Stars
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.
XTR/WARP is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
multi-task and multi-track music transcription for everyone
SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
Track, manage and optimize your recurring expenses in one powerful and human readable dashboard.
Code for "Neural Retrievers are Biased Towards LLM-Generated Content"
⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍
All-in-one infrastructure for search, recommendations, RAG, and analytics offered via API
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Generate a docker-compose yaml definition from a running container
Offline markdown to pdf, choose -> edit -> transform 🥂
The fixed clipboard manager for Windows, macOS & Linux
Python tool for converting files and office documents to Markdown.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
A lightweight Database GUI in your browser. It supports connecting to Postgres, MySQL, and SQLite.
A docker job scheduler (aka. crontab for docker)
Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
A PHP library for performing vector operations in MySQL without extensions