AnythingLLM v1.14.1

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

• fix: prevent EventEmitter memory warning in AIbitat agent framework by @simongonzalezdc in #5790
• Remove unused providers by @timothycarambat in #5793
• Patch reloading of embedder and lanceDB connection by @timothycarambat in #5804
• Better API errors by @timothycarambat in #5805
• Mistral Embedding Encoding by @timothycarambat in #5806
• fix: omit temperature param for Bedrock Claude Opus 4.8 by @kimnamu in #5822
• feat: expose requestToolApproval to custom agent skills by @angelplusultra in #5795
• feat: highlight variable references in agent flow blocks by @angelplusultra in #5799
• chat link in chat settings by @timothycarambat in #5837
• WorkspaceChat refactor by @timothycarambat in #5833
• More Frontend optimizations by @timothycarambat in #5838
• Migrate Cohere to OpenAI sdk by @shatfield4 in #5813
• feat: export workspace chat/chat thread to pdf by @shatfield4 in #5800

New Contributors

• @simongonzalezdc made their first contribution in #5790
• @kimnamu made their first contribution in #5822

Full Changelog: v1.14.0...v1.14.1