AnythingLLM v1.7.4 & the No-code Agent skill builder!

The no-code agent skill builder is live ⚡

Big changes

🏗️ The built-in no-code agent flow builder is alive!

Now, without a line of code you can seamlessly draft and run agentic skills that just make sense. No confusing setup - just AI skills on steroids, fully local and about 1000x easier to understand than MCP.

Read the docs on making your first skill ->

OCR scanning of PDF and images is live!

Now, when Anythingllm is given an image or nondigitized PDF we will automatically OCR the text content into a document. This is done via a local Tesseract model running in process!

this is OCR, not "vision" so if the content has no text - nothing will be found!

Lastly, we skipped a few Docker versions to make Docker <=> Desktop the same release version. It was confusing have two different semantic versions. They will now be lock-step going forward.

All the other fixes 🔧

• Enable include_reasoning in request by @timothycarambat in #3067
• parse streams from reasoning_content from DeepSeek API by @timothycarambat in #3068
• Add tokenizer improvements via Singleton class and estimation by @timothycarambat in #3072
• autodetect parseable text file contents by @timothycarambat in #3079
• inherit font size from UI for thoughts by @timothycarambat in #3099
• Enable consistent styling on chart items by @timothycarambat in #3126
• Add reasoning flag for azure models with "default" fallback by @timothycarambat in #3128
• Enable num_ctx to match defined chunk length in ollama embedder by @timothycarambat in #3129
• Patch PPLX streaming for timeouts by @timothycarambat in #3130
• Add improved logging and introspection to web-browsing by @timothycarambat in #3140
• [FEAT] Add Turkish Language Support (tr.js) #3108 by @TunahanDilercan in #3141
• [CHORE] Onboarding language translations by @timothycarambat in #3176
• fix UserMenu rendered twice on Main page by @sdeleeuw in #3110
• Add handling to reasoning models for Generic OpenAI connector by @timothycarambat in #3183
• Agent flow builder by @shatfield4 in #3077
• chore: rename Github to GitHub by @setchy in #3199
• chore: rename Gitlab to GitLab by @setchy in #3200
• Add querySelectorAll capability to web-scraping block by @timothycarambat in #3186
• Turkish translations by @cobanov in #3207
• OCR PDFs as fallback during upload by @timothycarambat in #3204
• Add OCR of image support by @timothycarambat in #3219
• feat(dataconnectors): support confluence personal access token by @lcgash in #3206
• fix agent builder move block bug by @shatfield4 in #3220
• Drop Node canvas for manual sharp conversion by @timothycarambat in #3221
• for projects in gitlab subgroup (#3075) by @t2tx in #3247
• Fix: fix text and format issues in Chinese documentation. by @alongLFB in #3249
• fix: sanitizeNamespace by @hakeemsyd in #3246
• fix: Patch agent flow to honor agent handler established provider by @timothycarambat in #3251

New Contributors

• @TunahanDilercan made their first contribution in #3141
• @sdeleeuw made their first contribution in #3110
• @setchy made their first contribution in #3199
• @cobanov made their first contribution in #3207
• @lcgash made their first contribution in #3206
• @t2tx made their first contribution in #3247
• @alongLFB made their first contribution in #3249

Full Changelog: v1.4.0...v1.7.4

AnythingLLM 1.4.0

🧠 AnythingLLM is <think>ing....

