Descriptions of the hardware and software I have setup at my home office for running open-source, local-first, portable, multi-agent AI workflows.

A process for automating Docker container base image updates.

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

NVIDIA Data Science stack tools

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

A high-throughput and memory-efficient inference and serving engine for LLMs

Neo4j graph construction from unstructured data using LLMs

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Actor-based state management & orchestration for complex app logic.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

A course on aligning smol models.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

Compare open-source local LLM inference projects by their metrics to assess popularity and activeness.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

Get your documents ready for gen AI

Morpheus - A Network For Powering Smart Agents - Compute + Code + Capital + Community

Technical Documentation

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning