Self-Hosted AI Tools You Can Run in Docker

Agenta is an AI agent workspace for teams that want to delegate work and manage recurring tasks together. Agents plan their own steps, use connected tools and carry feedback into later work.

SnapOtter is a self-hosted application for people and teams who need to edit or convert private files without uploading them to an online processing service. It combines media, document and local AI tools in a browser interface.

MCP Gateway & Registry gives platform teams a shared catalog and access gateway for the tools their AI agents and coding assistants use. It addresses scattered server connections, credentials and access policies across an organization.

Video2X processes video on your own hardware to increase resolution or add frames for smoother motion. It's for people improving existing footage, with several processing methods suited to anime and other video.

local-transcriber is a free, open-source app for turning audio and video recordings into text on your own computer. It's aimed at people handling private interviews, client calls or long talks who want transcription without uploading recordings to a cloud service. It runs fully offline once the required models are downloaded.

Semantica is a Python toolkit for teams building AI systems that need shared context, traceable decisions and policy checks. It connects facts and decisions to their evidence in queryable knowledge graphs.

CliRelay is an AI gateway for teams that want to manage coding assistants through a shared service on their own server. It builds on CLIProxyAPI and brings subscription accounts and provider API keys under central control.

FATE is a self-hosted federated learning framework for enterprises and institutions that want to train models together while protecting data privacy. It supports collaboration across participating organizations and uses homomorphic encryption and multi-party computation (MPC) for secure computation.

Langroid is a Python framework for developers building applications where AI agents divide up a task. Each agent can maintain its own conversation and use documents or tools, then delegate work to other agents.

Agentgateway is an open-source proxy for platform teams connecting applications and agents to models, tools and other agents. It brings routing and access controls together across AI protocols and ordinary service traffic.

MetaGPT is a Python AI agent framework for developers who want to generate software projects using local models through Ollama or remote model APIs. The framework runs on your machine and writes a project repository locally. Its example configuration uses OpenAI, which sends model requests to that provider and requires API credentials.

Torch-TensorRT compiles PyTorch models with TensorRT to reduce inference latency on NVIDIA hardware. It's for developers running models on their own machines or servers who want faster execution while keeping their PyTorch workflow. The project is open source under the BSD 3-Clause license.

Vane is a self-hosted AI search engine for people who want answers backed by sources they can check. It combines web research with a choice of local or cloud models and saves search history locally.

dstack is a self-hosted AI compute orchestration tool for teams running development, training and inference across cloud providers and their own servers. It gives those workloads a shared interface across Kubernetes, VMs and bare-metal clusters.

Zep Community Edition is a self-hosted memory service for developers building AI agents and conversational assistants. It turns chat history into connected facts so an assistant can recall context across conversations and distinguish current preferences from older ones.

Fabric organizes reusable AI prompts by task for people who want repeatable ways to analyze content, write, or work with code. Its community-contributed prompts, called Patterns, provide a starting point without requiring you to write each prompt yourself.

Super Agent Party is an AI companion platform for people who want a desktop character that can also carry out tasks. It combines character conversations with agents that operate applications and interact through messaging or live streams.

OpenSandbox gives developers isolated environments for AI agents that need to execute code or interact with browsers and developer tools. It runs on your own infrastructure, locally with Docker or on a Kubernetes cluster.

python-audio-separator splits recordings into separate vocal and instrumental tracks on your own hardware. It's a Python package for karaoke creators and developers who want to process audio in scripts or applications.

GPT Crawler collects website text into knowledge files for people building AI assistants around documentation or other web content. It prepares the material a custom GPT or assistant can use to answer questions about a site.

VideoLingo is a video translation app for creators and educators producing bilingual subtitles or dubbed videos. Its self-hosted browser interface brings transcription, translation and subtitle preparation into one workflow, though the selected providers determine which processing stays local.

PenguinHarness builds runnable AI agent applications from plain-language requirements on your computer or server. It's for developers who want agents to handle app creation, evaluation, tuning and deployment.

HunyuanCustom generates videos of specific people or objects for creators and researchers who need subjects to stay recognizable across frames. It builds on HunyuanVideo and supports generation on your own hardware.

MCP Toolbox for Databases connects coding assistants and AI agents to databases. It's for developers who want assistants to inspect data during development or use defined database actions in applications.

TEN Framework is a self-hosted framework for developers building voice agents and multimodal conversational applications. Its default assistant example depends on external services even when the application runs on your hardware.

ai-memory keeps project context for developers who switch coding assistants or machines. It preserves unfinished work, failed approaches and open questions so the next session can pick up the task.

Ollama runs open models for people who want local AI applications, model chat or a backend for coding assistants. It provides a command-line interface and an API, with a choice between inference on your hardware and its cloud service.

AgentENV runs isolated environments for AI agents across your own servers. It's for teams building parallel agent workflows or reinforcement learning systems that need many separate sandboxes.

Label Studio is a platform for teams preparing training datasets or reviewing AI outputs. It brings human annotation and evaluation into a browser interface that can run locally or on your own server.

II Agent is an AI agent for developers and teams who want an assistant to carry out research, build applications and handle documents. It can act through a browser, shell and files to complete tasks that need several steps.

Crawl4AI is a web crawler and scraper for developers feeding websites into AI agents, RAG systems and data pipelines. It can extract useful page content without requiring an LLM.

Atlas Note combines a self-hosted note library with AI search and answers that cite your notes. It's for people keeping meeting records, project notes or personal reference material who want to find related information without remembering exact wording. The browser interface runs on your own Docker-hosted server, and the project is open source under the MIT license.

Pezzo helps developers and teams manage prompts and investigate problems in LLM applications. It brings prompt editing and monitoring into one place for projects where several people contribute to AI behavior.

RedAmon is an AI penetration testing framework for security teams testing systems they're authorized to assess. It connects attack-surface discovery, exploit testing and code fixes in one self-hosted workspace.