Note

Desktop build of this release (1.7.3) are attached as binaries below

Notable changes 🌟

• Better Agent calling UI

• UI support for <think>ing models in chat response

Misc Fixes and improvements 🔧

• Add Support for NVIDIA NIM by @timothycarambat in #2766
• update chat model filters for openai by @timothycarambat in #2803
• Fixed a typo in README by @logscore in #2805
• Fix scraping failed bug in link/bulk link scrapers by @shatfield4 in #2807
• Fix timestamp bug in embed widget by @shatfield4 in #2806
• Redirect to default thread on thread deletion by @shatfield4 in #2808
• Add support for hiding sidebar by @timothycarambat in #2809
• Add vector search API endpoint by @timothycarambat in #2815
• patch ZH typo by @timothycarambat in #2816
• add Gitlab to watchable documents by @timothycarambat in #2817
• Fix(2753): Replace React Router Navigate with window.location for SSO state refresh by @andydev404 in #2818
• Docker Scout CI error by @timothycarambat in #2820
• APIPie LLM provider improvements by @shatfield4 in #2695
• Add thread name to workspaces get endpoint by @shatfield4 in #2822
• Add new workspace user management endpoint by @timothycarambat in #2842
• Add attachments to GenericOpenAI prompt by @wolfganghuse in #2831
• Purge cached docs and remove docs from all workspaces on vectorDB/embedder changes by @shatfield4 in #2819
• LLM performance metric tracking by @timothycarambat in #2825
• Append writable fields to dev API new workspace endpoint by @shatfield4 in #2843
• Enable default roles to be able to use attachments but not upload documents by @timothycarambat in #2860
• Add support for gemini authenticated models endpoint by @timothycarambat in #2868
• Remove fine-tuning flow by @timothycarambat in #2872
• fix wrong metadata assignment in MilvusProvider by @wolfganghuse in #2870
• update ollama performance mode by @timothycarambat in #2874
• Fix light mode table colors by @shatfield4 in #2873
• Fix styles of ChangeWarningModal by @shatfield4 in #2876
• Show scrollbar on rendered tables in chat by @shatfield4 in #2884
• Fix typo in frontend for SearXNG agent setup by @shatfield4 in #2917
• Normalize paths on files uploaded to prevent arbitrary file writes by @shatfield4 in #2905
• Patch unauthorized access to other user's pfps by @shatfield4 in #2904
• Audio file validations by @shatfield4 in #2902
• Patch custom models endpoint by @shatfield4 in #2903
• Add support for Google Generative AI (Gemini) embedder by @007900 in #2895
• Return timestamps in OpenAI compat endpoints in proper format by @timothycarambat in #2921
• Update README.md by @KPCOFGS in #2924
• make similarityResponse object arguments and not positional by @timothycarambat in #2930
• Reranker option for RAG by @timothycarambat in #2929
• Update example ENV files by @shatfield4 in #2931
• feat: add support for voyage-3-large and voyage-code-3 embedding models by @root-reindeer-flotilla in #2955
• Add caching to Gemini /models by @timothycarambat in #2969
• Support historical message image inputs/attachments for n+1 queries by @timothycarambat in #2919
• Swap to GH arm64 runner by @timothycarambat in #2980
• Fix similarity score bug in lance/chroma dbs by @shatfield4 in #2986
• Farsi (Persian) translations by @okaeiz in #2989
• AI agent ui animation by @timothycarambat in #2999
• Display thinking in the prompt response - model agnostic by @timothycarambat in #3001
• Fix stop generation button UI by @shatfield4 in #3011
• Bump perplexity models by @shatfield4 in #3014
• Dynamic fetching of TogetherAI models by @shatfield4 in #3017
• Add Version to AzureOpenAI by @timothycarambat in #3023
• Allow editing of LLM settings from workspace settings by @shatfield4 in #2865
• feat: update novita AI logo and default model by @jasonhp in #3037
• [Chore] Add better data-handling for unknown providers by @timothycarambat in #3026
• breakout latex plugin for delims by @timothycarambat in #3040
• Remove native LLM option by @shatfield4 in #3024
• Add ability to disable default agent skills by @timothycarambat in #3041

New Contributors

• @logscore made their first contribution in #2805
• @andydev404 made their first contribution in #2818
• @wolfganghuse made their first contribution in #2831
• @007900 made their first contribution in #2895
• @root-reindeer-flotilla made their first contribution in #2955
• @okaeiz made their first contribution in #2989
• @jasonhp made their first contribution in #3037

Full Changelog: v1.3.0...v1.4.0

AnythingLLM v1.3.0 | UI overhaul + Community Hub is live

The AnythingLLM Community hub is live!

The AnythingLLM Community Hub is a platform that works inside of AnythingLLM to easy share and import community create system prompts, slash commands, and agent skills. Everything on the community hub can be shared publicly with everyone or only privately with your team.

In the near future, we will be enabling:

• Workspace sharing
• Data Connectors
• Authentication flows

Learn more about the community hub and how to pull in or upload your own content to share with others.

Other notable changes

AnythingLLM now has an official Dark and light mode. This is going to pave the way for more custom theme options in the future.

All Changes

• Patch v1/document/upload filename charset encoding by @timothycarambat in #2535
• Simple SSO feature for login flows from external services by @timothycarambat in #2553
• add sessionToken validation connection auth for AWSbedrock by @timothycarambat in #2554
• Feature/update api example outputs by @MrSimonC in #2547
• Add optional limit and orderBy to dev api chat endpoint by @shatfield4 in #2559
• Allow 127.0.0.1 as valid URL for scraping by @shatfield4 in #2560
• 2488 novita ai llm integration by @timothycarambat in #2582
• Add header static class for metadata assembly by @timothycarambat in #2567
• DuckDuckGo web search agent skill support by @shatfield4 in #2584
• Added translation dutch (nl) by @MelroyB in #2595
• Update GitLab PAT token url by @GabLeRoux in #2598
• Fix the problem of web-searching can not complete searching sessions when using bing search. by @fiyen in #2611
• Handle OpenAI whisper transcription edge case by @shatfield4 in #2621
• Fix chat window scrollbar appearance option by @shatfield4 in #2589
• Add undo/redo functionality #2591 by @timothycarambat in #2623
• Frontend performance improvements by @timothycarambat in #2627
• Patch bad models endpoint path in LM Studio embedding engine by @shatfield4 in #2628
• Bump TogetherAI models by @shatfield4 in #2645
• Light/dark mode UI overhaul by @shatfield4 in #2629
• Pr 2660 branch by @timothycarambat in #2662
• Add more expiermental models from Gemini by @timothycarambat in #2663
• Add plaintext file extensions by @timothycarambat in #2664
• TogetherAI Llama 3.2 vision models support by @shatfield4 in #2666
• Mistral embedding engine support by @shatfield4 in #2667
• Pr 2653 branch by @timothycarambat in #2672
• feat: support setting maxConcurrentChunks for Generic OpenAI embedder by @hdelossantos in #2655
• Adjustable font size in chat input by @shatfield4 in #2692
• ✨ feat: Add Vietnamese translations and configuration by @bibo318 in #2641
• Fix typo with GCP deploy guideline by @TuanBC in #2718
• Fix markdown issue where type is missing in backticks by @timothycarambat in #2719
• Normalize Input Fields by @timothycarambat in #2720
• Community hub integration by @shatfield4 in #2555
• Community hub integration UX improvements by @shatfield4 in #2727

New Contributors

• @MelroyB made their first contribution in #2595
• @GabLeRoux made their first contribution in #2598
• @fiyen made their first contribution in #2611
• @hdelossantos made their first contribution in #2655
• @bibo318 made their first contribution in #2641
• @TuanBC made their first contribution in #2718

Full Changelog: v1.2.4...v1.3.0

AnythingLLM Docker v1.2.4

What's Changed

• hide config for agent skills to manager (perm not allowed) by @timothycarambat in #2469
• Integrate Apipie support directly by @timothycarambat in #2470
• LiteLLM agent support by @shatfield4 in #2460
• Pasting text bug fix by @shatfield4 in #2425
• Fix file name/folder name truncation by @shatfield4 in #2456
• Daily message limit per user by @shatfield4 in #2417
• Add backfilling on query for chat widget to improve UX by @timothycarambat in #2482
• Support free-form input for workspace model for providers with no /models endpoint by @shatfield4 in #2397
• OpenAI o1 model support by @shatfield4 in #2427
• Tts open ai compatible endpoints by @timothycarambat in #2487
• Handle Bedrock models that cannot use system prompts by @timothycarambat in #2489
• Handle non-ascii characters in single and bulk link scraper URLs by @shatfield4 in #2495
• Passthrough agentModel for LMStudio by @timothycarambat in #2499
• Patch DNDFilePicker useEffect callback by @timothycarambat in #2506
• Add Groq vision preview support by @timothycarambat in #2511
• Feature/thread creation slug name by @timothycarambat in #2512
• Enable the ability to disable the chat history UI by @timothycarambat in #2501
• Fix tooling examples by @timothycarambat in #2513
• Rework failover agent invocation selection for agent and ephemmeral agent by @timothycarambat in #2515
• Github data connector improvements by @shatfield4 in #2439
• Add Grok/XAI support for LLM & agents by @timothycarambat in #2517
• Alignment crime fixed by @James-Lu-none in #2528
• Add filtering to sessionID for workspace chats by @timothycarambat in #2531

New Contributors

• @James-Lu-none made their first contribution in #2528

Full Changelog: v1.2.3...v1.2.4

Pinned Desktop version: v1.6.8

AnythingLLM v1.2.3

Notable Changes

• Support @agent custom skills in developer API calls by @timothycarambat in #2280

• Add ability to copy/paste images, files, and text from web, local, or otherwise by @timothycarambat in #2326

