LoginSign Up
← Back to all sparks
A

AnythingLLM

AI-ASSISTANTS
Velocity6.3

All-in-one private AI desktop and Docker app that lets you chat with any LLM and your own documents.

anythingllm.com ↗

AnythingLLM breaks out of the app: on-device Magic Features go OS-wide, and a Pro tier appears.

local-first-aion-device-agentsos-wide-assistantmonetizationmeeting-assistanthybrid-routing
◆Current state
AnythingLLM is a local-first AI assistant shipping at a fast clip. The v1.15.0 desktop release is a genuine departure: Magic Features (Echo dictation, Beacon highlight-to-act, Tab autocomplete) now work in any app, fully on-device, and a new AnythingLLM Pro tier introduces paid limits on top of a free daily tier. Recent releases also overhauled the Meeting Assistant for multi-GPU support and added a stack of new model providers and STT/TTS engines.
◆Where it's heading
The product is expanding from an in-app RAG and chat tool into a full on-device AI agent platform that operates across the whole OS. The arc is clear: native tool calling, then a hybrid local-cloud Model Router plus Scheduled Jobs and automatic memories (v1.13), then a leaner Meeting Assistant with diarization (v1.14.1), now OS-wide Magic Features and a monetization tier (v1.15). The positioning is explicitly privacy-first, pitched against cloud tools like Grammarly and SuperWhisper.
◆Prediction
The 1.14.2 notes reference a 2.0.0-preview, so expect a 2.0 desktop release consolidating the OS-wide agent direction, more Magic/OS-level surfaces, and expansion of the Pro tier's paid features. Provider breadth and on-device performance look like continuing themes.

◆Recent moves

  1. 1d ago

    OS-wide Magic Features and the AnythingLLM Pro tier (v1.15.0)

    ⚡ SPARK

    v1.15.0 takes AnythingLLM out of its own window: Magic Echo (dictation), Magic Beacon (highlight-to-act with full agent/MCP access), and Magic Tab (autocomplete) now work in any app, fully on-device, alongside a new AnythingLLM Pro tier. It reframes the product as an OS-wide agent and adds its first paid layer.

    View source ↗
  2. 4d ago

    Pre-1.15 patches: Brave/fastCRW search, Groq STT (1.14.2)

    A pre-1.15 patch release migrating the AWS SDK to OpenAI, adding Groq STT, Brave Search and fastCRW web-search providers, and fixing temperature handling for Opus 4.7/4.8. Provider-breadth and maintenance work staging the larger 1.15 release.

    View source ↗
  3. 10d ago

    Meeting Assistant overhaul: multi-GPU, diarization, API (1.14.1)

    A substantial Meeting Assistant overhaul: Intel/AMD/NVIDIA GPU support for a 92% smaller binary and 15% faster processing, a transcription API endpoint, basic speaker identification, and dual-channel diarization, plus chat export and other fixes. A major efficiency-and-capability upgrade to an existing feature.

    View source ↗
  4. 18d ago

    Tool-calling on by default, Cerebras, new STT/TTS engines (1.14.0)

    v1.14.0 makes native tool calling opt-out by default, adds the Cerebras provider and new STT (Deepgram, OpenAI) and TTS (KokoroTTS) engines, and converts web-scraping output to markdown. Broad agent and provider improvements that smooth the path toward fully automatic tool use.

    View source ↗
  5. 1mo ago

    AnythingLLM v1.13.0 - A Hybrid AI Experience

    ⚡ SPARK

    v1.13.0 introduced the Model Router for user-defined hybrid local-cloud routing per message, Scheduled Jobs for cron-driven background agents, automatic memories/personalization, and agent surveys. It is the release that turned AnythingLLM from a chat app into an automated, hybrid agent platform — the foundation the OS-wide 1.15 work builds on.

    View source ↗
  6. 2mo ago

    Gmail/Outlook/Calendar agent skills, streamed embedding (1.12.1)

    v1.12.1 added streamed per-document embedding with a non-blocking queue and built-in Gmail, Outlook, and Google Calendar agent skills, plus PDF language support and quality-of-life fixes. Integration breadth and embedding UX that broaden what the agent can reach.

    View source ↗