LocalAI v2.28.0 — Release Notes & Engineering Impact

# 🎉 LocalAI v2.28.0: New Look & The Rebirth of LocalAGI! 🎉 <table> <tr> <td align="center"> <img src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/core/http/static/logo.png" width="300" alt="New LocalAI Logo"> <br> <em>Our fresh new look!</em> </td> </tr> </table> Big news, everyone! Not only does LocalAI have a brand new logo, but we're also celebrating the full rebirth of **LocalAGI**, our powerful agent framework, now completely rewritten and ready to revolutionize your local AI workflows! ## Rewinding the Clock: The Journey of LocalAI & LocalAGI Two years ago, **LocalAI** emerged as a pioneer in the local AI inferencing space, offering an OpenAI-compatible API layer long before it became common. Around the same time, **LocalAGI** was born as an experiment in AI agent frameworks – you can even find the [original announcement here](https://x.com/mudler_it/status/1687938358079578113)! Originally built in Python, it inspired many with its local-first approach. <details> <summary>See LocalAGI (Original Python Version) in Action!</summary> *Searching the internet (interactive mode):* <video src="https://github.com/mudler/LocalAGI/assets/2420543/23199ca3-7380-4efc-9fac-a6bc2b52bdb3"></video> *Planning a road trip (batch mode):* <video src="https://github.com/mudler/LocalAGI/assets/2420543/9ba43b82-dec5-432a-bdb9-8318e7db59a4"></video> </details> That early experiment has now evolved significantly! ## Introducing LocalAGI v2: The Agent Framework Reborn in Go! <p align="center"> <a href="https://github.com/mudler/LocalAGI" target="_blank"><img src="https://raw.githubusercontent.com/mudler/LocalAGI/refs/heads/main/webui/react-ui/public/logo_2.png" width="300" alt="LocalAGI Logo"></a> </p> We're thrilled to announce that [**LocalAGI**](https://github.com/mudler/LocalAGI) has been rebuilt from the ground up in **Golang**! It's now a modern, robust AI Agent Orchestration Platform designed to work seamlessly with LocalAI. Huge thanks to the community, especially @richiejp, for jumping in and helping create a fantastic new WebUI! LocalAGI leverages all the features that make LocalAI great for agentic tasks. During the refactor, we even spun out the memory layer into its own component: [**LocalRecall**](https://github.com/mudler/LocalRecall?tab=readme-ov-file), a standalone REST API for persistent agent memory. ### 🚀 What Makes LocalAGI v2 Shine? * **🎯 OpenAI Responses API Compatible:** Integrates perfectly with LocalAI, acting as a drop-in replacement for cloud APIs, keeping your interactions local and secure. * **🤖 Next-Gen AI Agent Orchestration:** Easily configure, deploy, and manage teams of intelligent AI agents through an intuitive no-code web interface. * **🛡️ Privacy-First by Design:** Everything runs locally. Your data *never* leaves your hardware. * **📡 Instant Integrations:** Comes with built-in connectors for Slack, Telegram, Discord, GitHub Issues, IRC, and more. * **⚡ Extensible and Multimodal:** Supports multiple models (text, vision) and custom actions, perfectly complementing your LocalAI setup. ### ✨ Check out the new LocalAGI WebUI:    ## What's New Specifically in LocalAI v2.28.0? Beyond the rebranding and the major LocalAGI news, this LocalAI release also brings its own set of improvements: * **🖼️ SYCL Support:** Added SYCL support for `stablediffusion.cpp`. * **✨ WebUI Enhancements:** Continued improvements to the user interface. * **🧠 Diffusers Updated:** Core diffusers library has been updated. * **💡 Lumina Model Support:** Now supports the [Lumina model family](https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0) for generating stunning images! * **🐛 Bug Fixes:** Resolved issues related to setting `LOCALAI_SINGLE_ACTIVE_BACKEND` to `true`. ## The