• Support more Confluence URL formats by @shatfield4 in #2118

• Tavily search web search agent support by @shatfield4 in #2395

• Support XLSX files by @shatfield4 in #2403

What's Changed

• Patch missing folder autogenerate for plugins by @timothycarambat in #2273
• bump Perplexity models by @timothycarambat in #2275
• Make userId actually optional for workspaceThread endpoint by @timothycarambat in #2276
• Patch UI bug with agent skill web-search and sql-connector by @timothycarambat in #2282
• Patch 11Labs selection UI bug by @timothycarambat in #2284
• 1943 add fireworksai support by @timothycarambat in #2300
• Appearance setting for show/hide scroll bar on chat window by @shatfield4 in #2187
• Fix gitlab data connector for self-hosted instances (#2315) by @blazeyo in #2316
• Add more verbose error messages in embed chat by @shatfield4 in #2306
• Load all branches in gitlab data connector by @timothycarambat in #2325
• Fix custom domain in confluence by @shatfield4 in #2328
• Enable Mistral Multimodal by @timothycarambat in #2343
• Added JSONSchema for plugin.json files by @Jaid in #2344
• Make streaming behavior more natural by @shatfield4 in #2336
• Add select/unselect all context menu to directory component by @shatfield4 in #2337
• PR#2355 Continued + expanded scope by @timothycarambat in #2365
• Export embedded chat history by @shatfield4 in #2329
• Improve remove document UX by @shatfield4 in #2359
• Workspace agent autoselection by @shatfield4 in #2357
• Support attachments in developer API by @shatfield4 in #2373
• 1417 completion timeout by @timothycarambat in #2374
• Add dropdown for confluence connector deployment by @timothycarambat in #2376
• Added an option to fetch issues from gitlab. Made the file fetching a… by @blazeyo in #2335
• 1959 filetype filters by @timothycarambat in #2378
• Support DeepSeek by @shatfield4 in #2377
• Patch bug with pasted text not being detected by @timothycarambat in #2386
• [FEAT] Add Llama 3.2 models to Fireworks AI's LLM selection dropdown by @a4v2d4 in #2384
• Added voyage-3 and voyage-3-lite. by @blazeyo in #2394
• Add 3GB file size limit to body parser middlewares by @blazeyo in #2390
• Add exception handling for special case files like Dockerfile and Jenkinsfile by @timothycarambat in #2410

New Contributors

• @blazeyo made their first contribution in #2316
• @Jaid made their first contribution in #2344
• @a4v2d4 made their first contribution in #2384

Full Changelog: v1.2.2...v1.2.3

AnythingLLM v.1.2.2 | The custom agent skill release!

🥳 Big Changes

• Custom Agent Skills: Create fully custom agent skills to extend the capabilities of your @agent invocations. If it can be done in NodeJS - you can do it here.

• AnythingLLM Browser Extension: Send and embed information from the web directly to AnythingLLM or embed directly into your workspaces for later! This can allow you to even scrape data from password protected, VPN protected, or otherwise non-public webpages

• You can now use @agent to run skills via the developer API. (nice)

What's Changed

• Update common.js by @hejp001 in #2148
• Refactor api endpoint chat handler to its own function by @timothycarambat in #2157
• Api session id support by @timothycarambat in #2158
• Enabled use of @agent (and skills) via dev API calls by @timothycarambat in #2161
• Move embed to submodule by @timothycarambat in #2163
• Update common.js by @hejp001 in #2165
• Add RAG agent plugin to API agent by @timothycarambat in #2171
• feat: Added Elestio as one-click deploy option by @kaiwalyakoparkar in #2168
• Update common.js by @hejp001 in #2179
• Support gpt-4o for Azure deployments by @timothycarambat in #2182
• Mobile render fix by @jeffscottward in #2176
• AnythingLLM Chrome Extension by @timothycarambat in #2066
• handle onblur for emebed domains by @timothycarambat in #2199
• Add new Voyage AI embedding models by @shatfield4 in #2193
• Bug/make swagger json output openapi 3 compliant by @MrSimonC in #2219
• Feature/use escape key to close documents modal by @timothycarambat in #2222
• Feature/add searchapi web browsing by @timothycarambat in #2224
• fixed the typo in LLMs by @amrrs in #2225
• Ollama sequential embedding by @timothycarambat in #2230
• remove Jazzicons & Add default pfps by @timothycarambat in #2233
• update docs showing no need for manual port forwarding of Server in G… by @MrSimonC in #2247
• match user prompts exactly not partially by @MrSimonC in #2245
• Milvus bug fix by @shatfield4 in #2183
• Fix UI for slash cmd presets by @shatfield4 in #2260
• Add support for custom agent skills via plugins by @timothycarambat in #2202
• Add Gemini exp models by @timothycarambat in #2268
• Update OpenAI models and prices #2261 by @timothycarambat in #2269
• UI Cleanup by @timothycarambat in #2270

