Self-hostable software: AI & ML Practitioners (23)

AutoGPT is a platform for creating, deploying, and managing continuous AI agents that automate complex workflows.

Ollama is a local runtime for running open models and interacting with them through a CLI, REST API, and integrations.

Hermes Agent is a self-improving AI agent with a terminal UI and messaging gateway that can run across CLI and chat platforms.

Open WebUI is a self-hosted AI platform for chatting with LLMs, managing RAG, and building custom model workflows, designed to run entirely offline.

ComfyUI is a graph-based visual engine for designing and running advanced Stable Diffusion workflows.

NextChat is a lightweight, fast AI assistant web app and desktop client with support for multiple LLM providers and self-hosted models.

GPT4All runs large language models privately on everyday desktops and laptops, and provides a Python client around llama.cpp implementations.

Pi Monorepo provides tools for building AI agents and managing LLM deployments.

A Gradio web UI for running large language models locally, with chat, vision, tool-calling, training, and image generation.

Netron is a viewer for neural network, deep learning, and machine learning models.

Composio SDK provides TypeScript and Python libraries for integrating AI agents with external apps and services.

SillyTavern is a locally installed interface for interacting with text generation LLMs, image generation engines, and TTS voice models.