# Docker Agent

## Docs

- [Contributing](https://mintlify.wiki/docker/docker-agent/community/contributing.md): docker-agent is open source. Here's how to set up your development environment and contribute.
- [Telemetry](https://mintlify.wiki/docker/docker-agent/community/telemetry.md): docker-agent collects anonymous usage data to help improve the tool. Telemetry can be disabled at any time.
- [Troubleshooting](https://mintlify.wiki/docker/docker-agent/community/troubleshooting.md): Common issues and how to resolve them when working with docker-agent.
- [Agents](https://mintlify.wiki/docker/docker-agent/concepts/agents.md): An agent is an AI-powered entity with a model, instructions, tools, and optional sub-agents — the core building block of docker-agent.
- [Models](https://mintlify.wiki/docker/docker-agent/concepts/models.md): Models are the AI engines behind your agents. Docker Agent supports multiple providers and flexible configuration via inline references or named model definitions.
- [Multi-Agent Systems](https://mintlify.wiki/docker/docker-agent/concepts/multi-agent.md): Build teams of specialized agents that collaborate and delegate tasks to each other.
- [Tools](https://mintlify.wiki/docker/docker-agent/concepts/tools.md): Tools give agents the ability to act in the world — read files, run commands, search the web, query databases, and more.
- [Agent configuration](https://mintlify.wiki/docker/docker-agent/configuration/agents.md): Complete reference for all fields in an agent definition.
- [Hooks](https://mintlify.wiki/docker/docker-agent/configuration/hooks.md): Run shell commands at lifecycle events to validate, log, block, or modify agent behavior.
- [Model configuration](https://mintlify.wiki/docker/docker-agent/configuration/models.md): Complete reference for defining models with providers, parameters, and reasoning settings.
- [Configuration overview](https://mintlify.wiki/docker/docker-agent/configuration/overview.md): docker-agent uses YAML configuration files to define agents, models, tools, and their relationships.
- [Permissions](https://mintlify.wiki/docker/docker-agent/configuration/permissions.md): