Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

LLM (Large Language Model) FineTuning

🏗️ Fine-tune, build, and deploy open-source LLMs easily!

LLMs and Machine Learning done easily

A list of LLMs Tools & Projects

This is a PHP library for Ollama. Ollama is an open-source project that serves as a powerful and user-friendly platform for running LLMs on your local machine. It acts as a bridge between the complexities of LLM technology and the desire for an accessible and customizable AI experience.

Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs

Samples on how to build industry solution leveraging generative AI capabilities on top of SAP BTP and integrated with SAP S/4HANA Cloud.

EmbeddedLLM: API server for Embedded Device Deployment. Currently support CUDA/OpenVINO/IpexLLM/DirectML/CPU

GPU-accelerated LLaMA inference wrapper for legacy Vulkan-capable systems a Pythonic way to run AI with knowledge (Ilm) on fire (Vulkan).

Read your local files and answer your queries

Multi-agent workflows with Llama3: A private on-device multi-agent framework

This project contains the code and documentation for an autonomous AI agent that classifies, enriches, and scores inbound business leads. It is built with a FastAPI backend, a LangGraph agent workflow powered by a local Ollama LLM, and a Streamlit frontend for demonstration.

In this project, we leverage Weaviate, a vector database, to power our retrieval-augmented generation (RAG) application. Weaviate enables efficient vector similarity search, which is crucial for building effective RAG systems. Additionally, we use local language model (LLM) and embedding models.

JSONFIRST integration package — jsonfirst.com

SiliconSoap is a cool new way to watch AI agents talk to each other. We make open-source AIs and the newest, most advanced AIs battle it out in exciting, planned conversations. Get ready for AIs with strong personalities, powerful speeches, and quick comebacks. We also add AI-made pictures and sounds to make it even more fun to watch. It's like ...

*the-stix-intern* a minimalistic framework for the automized extraction of CTI from unstructured texts

LocalPrompt is an AI-powered tool designed to refine and optimize AI prompts, helping users run locally hosted AI models like Mistral-7B for privacy and efficiency. Ideal for developers seeking to run LLMs locally without external APIs.

Gittxt is an AI-focused CLI and plugin tool for extracting, filtering, and packaging text from GitHub repos. Build LLM-compatible datasets, prep code for prompt engineering, and power AI workflows with structured .txt, .json, .md, or .zip outputs.

AI study assistant for engineering students.

🌳 Open-source RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval - Complete open-source implementation with 100% local LLMs (Granite Code 8B + mxbai-embed-large)

This project implements a production-ready Conversational (RAG) chatbot using LangChain, Groq’s LLaMA 3 model, ChromaDB, and HuggingFace embeddings. It supports persistent chat history across sessions using RunnableWithMessageHistory, and integrates modular prompting, document loading, and retriever-aware chains to handle context-aware multi-chats.

An AI-powered job hunting agent that autonomously analyzes job descriptions, matches resumes, generates customized cover letters, and controls application decisions using LangGraph workflows, LangChain orchestration, and LangSmith monitoring, powered by open-source LLMs via Ollama.

AI-powered quiz generator that creates MCQs from lecture PDFs using open-source LLMs (Qwen2.5-3B-Instruct). Includes PDF parsing, text chunking, and automated question generation.

945-generation adversarial evaluation of 3 open LLMs across 3 personas and 20 attack types, measuring semantic drift, override rates, and distributional instability.

Create a Small LLM using EleutherAI/gpt-neo-2.7B - Fine Tune It for a Specalized Purpouse and Leverage as a Co-Pilot

Turn text/audio/video into study packs (summaries, concept maps, quizzes). Flutter + FastAPI. Uses GPT-OSS-20B (Replicate) by default, with optional fallbacks (OpenAI/Anthropic) and OSS modes (Ollama/vLLM).

LLM-powered chatbot for insurance claims processing using open-source models