AI chat assistant for Obsidian with contextual awareness, smart writing assistance, and one-click edits. Features vault-aware conversations, semantic search, and local model support.

A curated list of amazingly awesome Modal applications, demos, and shiny things. Inspired by awesome-php.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Access large language models from the command-line

llm-consortium orchestrates mulitple LLMs, iteratively refines & achieves consensus.

An extremely fast Python package and project manager, written in Rust.

A game theoretic approach to explain the output of any machine learning model.

Local LLM-based social network filter

Tools and extensions for gptme

Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Inverse Constitutional AI: compressing pairwise preference data into a short constitution of principles.

The Web We Lost, and What Comes Next

A course on aligning smol models.

The Foundation repository contains the initial guidance documents, recommendations, and resources needed to build a psychosecurity-first operation.

PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure

Functional optics: a (partial) porting of Scala monocle

Ramda functions reimplemented in fp-ts

Inspect: A framework for large language model evaluations

A modular graph-based Retrieval-Augmented Generation (RAG) system

Vivaria is METR's tool for running evaluations and conducting agent elicitation research.

Examples of programs built using Modal

the supercharged twitter feed

cuML - RAPIDS Machine Learning Library

Real-time video and audio processing on Streamlit

Implementation of Ag-Grid component for Streamlit

A python package for creating subscription Streamlit apps