An open-source AI agent that brings the power of Gemini directly into your terminal.

Graph traversal for improved RAG

Korean adaptation of HalluLens

Tool for shell commands execution, visualization and alerting. Configured with a simple YAML file.

An ultra-fast BM25 retriever with support for multiple variants and meta-data filtering.

Mock of vLLM. Easily test your vllm code without any GPUs.

Learn Generative AI fundamentals through Java programming.

LLM-as-a-judge using G-eval Scratch

Kernels & AI inference engine for mobile devices.

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Build Real-Time Knowledge Graphs for AI Agents

Korean version of DarkBench

MCP-based Agent Deep Evaluation System

Python Implementation of MUVERA (Multi-Vector Retrieval via Fixed Dimensional Encodings)

Copilot Chat extension for VS Code

Offline, privacy-first grammar checker. Fast, open-source, Rust-powered

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Simple UI for debugging correlations of text embeddings

[ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

https://transformer-circuits.pub/2025/attribution-graphs/methods.html

FEVER (Fact Extraction and VERification) Annotation Platform and Baselines

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Code and data for the Chain-of-Draft (CoD) paper

GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings

Fast Semantic Text Deduplication & Filtering

The project aims to manipulate virtual objects with the recognition of your hand.