Llampart 1.0.0 is a standalone local web UI for llama-server with translations, extended settings, and a polished conversation sidebar, released under MIT license.
Hi everyone, I’ve just published the first public release of **llampart 1.0.0**: [https://github.com/mchowy-troll/llampart](https://github.com/mchowy-troll/llampart) llampart is a standalone local web UI designed to work with \`llama-server\`. It started from the \`llama-ui\` work in the \`llama.cpp\` project, but over time I customized it into a separate interface focused on local use, everyday comfort, and a more complete desktop-style experience. The goal was not to build another hosted chat service, but a clean local UI that feels pleasant to use for longer sessions while keeping the workflow simple. Some highlights: * **standalone** local web UI for \`llama-server\` * **extended settings interface with appearance**, model, MCP, tools, data, and advanced sections * localized interface: **English, Polish, German, French, Italian, and Spanish** * **two-column conversation sidebar** with conversation date/time display, conversation pinning, selective conversation deletion, delete-all while preserving pinned conversations * local import/export workflow that avoids exporting sensitive settings by default * llama-server connection workflow * MCP-related UI flows for servers, tools, resources, and prompts * **minimal Reasoning / Tools display mode** * dark, light, and **Frosted Glass interface** modes * bundled wallpapers and **wallpaper customization** * optional Caddy deployment guide for local/LAN setup [llampart 1.0.0 - main page](https://preview.redd.it/n4zkw01kaz2h1.png?width=4304&format=png&auto=webp&s=89089ea0f2c3bc874fa753c48187c591cb5682bf) [llampart 1.0.0 - chat](https://preview.redd.it/1dhywqdnaz2h1.png?width=5062&format=png&auto=webp&s=20afa194b14f2757e841979be4c9085c8851cfa5) [llampart 1.0.0 - settings](https://preview.redd.it/45at56hqaz2h1.png?width=5062&format=png&auto=webp&s=519065ce4797a5deff9e3336af323151ea299206) The project is **MIT-licensed**. I also tried to be careful with attribution and licensing notes, since llampart is based in part on \`llama-ui\` from \`llama.cpp\` and uses Svelte/SvelteKit for the frontend. This is an initial public source release, so I’m sure there will still be things to improve. Feedback, suggestions, and issue reports are very welcome. Thanks to the \`llama.cpp\` community — this project would not exist without that ecosystem.
Llama-Studio is a WebUI for managing llama-server sessions, allowing configuration, monitoring, and control of multiple instances for local development and experimentation.
LLC, a lightweight alternative to OpenWebUI for running local LLMs, updates to v0.6 with a chat converter to import OpenWebUI history and custom tool calls for user-defined tools.
LlamaStation v0.9 is a Windows GUI for llama.cpp that offers a clean interface with full parameter control, multiple backends (official, TurboQuant, AtomicChat, BeeLlama), real-time VRAM monitoring, per-model profiles, voice mode, and headless mode, all without intermediate layers like Ollama.
The author built a custom llama.cpp server and Mikupad UI to enable local inference and activation steering with Anthropic's open-weight Natural Language Autoencoders. A LoRA version is in development to reduce memory requirements.
Llama.cpp announces a new website and unified 'llama' binary for simpler LLM inference, along with updates like Hugging Face cache migration and multimodal support.