Tool Library

Local and self-hosted AI tools

Compare model runtimes, serving engines, GPU infrastructure, chat interfaces, knowledge systems, agents, and image workflows by what they actually operate.

Find the right tool Compare tools Execution recipes Choose a model and hardware →Start from existing hardware →Browse model library →
29 reviewed tools · 27 self-hostable · updated 2026-08-20

All tools

29 matching tools

Open source

AnythingLLM

Knowledge & RAG

Mintplex Labs · MIT

A desktop and self-hosted workspace for document chat, RAG, and AI agents.

Desktop / localSelf-hostedmacOSWindows
Best for

Private document question answering

Open source

AUTOMATIC1111

Image

AUTOMATIC1111 · AGPL-3.0

A widely used local Stable Diffusion web interface with extensive controls, extensions, and model support.

Desktop / localSelf-hostedmacOSWindows
Best for

Detailed Stable Diffusion controls

Open source

ComfyUI

Image

Comfy Org · GPL-3.0

A node-based workflow engine and interface for local generative image and media models.

Desktop / localSelf-hostedmacOSWindows
Best for

Reproducible image-generation workflows

Open source

DeepSeek Harness

Agents

DeepSeek AI · MIT

An open-source, plugin-first agent harness with local Web UI, tools, sessions, approvals, and extensible model adapters.

Desktop / localSelf-hostedmacOSWindows
Best for

Building highly extensible agent workflows

Source available

Dify

Agents

LangGenius · Dify Open Source License

A visual platform for building and operating AI workflows, agents, and RAG applications.

Self-hostedManaged cloudLinuxDocker
Best for

Building AI workflows without coding every integration

Open source

Flowise

Agents

FlowiseAI · Apache-2.0 community; commercial enterprise components

A visual low-code platform for composing, evaluating, and deploying AI agents and LLM workflows.

Desktop / localSelf-hostedmacOSWindows
Best for

Visual agent and RAG prototyping

Open source

GPUStack

GPU Infra

GPUStack · Apache-2.0

A GPU cluster manager and model-serving control plane for heterogeneous infrastructure.

Self-hostedClusterLinuxDocker
Best for

Pooling GPUs across multiple servers

Open source

InvokeAI

Image

Invoke AI · Apache-2.0

A professional local creative application for generative images, canvas editing, workflows, and asset management.

Desktop / localSelf-hostedmacOSWindows
Best for

Canvas-based professional image workflows

Open source

Jan

Runtimes

Jan HQ · Apache-2.0

An open-source desktop chat application and local API for running models privately on a personal computer.

Desktop / localmacOSWindows
Best for

Open-source desktop local chat

Open source

Khoj

Knowledge & RAG

Khoj AI · AGPL-3.0

A self-hostable personal AI and knowledge assistant with document search, agents, automations, and research workflows.

Desktop / localSelf-hostedmacOSWindows
Best for

A private personal knowledge assistant

Open source

Langflow

Agents

Langflow · MIT

An open-source visual builder for creating AI agents and workflows that can run as APIs or MCP servers.

Desktop / localSelf-hostedmacOSWindows
Best for

Visual agent workflows with Python extensibility

Open source

Letta

Agents

Letta · Apache-2.0

An open-source platform for building stateful agents with persistent, editable, and external memory.

Desktop / localSelf-hostedmacOSWindows
Best for

Stateful agents with inspectable memory

Open source

LibreChat

Chat UIs

LibreChat · MIT

A self-hosted multi-provider chat application with agents, files, search, MCP, and model routing.

Self-hostedLinuxDocker
Best for

Self-hosted multi-provider chat

Open source

llama.cpp

Runtimes

ggml-org · MIT

A portable C/C++ inference engine that underpins much of the GGUF local-model ecosystem.

Desktop / localSelf-hostedmacOSWindows
Best for

Maximum portability and runtime control

Proprietary

LM Studio

Runtimes

LM Studio · Proprietary

A polished desktop application for discovering, running, and serving local models.

Desktop / localmacOSWindows
Best for

Exploring local models from a desktop UI

Open source

LocalAI

Serving

LocalAI Project · MIT

A self-hosted OpenAI-compatible API that runs language, image, audio, and multimodal models through modular local backends.

Desktop / localSelf-hostedmacOSLinux
Best for

One private API across several AI modalities

Open source

MLX LM

Runtimes

Apple MLX · MIT

Apple Silicon-native tooling for generating, quantizing, fine-tuning, and serving language models with MLX.

Desktop / localSelf-hostedmacOS
Best for

Efficient LLM work on Apple Silicon

Source available

n8n

Agents

n8n · n8n Sustainable Use License

A workflow automation platform that connects AI agents and model calls to hundreds of business applications.

Self-hostedManaged cloudLinuxDocker
Best for

Connecting AI to business systems

Open source

Ollama

Runtimes

Ollama · MIT

A straightforward local model runtime with a CLI, model library, and local API.

Desktop / localSelf-hostedmacOSWindows
Best for

Running local models with minimal setup

Source available

Open WebUI

Chat UIs

Open WebUI · Open WebUI License

A self-hosted chat and knowledge interface for local and cloud model providers.

Desktop / localSelf-hostedmacOSWindows
Best for

Adding a shared UI to Ollama or an API server

Open source

TensorRT-LLM

Serving

NVIDIA · Apache-2.0

An NVIDIA inference toolkit for building and serving highly optimized language-model engines on NVIDIA GPUs.

Self-hostedClusterLinux
Best for

Maximum serving performance on NVIDIA GPUs

Open source

vLLM

Serving

vLLM Project · Apache-2.0

A high-throughput inference and serving engine for production language-model APIs.

Self-hostedClusterLinux
Best for

High-throughput model APIs

Open source

Xinference

Serving

Xorbits · Apache-2.0

A model-serving platform for deploying language, embedding, reranking, image, and audio models.

Desktop / localSelf-hostedmacOSWindows
Best for

Serving several model types from one control plane

Open source

GPT4All

Runtimes

Nomic AI · MIT

A private desktop chat application and Python SDK for running GGUF language models on everyday computers.

Desktop / localSelf-hostedmacOSWindows
Best for

Offline desktop chat on consumer computers

Open source

KoboldCpp

Runtimes

KoboldCpp Project · AGPL-3.0

A compact GGUF runtime and web interface focused on local text generation, roleplay, and story workflows.

Desktop / localSelf-hostedmacOSWindows
Best for

Local creative writing and roleplay

Open source

KServe

GPU Infra

KServe Project · Apache-2.0

A Kubernetes-native inference platform for standardizing scalable predictive and generative model services.

ClusterLinuxKubernetes
Best for

Standardized model services on Kubernetes

Source available

LobeChat

Chat UIs

LobeHub · LobeHub Community License

A polished chat and agent workspace with provider routing, knowledge bases, plugins, and optional managed cloud.

Desktop / localSelf-hostedWebmacOS
Best for

Polished personal or team AI workspace

Open source

RAGFlow

Knowledge & RAG

InfiniFlow · Apache-2.0

A self-hosted RAG engine focused on document understanding, retrieval, and traceable answers.

Self-hostedLinuxDocker
Best for

Document-heavy knowledge systems

Open source

SGLang

Serving

SGLang Project · Apache-2.0

A high-performance serving framework for language and multimodal model workloads.

Self-hostedClusterLinux
Best for

High-performance language and multimodal serving