extropians list archive 1996-2003

rl from zero pretrain, can it be done? yes.

prime is a framework for efficient, globally distributed training of AI models over the internet.

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

Perun is a Python package that measures the energy consumption of your applications.

Highly accurate and efficient VSLAM system for Python

Train an adapter for any embedding model in under a minute

High throughput synchronous and asynchronous reinforcement learning

Evaluating LLMs by having them play games against each other

[ACL 2025] AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

A TypeScript framework for building MCP servers elegantly

Graphs for Everyone

LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.

Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding

Python tool for converting files and office documents to Markdown.

Model Context Protocol Servers

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference i…

All-in-one platform for search, recommendations, RAG, and analytics offered via API

CalHacks 11.0 | Sift - Supercharged Semantic Search

An open-source RAG-based tool for chatting with your documents.

Back-of-the-envelope stuffs in Python

A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

Python bindings for llama.cpp

Chroma's fork of hnswlib - a header-only C++/python library for fast approximate nearest neighbors

Evaluation and Tracking for LLM Experiments and AI Agents

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

This package, developed as part of our research detailed in the Chroma Technical Report, provides tools for text chunking and evaluation. It allows users to compare different chunking methods and i…

A lightweight open-source package to fine-tune embedding models.