LoginSign Up
← Back to all sparks
A

AnythingLLM

AI-ASSISTANTS
Velocity2.5

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

anythingllm.com ↗

After going OS-wide, AnythingLLM turns back inward — image generation and the unglamorous fixes power users notice.

image-generationlocal-firstagent-toolingfile-managementprovider-breadthdesktop
◆Current state
v1.16.0 adds image generation through /img on any configured provider, including attachments for edits and combination prompts, and pairs it with file-picker work: folder drag-and-drop that preserves hierarchy, lazy loading for large document sets, and a URL fetcher that stops demanding an explicit scheme. Two long-standing annoyances are gone — tools can be toggled mid-session without restarting an agentic chat, and aborting a response now actually kills the inference rather than leaving it running. This follows the 1.15 release that pushed the assistant out of its own window and introduced the Pro tier.
◆Where it's heading
The project alternates between reach and repair. The 1.13 through 1.15 arc expanded where the assistant lives — hybrid routing, scheduled agents, then OS-wide Magic Features and a paid tier — and 1.16 spends its effort on modality breadth plus the correctness of what already exists. Image generation arrives routed through whatever provider the user has configured, which is consistent with how the project has always added capability: wire up the ecosystem rather than build the model. The changelog explicitly defers agent-tool image generation to the next release.
◆Prediction
Image generation should move from a slash command into the agent tool surface next, since the release notes name it directly, and the recursive folder import that 1.16 stops short of is the obvious completion of the file-picker work. Whether the Pro tier gains features beyond limit removal is not something these entries indicate.

◆Recent moves

  1. 6d ago

    Image generation via /img, folder drag-and-drop, real abort

    v1.16.0 adds image generation via /img on supported providers, with attachments for edits and follow-ups, plus folder drag-and-drop that preserves hierarchy and lazy loading for large document sets. Two fixes matter more than they look: tools can be toggled mid-session, and aborting a response now genuinely terminates the inference instead of letting it run on. New modality, but routed through existing providers rather than changing the product's direction.

    View source ↗
  2. 1mo 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 ↗
  3. 1mo 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 ↗
  4. 2mo 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 ↗
  5. 2mo 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 ↗
  6. 2mo 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 ↗