ML Application · Svelte

ollama-webui-personal

Petr Sovadina@petrsovadina · Atlas 68.5 · #6 builder

View on GitHub Open Petr Sovadina's Atlas

What it is

This repository provides a personal fork of the Open WebUI, a web-based interface for interacting with LLMs via Ollama or OpenAI-compatible APIs. It includes features such as retrieval-augmented generation (RAG), audio transcription, image generation, and web browsing integration.

Scored from the code at its last scan, 22 Oct 2026. How merit is scored

Where it counts

NLP & LLMs95%
Machine Learning90%
Computer Vision60%
AI Agents40%
MLOps20%
Data Science10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the NLP & LLMs board

Whole board

RankProjectBuilderFieldMerit

25snap-cite-livive-netAI Developer Tool · PythonSnap Cite is a tool for generating offline, verifiable grounding reports that assert the explicit presence of specific API members in a given snapshot. It provides a CLI, validation, and reporting functionality to support evidence-based claims about API definitions.57.4/100ImplementationJarad PeckenpaughNLP & LLMs
26orionOther AI Project · TypeScriptOrion is a local-first desktop application for tracking hunting sessions in the game Entropia Universe. It monitors the game's chat log to extract events (loot, skill gains, combat, etc.), stores them in a local database, and provides analytics through a React/TypeScript…57.0/100ImplementationNepheriusNLP & LLMs
27ollama-webui-personalML Application · Svelte56.4/100ImplementationPetr SovadinaNLP & LLMs
28HuggingFace-Project-LearningEducational Implementation · Jupyter NotebookThe repository is a collection of 38 Jupyter notebooks that follow the Hugging Face NLP and Reasoning courses, with added reimplementations of tokenizers, GRPO, and a causal LM training loop from scratch, and an end-to-end Romanian QA project (though the key evaluation notebook…56.2/100ImplementationPop AlexandruNLP & LLMs
29GWIQ-atlasAI Developer Tool · PythonGWIQ-atlas is a toolkit for building per-layer activation atlases of language models to enable informed quantization and surgical analysis. It provides tools for activation census, layer analysis, compliance behavior mapping, and atlas construction, but lacks the surgery tools…56.0/100ImplementationRickNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from Petr Sovadina