An AI chatbot built with DeepScaleR and deployed locally using Ollama, FastAPI, and Gradio.
Video Summarizer using Local LLM (facebook/bart-large-cnn). Submit a YouTube URL and get an AI-generated summary of the video.
Chatbot UI powered by local LLaMA3 using Ollama + Streamlit. 100% offline, no API keys needed.
An automated system designed to replace manual Excel tracking. It securely connects to Gmail via OAuth2 and uses a Local LLM to analyze recruiter emails and update application statuses without sending data to third parties. Built with FastAPI and asyncio to handle concurrent email processing efficiently.
A Polymathic Autonomous Organization (PAO) - sovereign, self-funding AI development environment with Solana blockchain integration. Features three autonomous agents (Analyst, Artist, Engineer) in a Textual TUI, local TensorRT-LLM inference, and economic generative loop.
Langer is a lightweight desktop tool for translating text with multiple LLMs and evaluating them using standard metrics. It provides an easy Python/Tkinter interface, JSON batch translation, plugin-based evaluators, and support for both cloud and local LLMs.
Production-ready RAG system starter kit with local LLM inference, hybrid search, and intelligent document processing - deploy AI that learns from your knowledge base in minutes.
Free, offline OCR using local LLMs with Ollama. Convert images to text with vision-enabled models running entirely on your machine — no cloud, no API costs, full privacy.
Chat LLM local: Interfaz CLI para modelos GGUF y Transformers con compatibilidad CUDA. Permite ejecutar Llama, Mistral, Gemma, Phi y Qwen localmente con detección automática de modelos, adaptación de mensajes del sistema, soporte RAG y más.
Project demonstrates an agentic Retrieval-Augmented Generation (RAG) application built using CrewAI and Streamlit.
An Experimental Cognitive Architecture with Persistent Memory for stateful LLM-agents
automate the batching and execution of prompts.
A constrained generation filter for local LLMs that makes them quote properly from a source document
AI-powered Bash terminal built with Python, Tkinter, tkterm, using local LLM through LMStudio for natural language command generation; features whitelist/blacklist management, intuitive interface.
python SDK for CZero Engine (API endpoints usage examples)
Local RL-driven AI orchestrator fusing RAG, CAG, and graphs - Built offline on consumer hardware.
Add a description, image, and links to the local-llm topic page so that developers can more easily learn about it.
To associate your repository with the local-llm topic, visit your repo's landing page and select "manage topics."