
How v1.10.0 went

More in AI

View all
Jan

Run large language models locally, offline.

Menlo Research
Devin Desktop

The agentic IDE formerly released as Windsurf.

Cognition
Kimi Code

A terminal coding agent from the makers of Kimi.

Moonshot AI
codex

codex release notes.

codex
Ollama

Get up and running with large language models locally.

Ollama
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openclaw

Discussion