ML Application · HTML

llamahtml

LLamaHTML is a simple html file to communicate with a running llamacpp llama-server

jerry howell@openconstruct · Atlas 64.1 · #14= builder

View on GitHub26 Open jerry howell's Atlas

What it is

llamahtml is a single-file HTML/JavaScript client that provides a user-friendly web interface for interacting with a locally running llama.cpp server. It offers streaming responses, markdown rendering, configurable generation parameters, and theme switching.

Scored at5c6796f7 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

NLP & LLMs90%
Machine Learning80%
AI Agents10%

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

87diffwhispererAI Developer Tool · Pythondiffwhisperer is an AI developer tool that integrates with Claude Code to automatically generate natural language explanations of code changes using local Ollama models. It provides a hook for real-time explanations and a web dashboard for viewing, filtering, and regenerating…46.5/100ImplementationemmjayhNLP & LLMs
88langflow-personalAI Developer Tool · TypeScriptLangflow-personal is a fork of the LangFlow project that provides a visual interface for prototyping LangChain chains and agents. It includes a FastAPI backend, React frontend, and Docker deployment configurations for easy experimentation with language model applications.46.3/100ImplementationPetr SovadinaNLP & LLMs
89llamahtmlML Application · HTML44.1/100Implementationjerry howellNLP & LLMs
90ling-3.0-tiny-cu130-torch213-py312-sm89Inference System · PythonA Docker image that serves the inclusionAI/Ling-3.0-tiny language model using vLLM, with build-time verification of dependencies and model compatibility.43.8/100ImplementationRickNLP & LLMs
91mistral-ml-flowMLOps Infrastructure · ShellThe mistral-ml-flow repository provides a Docker image (ml-workflow-image) and helper scripts to create a reproducible GPU environment for running the GWIQ atlas CLI, which is used for analyzing language models such as Mistral and Qwen.41.4/100ImplementationRickNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from jerry howell