Stars
Measuring how well CLI agents can post-train LLMs
Distributed Task Queue (development branch)
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
A benchmark for LLMs on complicated tasks in the terminal
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
The Greek NLP toolkit for Python. Supports NER/DP/POS Tagging/Greeklish-to-Greek Transliteration. Visit the web demo here: https://huggingface.co/spaces/AUEB-NLP/greek-nlp-toolkit-demo (paper prese…
Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation
Fully open data curation for reasoning models
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Code for "PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements", accepted for Oral Presentation at the Main Conference of EMNLP 2025. Paper available at: https://arxiv.or…
💹 StockSim: Multi-Agent LLM Financial Market Simulator — A realistic trading simulation platform for evaluating large language models in dynamic financial environments.
The official Python SDK for Model Context Protocol servers and clients
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Open roles at Kaedim and a summary of what it's like to work with us.
AI wearables. Put it on, speak, transcribe, automatically
Question Answering over Tabular Data with LLM Code Generation
📃 A better UX for chat, writing content, and coding with LLMs.
DSPy: The framework for programming—not prompting—language models
Parallel Reasoning: llm-consortium orchestrates mulitple LLMs, iteratively refines & achieves consensus.
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
Everything you need to know to build your own RAG application
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
A modular graph-based Retrieval-Augmented Generation (RAG) system