lmstudio

Autonomous Dual-Role MCP Server: Enterprise Code Auditor & System Architect powered by Local LLMs (LM Studio) with AST Guard & Discord Observability.

MedScan AI is a Flask-based web application that uses OCR and AI to analyze prescription images and provide clinical insights.

Google Jobs Scraper — free, open-source Google Jobs scraper. Unlimited jobs, salaries & apply links as clean JSON, no API key, no proxies.

🩸 Streamline blood bank management with AI to ensure real-time availability, secure workflows, and optimized donor matching for emergencies.

Multi-server GPU slot management for LM Studio and other OpenAI-compatible inference backends

Use LLM Model to solve/guess wordle game problem

LMStudio Local Setup, Testing and Troubleshooting

Enable DSPy to authenticate using Pi-style credentials and ChatGPT subscriptions for efficient local and cloud language model use.

Authorization tokens to access llama.cpp server (LM Studio, Ollama, Msty, GPT4All, Jan)

Catching silent AI failures. This pipeline evaluates prompt versions locally (LM Studio) or in the cloud (Groq) against golden datasets, generating dynamic HTML scorecards and Slack alerts to prevent degraded LLM logic from reaching users.

App Streamlit que processa planilhas de orçamento (.xls/.xlsx) e gera visualizações interativas: visão geral, lista completa, análise de preços, quantidades por unidade, distribuição por categoria e estatísticas descritivas. Integração opcional com IA local (LM Studio) para resumos executivos. Tecnologias: Python, Pandas, Plotly, Streamlit.

MCP server to control brave browser

Time Series Analyzer com IA local. Análise do dataset de clima diário de Delhi (2013-2017) com 4 parâmetros. Decomposição (tendência/sazonalidade), detecção de anomalias (IQR), previsão com Prophet. Insights em linguagem natural gerados por Hermes 3 (LM Studio). Dashboard interativo com Streamlit e Plotly.

Contributor of RAG-Anything: All-in-One RAG System + LMStudio

A conversational AI powered by custom Multi-step Retrieval-Augmented Generation (RAG) pipeline, orchestrated with LangChain, to ground a locally-hosted Llama 3 8B Instruct model in a private knowledge base.

A lightweight, private Retrieval-Augmented Generation (RAG) web application that allows you to chat with and summarize any YouTube video using your own local LLMs (via LM Studio, Ollama, or any OpenAI-compatible API).

This project is a minimal study scaffold for building a Multi-Agent Research Assistant with LangChain, LangGraph and LM Studio.

A Python benchmark tool for profiling local GPU VRAM usage, vector search latency, and LLM inference speed on RTX 3090 systems.

Generate Articles in Bulk volume for Blog Website. 100% Works Offline

Python planner-worker orchestration runtime with adapters, reports, guardrails, and tests