Complete Local Stack for Privacy-First AI With LocalAGI rejoining LocalAI alongside LocalRecall, our ecosystem provides a complete, open-source stack for private, secure, and intelligent AI operations: <table> <tr> <td width="30%" valign="top" align="center"> <a href="https://github.com/mudler/LocalAI"> <img src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/core/http/static/logo.png" width="200" alt="LocalAI Logo"> <h3>LocalAI</h3> </a> </td> <td width="70%" valign="top"> <p>The free, Open Source OpenAI alternative. Acts as a drop-in replacement REST API compatible with OpenAI specifications for local AI inferencing. No GPU required.</p> <p><em>Link:</em> <a href="https://github.com/mudler/LocalAI">https://github.com/mudler/LocalAI</a></p> </td> </tr> <tr> <td width="30%" valign="top" align="center"> <a href="https://github.com/mudler/LocalAGI"> <img src="https://raw.githubusercontent.com/mudler/LocalAGI/refs/heads/main/webui/react-ui/public/logo_2.png" width="200" alt="LocalAGI Logo"> <h3>LocalAGI</h3> </a> </td> <td width="70%" valign="top"> <p>A powerful Local AI agent management platform. Serves as a drop-in replacement for OpenAI's Responses API, supercharged with advanced agentic capabilities and a no-code UI.</p> <p><em>Link:</em> <a href="https://github.com/mudler/LocalAGI">https://github.com/mudler/LocalAGI</a></p> </td> </tr> <tr> <td width="30%" valign="top" align="center"> <a href="https://github.com/mudler/LocalRecall"> <img src="https://raw.githubusercontent.com/mudler/LocalRecall/refs/heads/main/static/localrecall_horizontal.png" width="200" alt="LocalRecall Logo"> <h3>LocalRecall</h3> </a> </td> <td width="70%" valign="top"> <p>A RESTful API and knowledge base management system providing persistent memory and storage capabilities for AI agents. Designed to work alongside LocalAI and LocalAGI.</p> <p><em>Link:</em> <a href="https://github.com/mudler/LocalRecall">https://github.com/mudler/LocalRecall</a></p> </td> </tr> </table> ## Join the Movement! ❤️ A massive **THANK YOU** to our incredible community! LocalAI has over **31,800 stars**, and LocalAGI has already rocketed past **450+ stars**! As a reminder, LocalAI is real FOSS (Free and Open Source Software) and its sibling projects are community-driven and not backed by VCs or a company. We rely on contributors donating their spare time. If you love open-source, privacy-first AI, please consider starring the repos, contributing code, reporting bugs, or spreading the word! 👉 **Check out the reborn LocalAGI v2 today:** [https://github.com/mudler/LocalAGI](https://github.com/mudler/LocalAGI) Let's continue building the future of AI, together! 🙌 ## Full changelog :point_down: <details> <summary> :point_right: Click to expand :point_left: </summary> ## What's Changed ### Bug fixes :bug: * fix(stablediffusion): Avoid GGML commit which causes CUDA compile error by @richiejp in https://github.com/mudler/LocalAI/pull/5170 ### Exciting New Features 🎉 * feat(loader): enhance single active backend by treating as singleton by @mudler in https://github.com/mudler/LocalAI/pull/5107 ### 🧠 Models * chore(model gallery): add all-hands_openhands-lm-32b-v0.1 by @mudler in https://github.com/mudler/LocalAI/pull/5111 * chore(model gallery): add burtenshaw_gemmacoder3-12b by @mudler in https://github.com/mudler/LocalAI/pull/5112 * chore(model gallery): add all-hands_openhands-lm-7b-v0.1 by @mudler in https://github.com/mudler/LocalAI/pull/5113 * chore(model gallery): add all-hands_openhands-lm-1.5b-v0.1 by @mudler in https://github.com/mudler/LocalAI/pull/5114 * chore(model gallery): add gemma-3-12b-it-qat by @mudler in https://github.com/mudler/LocalAI/pull/5117 * chore(model gallery): add gemma-3-4b-it-qat by @mudler in https://github.com/mudler/LocalAI/pull/5118 * chore(model