New Contributors

• @hejp001 made their first contribution in #2148
• @kaiwalyakoparkar made their first contribution in #2168
• @jeffscottward made their first contribution in #2176
• @amrrs made their first contribution in #2225

Full Changelog: v1.2.1...v1.2.2

this version correlates with desktop v.1.6.5

AnythingLLM v1.2.1

What's Changed

• Slash commands edit bug fix by @shatfield4 in #2073
• Populate .env file using variable inside userdata script by @saravanan30erd in #2075
• add exp model to v1Beta by @timothycarambat in #2082
• #2084 Support Go filetype by @leaanthony in #2085
• Update the display to show 95% of the width on small screens, else 635px by @MrSimonC in #2089
• Fix depth handling in bulk link scraper by @shatfield4 in #2096
• Finetune ui improvements by @shatfield4 in #2053
• Improve search of document picker by @shatfield4 in #2097
• Auto URL detection for localai by @shatfield4 in #2083
• Add prompt window limits for gpt-4o-* models by @mPyKen in #2104
• fix(Dockerfile): remove hardcoded exposed port by @kabaluyot in #2106
• Encryption in JWT for single-user password mode by @timothycarambat in #2111
• Fix TypeError by replacing this.openai.createChatCompletion with the correct function call by @shaharhi in #2117
• Agent Context window + context window refactor. by @timothycarambat in #2126
• Fix markdown styling for rendered images by @shatfield4 in #2125
• Fix tooltip showing on both sides of file picker by @shatfield4 in #2124
• Omit invalid response.text values and prompts by @timothycarambat in #2127
• Fix multi-user setup bug for invalid username/password by @shatfield4 in #2130
• Allow readable username passed in script widget by @timothycarambat in #2131
• Support suggestions of messages for empty chat in widget by @timothycarambat in #2133
• Added Hebrew language by @timothycarambat in #2143

New Contributors

• @saravanan30erd made their first contribution in #2075
• @leaanthony made their first contribution in #2085
• @mPyKen made their first contribution in #2104
• @kabaluyot made their first contribution in #2106
• @shaharhi made their first contribution in #2117

Full Changelog: v1.2.0...v1.2.1

Desktop Version Pin: v1.6.4

AnythingLLM v1.2.0

New features

• Full PiperTTS for in-browser text-to-speech with over 100+ voices (s/o to @rhasspy & @diffusion-studio for MIT work & base-fork of NPM package)
• Full Portuguese by @im-ramon
• Full German Translation
• Multiple /slash command expansion in prompts by @shatfield4
• MathJax/KaTeX/LaTeX support in responses

Fixes & others

• Fix typo by @martincenturion in #2041
• 2034 automate port forwarding for GitHub codespaces using gh cli by @MrSimonC in #2035
• Youtube loader whitespace fix by @shatfield4 in #2051
• 2049 remove break that prevents fetching files from gitlab repo by @mehmetunlu in #2050
• Hide upload element for default role users by @timothycarambat in #2061
• New user account validations by @shatfield4 in #2037
• Developer API access for embed chat widgets by @shatfield4 in #1999
• Speech to text hotkey by @Rrojaski in #1771

New Contributors

• @martincenturion made their first contribution in #2041
• @MrSimonC made their first contribution in #2035
• @im-ramon made their first contribution in #2054
• @mehmetunlu made their first contribution in #2050
• @Rrojaski made their first contribution in #1771

Desktop version pin: v1.6.1

Full Changelog: v1.1.1...v1.2.0

AnythingLLM v1.1.1

What's Changed

• Gemini Pro 1.5, API support for 2M context and new experimental model by @RahSwe in #2031
• Added Italian translation by @rglauco in #2025
• handle OpenRouter exceptions on streaming by @timothycarambat in #2033
• Ollama performance mode option by @shatfield4 in #2014

New Contributors

• @RahSwe made their first contribution in #2031
• @rglauco made their first contribution in #2025

Full Changelog: v1.1.0...v1.1.1

AnythingLLM v1.1.0 w/multimodality support

What's Changed

Notable

• Add multimodality support by @timothycarambat in #2001
• Add drag-and-drop to chat window for auto upload & embed of documents by @timothycarambat in #1995

---

• Updated API for workspace to return active threads by @timothycarambat in #1978
• Fix GroqAI picker UI bug by @timothycarambat in #1993
• Enable editing of OpenRouter stream timeout for slower connections by @timothycarambat in #1994
• Drag and drop file colors update & margin styles by @shatfield4 in #2000
• Added more char exceptions to mapping extension by @timothycarambat in #2010

Full Changelog: v1.0.0...v1.1.0