⌕
AnythingLLM

AnythingLLM 1.19.0

開源本地 AI 助手,文件餵給模型離線問答。

WindowsMIT
发布 2026-10-26 · 核验 2026-11-16
立即下载

软件简介

AnythingLLM 把 PDF、網頁與筆記建成私有知識庫,搭配本地模型或雲端 API 問答,支援多模型、多助手與 Agent 工具調用。

功能特点

  • 本地知識庫問答
  • 支援本地模型
  • 多模型與多助手
  • Agent 工具調用
更新日志 · 1.19.0

Built-in LLM for Docker

<img width="3680" height="2212" alt="AnythingLLM Docker built-in LLM powered by Lemonade and llama.cpp" src="https://github.com/user-attachments/assets/410b5784-ca15-4027-a1c4-056d9d5c748e" />

AnythingLLM Docker now has a default local LLM experience right out of the box. The same kind of built-in engine that ships with AnythingLLM Desktop can now run inside the container: Lemonade, the fully open-source local inference server from AMD, running your models with llama.cpp. You no longer need to run Ollama, LM Studio or any other inference server next to AnythingLLM.

Pass your GPU into the container and the engine is accelerated on whatever hardware you have. It picks the fastest backend automatically: CUDA for NVIDIA GPUs, Vulkan for AMD and Intel GPUs, or the CPU. It runs on both amd64 and arm64 hosts.

When it's turned on, Built-in becomes the default LLM provider during onboarding, with three models recommended for your hardware. You can download any model from the model table or pull any GGUF model from Hugging Face. It works everywhere a provider can be used: the system LLM, workspace and agent LLMs, the chat window model picker, and Model Router.

> [!TIP]

> The built-in LLM is off by default. Turn it on by starting the container with -e ENABLE_BUILT_IN_LLM=true, and add --gpus all (or pass in your AMD or Intel GPU devices) for GPU acceleration. See Built-in LLM for Docker for the full setup for each kind of hardware.

Color palettes

Color palettes are straightforward thematic tinting you can apply to the entire UI. We plan to expand this functionality more so you can more heavily customize the UI and even layout. Learn more

<table>

<tr>

<td><img width="100%" alt="Ocean color palette" src="https://github.com/user-attachments/assets/08c2baa2-9a9b-4ecd-ae95-88e88175ffe5" /></td>

<td><img width="100%" alt="Forest color palette" src="https://github.com/user-attachments/assets/4274998a-dba8-490e-ab5d-9faecf9248c4" /></td>

</tr>

<tr>

<td><img width="100%" alt="Plum color palette" src="https://github.com/user-attachments/assets/214c3571-7d72-4111-bf08-ce3d60ff1b99" /></td>

<td><img width="100%" alt="Ember color palette" src="https://github.com/user-attachments/assets/88449231-139c-40a3-bb49-135bd0f1e9fa" /></td>

</tr>

</table>

----

What's Changed

  • fix: route Bedrock India (in.) inference profiles via bedrock-runtime by @kimnamu in https://github.com/Mintplex-Labs/anything-llm/pull/6717
  • Remove open-computer (moved to its own repo) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6727
  • Neutralize spreadsheet formulas in CSV chat exports by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6728
  • Cap request body size to prevent unauthenticated embed DoS by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6729
  • feat: show notice when response hits max output token limit (#6703) by @ManojDevarajulu in https://github.com/Mintplex-Labs/anything-llm/pull/6726
  • Hold clarifying-question timeout once the user starts answering by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6730
  • Move Weaviate to weaviate-client v3 by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6675
  • Support .mov files for transcription by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6721
  • Stop system prompt variable values from expanding other placeholders by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6731
  • Apply workspace model changes to agent sessions mid-thread by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6673
  • Show per-file embed progress in context overflow modal by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6639
  • fix: include email body/recipients and job prompt in tool approval requests by @rtmalikian in https://github.com/Mintplex-Labs/anything-llm/pull/6732
  • fix: send the full GitLab branch name when fetching repository files by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6740
  • fix: return MCP tool text without the result envelope by @Sairaj-24 in https://github.com/Mintplex-Labs/anything-llm/pull/6736
  • Fix prompt compressor crash on history records skipped by convertToPromptHistory (#6737) by @ManojDevarajulu in https://github.com/Mintplex-Labs/anything-llm/pull/6738
  • fix: keep current-turn attachments when the string compressor runs by @devYRPauli in https://github.com/Mintplex-Labs/anything-llm/pull/6742
  • Stop sending deprecated sampling and thinking params to Gemini by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6733
  • fix: count the text of messages with attachments in statsFrom by @devYRPauli in https://github.com/Mintplex-Labs/anything-llm/pull/6745
  • Built-in LLM for Docker (embedded_lemonade) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6719
  • fix: truncate long citation URLs in the detail modal by @leilei3167 in https://github.com/Mintplex-Labs/anything-llm/pull/6781
  • fix: default OpenAI image generation to gpt-image-2.5-flare by @rtmalikian in https://github.com/Mintplex-Labs/anything-llm/pull/6780
  • fix: keep conversation history when the OpenAI compatible chat prompt is compressed by @MarMarLabs in https://github.com/Mintplex-Labs/anything-llm/pull/6777
  • fix: tell the user why a password reset was refused by @MarMarLabs in https://github.com/Mintplex-Labs/anything-llm/pull/6771
  • fix: report empty connector imports as failures by

下载地址

官方下载直接指向软件作者的发布地址;网盘镜像为同一文件的转存,下载后可用 SHA-256 核对(官方未提供校验值的文件除外)。

  • Windows x64 · 安裝包AnythingLLMDesktop.exe · 384.6 MB

相关推荐