AgentDock

AgentDock is an independent tool runtime that gives AI agents secure access to files, commands, and browsers across local and remote machines.

AgentDock is a runtime that provides controlled file, command, Git, and browser automation for AI agents. It functions by exposing tools over MCP (Model Context Protocol) via HTTP, allowing users to connect multiple instances to manage local computers, servers, and containers from a single conversation. Users can write code, run tests, manage Docker services, and operate authenticated web pages or desktop applications. It enforces explicit permission boundaries to ensure operations occur in secure environments while returning traceable results. The tool is designed for users needing to coordinate work across multiple devices without switching SSH sessions or relying on specific coding-agent quotas.

AgentDock at a glance

Best for: Software engineer
Runs on: macOS, Linux, Windows, Docker, Web
Pricing: Free
Released: May 2026
Category: AI agent tool
Website: github.com/uvwt/agentdock

Key features

Manage files, commands, and Git operations
Automate web browsers and macOS desktop applications
Coordinate cross-device workflows in a single chat
Execute and manage Docker services and containers
Persist long-running task states and resume after interruptions
Support dynamic MCP servers and extensible Skills
Verify results with structured, traceable output

Use it for

Managing multiple remote servers via a single AI chat interface
Executing cross-device workflows across local and remote infrastructure
Automating browser actions and desktop application tasks
Deploying and configuring Docker services and reverse proxies

Alternatives to AgentDock

Docker Agent — Builds and runs AI agents using a declarative YAML configuration.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
AgentFlux — Plans workflows from descriptions and runs locally in Docker.
Agent Executor — Declarative runtime for scaling stateful agent workloads with isolation.
Agensh — Scales to 1,024 self-organizing agents without a central orchestrator.
Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
CodePilot — Consolidates multiple AI agents and local model connections in one workspace.
Agent Squad — Runs multi-agent orchestration in Python, TypeScript, and locally on Apple devices.
Adyen — Share AI agent resources across coding tools and repositories easily.

All AgentDock alternatives