Install and Run Python Applications in Isolated Environments

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

WARC + AI - Experimental Retrieval Augmented Generation Pipeline for Web Archive Collections.

Official repository of the xLSTM.

Parse files for optimal RAG

802.11 Attack Tool

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

Powerful scripting language & versatile interactive shell

A Commander for modern Go CLI interactions

command argument completion generator for spf13/cobra

ZeroMQ core engine in C++, implements ZMTP/3.1

Pure Java ZeroMQ

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

A fast, compressed, persistent binary data store library for C.

A Low-Level Abstraction of Memory Access

Abstraction Library for Parallel Kernel Acceleration 🦙

Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction

gguf (GPT-Generated Unified Format) connector

Open weights language model from Google DeepMind, based on Griffin.

Parallel Extraction from External Data Sources with U-SQL

Drop-in, local AI alternative to the OpenAI stack. Multi-engine (llama.cpp, TensorRT-LLM). Powers 👋 Jan

The realtime kanban board for workgroups built with React and Redux.

Code from the Poseidon Labs blog

AICI: Prompts as (Wasm) Programs

Open-Source Evaluation for GenAI Application Pipelines

Instant, controllable, local pre-trained AI models in Rust

R2R is an open source answer engine with a RESTful API. Powered by RAG, features include hybrid search, graph / multimodal RAG, and more.

ingestr is a CLI tool to copy data between any databases with a single command seamlessly.

QLoRA: Efficient Finetuning of Quantized LLMs