gallery): add tesslate_synthia-s1-27b by @mudler in https://github.com/mudler/LocalAI/pull/5119 * chore(model gallery): add katanemo_arch-function-chat-7b by @mudler in https://github.com/mudler/LocalAI/pull/5120 * chore(model gallery): add katanemo_arch-function-chat-1.5b by @mudler in https://github.com/mudler/LocalAI/pull/5121 * chore(model gallery): add katanemo_arch-function-chat-3b by @mudler in https://github.com/mudler/LocalAI/pull/5122 * chore(model gallery): add gemma-3-27b-it-qat by @mudler in https://github.com/mudler/LocalAI/pull/5124 * chore(model gallery): add open-thoughts_openthinker2-32b by @mudler in https://github.com/mudler/LocalAI/pull/5128 * chore(model gallery): add open-thoughts_openthinker2-7b by @mudler in https://github.com/mudler/LocalAI/pull/5129 * chore(model gallery): add arliai_qwq-32b-arliai-rpr-v by @mudler in https://github.com/mudler/LocalAI/pull/5137 * chore(model gallery): add watt-ai_watt-tool-70b by @mudler in https://github.com/mudler/LocalAI/pull/5138 * chore(model gallery): add eurydice-24b-v2-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5139 * chore(model gallery): add mensa-beta-14b-instruct-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5140 * chore(model gallery): add meta-llama_llama-4-scout-17b-16e-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5141 * fix(gemma): improve prompt for tool calls by @mudler in https://github.com/mudler/LocalAI/pull/5142 * chore(model gallery): add cogito-v1-preview-qwen-14b by @mudler in https://github.com/mudler/LocalAI/pull/5145 * chore(model gallery): add deepcogito_cogito-v1-preview-llama-8b by @mudler in https://github.com/mudler/LocalAI/pull/5147 * chore(model gallery): add deepcogito_cogito-v1-preview-llama-3b by @mudler in https://github.com/mudler/LocalAI/pull/5148 * chore(model gallery): add deepcogito_cogito-v1-preview-qwen-32b by @mudler in https://github.com/mudler/LocalAI/pull/5149 * chore(model gallery): add deepcogito_cogito-v1-preview-llama-70b by @mudler in https://github.com/mudler/LocalAI/pull/5150 * chore(model gallery): add agentica-org_deepcoder-14b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5151 * chore(model gallery): add trappu_magnum-picaro-0.7-v2-12b by @mudler in https://github.com/mudler/LocalAI/pull/5153 * chore(model gallery): add soob3123_amoral-cogito-v1-preview-qwen-14b by @mudler in https://github.com/mudler/LocalAI/pull/5154 * chore(model gallery): add agentica-org_deepcoder-1.5b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5156 * chore(model gallery): add zyphra_zr1-1.5b by @mudler in https://github.com/mudler/LocalAI/pull/5157 * chore(model gallery): add tesslate_gradience-t1-3b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5160 * chore(model gallery): add lightthinker-qwen by @mudler in https://github.com/mudler/LocalAI/pull/5165 * chore(model gallery): add mag-picaro-72b by @mudler in https://github.com/mudler/LocalAI/pull/5166 * chore(model gallery): add hamanasu-adventure-4b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5167 * chore(model gallery): add hamanasu-magnum-4b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5168 * chore(model gallery): add daichi-12b by @mudler in https://github.com/mudler/LocalAI/pull/5169 * chore(model gallery): add skywork_skywork-or1-7b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5173 * chore(model gallery): add skywork_skywork-or1-math-7b by @mudler in https://github.com/mudler/LocalAI/pull/5174 * chore(model gallery): add skywork_skywork-or1-32b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5175 * chore(model gallery): add nvidia_llama-3.1-8b-ultralong-1m-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5176 * chore(model gallery): add nvidia_llama-3.1-8b-ultralong-4m-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5177 * chore(model gallery): add m1-32b by @mudler in https://github.com/mudler/LocalAI/pull/5182 ### 📖 Documentation and examples * Update README.md by @qwerty108109 in https://github.com/mudler/LocalAI/pull/5172 * Rebrand: the LocalAI stack family by @mudler in https://github.com/mudler/LocalAI/pull/5159 ### 👒 Dependencies * chore: :arrow_up: Update ggml-org/llama.cpp to `c80a7759dab10657b9b6c3e87eef988a133b9b6a` by @localai-bot in https://github.com/mudler/LocalAI/pull/5105 * chore: :arrow_up: Update ggml-org/llama.cpp to `f423981ac806bf031d83784bcb47d2721bc70f97` by @localai-bot in https://github.com/mudler/LocalAI/pull/5108 * chore(deps): bump llama.cpp to 'f01bd02376f919b05ee635f438311be8dfc91d7c by @mudler in https://github.com/mudler/LocalAI/pull/5110 * fix(sycl): kernel not found error by forcing -fsycl by @richiejp in https://github.com/mudler/LocalAI/pull/5115 * chore: :arrow_up: Update ggml-org/llama.cpp to `c262beddf29f3f3be5bbbf167b56029a19876956` by @localai-bot in https://github.com/mudler/LocalAI/pull/5116 * chore: :arrow_up: Update ggml-org/llama.cpp to `3e1d29348b5d77269f6931500dd1c1a729d429c8` by @localai-bot in https://github.com/mudler/LocalAI/pull/5123 * chore: :arrow_up: Update ggml-org/llama.cpp to `6bf28f0111ff9f21b3c1b1eace20c590281e7ba6` by @mudler in https://github.com/mudler/LocalAI/pull/5127 * chore: :arrow_up: Update ggml-org/llama.cpp to `916c83bfe7f8b08ada609c3b8e583cf5301e594b` by @localai-bot in https://github.com/mudler/LocalAI/pull/5130 * chore(deps): bump securego/gosec from 2.22.0 to 2.22.3 by @dependabot in https://github.com/mudler/LocalAI/pull/5134 * chore(deps): bump llama.cpp to `4ccea213bc629c4eef7b520f7f6c59ce9bbdaca0` by @mudler in https://github.com/mudler/LocalAI/pull/5143 * chore: :arrow_up: Update ggml-org/llama.cpp to `b32efad2bc42460637c3a364c9554ea8217b3d7f` by @localai-bot in https://github.com/mudler/LocalAI/pull/5146 * chore: :arrow_up: Update ggml-org/llama.cpp to `d3bd7193ba66c15963fd1c59448f22019a8caf6e` by @localai-bot in https://github.com/mudler/LocalAI/pull/5152 * chore: :arrow_up: Update ggml-org/llama.cpp to `64eda5deb9859e87a020e56bab5d2f9ca956f1de` by @localai-bot in https://github.com/mudler/LocalAI/pull/5155 * chore: :arrow_up: Update ggml-org/llama.cpp to `bc091a4dc585af25c438c8473285a8cfec5c7695` by @localai-bot in https://github.com/mudler/LocalAI/pull/5158 * chore: :arrow_up: Update ggml-org/llama.cpp to `71e90e8813f90097701e62f7fce137d96ddf41e2` by @localai-bot in https://github.com/mudler/LocalAI/pull/5171 * chore: :arrow_up: Update ggml-org/llama.cpp to `d6d2c2ab8c8865784ba9fef37f2b2de3f2134d33` by @localai-bot in https://github.com/mudler/LocalAI/pull/5178 * fix(stablediffusion): Pass ROCM LD CGO flags through to recursive make by @richiejp in https://github.com/mudler/LocalAI/pull/5179 ### Other Changes * docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/5104 * chore: drop remoteLibraryURL from kong vars by @mudler in https://github.com/mudler/LocalAI/pull/5103 * fix: race during stop of active backends by @mudler in https://github.com/mudler/LocalAI/pull/5106 * fix(webui): improve model display, do not block view by @mudler in https://github.com/mudler/LocalAI/pull/5133 * feat(diffusers): add support for Lumina2Text2ImgPipeline by @mudler in https://github.com/mudler/LocalAI/pull/4806 * feat(stablediffusion): Enable SYCL by @richiejp in https://github.com/mudler/LocalAI/pull/5144 * fix(stablediffusion): Avoid overwriting SYCL specific flags from outer make call by @richiejp in https://github.com/mudler/LocalAI/pull/5181 ## New Contributors * @qwerty108109 made their first contribution in https://github.com/mudler/LocalAI/pull/5172 </details> **Full Changelog**: https://github.com/mudler/LocalAI/compare/v2.27.0...v2.28.0