Self-hostable software: AI & ML Practitioners (15)

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

A desktop app for running local LLMs with chat, vision, tool-calling, training, image generation, and an API.

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

Langfuse is an open source LLM engineering platform for teams to develop, monitor, evaluate, and debug AI applications.

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

llamafile lets users distribute and run LLMs as a single-file executable with no installation. It also includes whisperfile for local speech-to-text transcription and translation.

A framework for building and deploying AI services with gRPC, HTTP, and WebSocket communication.

A CLI tool and Python library for interacting with large language models from remote APIs or locally installed models.

A SvelteKit chat interface for OpenAI-compatible LLM APIs, powering HuggingChat.

An AI-powered research assistant that performs iterative research using multiple LLMs and search engines, with citations and a searchable local knowledge base.

Big-AGI is a multi-model AI workspace for experts, focused on chat, model comparison, and local-first self-hosting.

Honcho is a memory infrastructure for building stateful agents that track people, agents, groups, projects, and ideas over time.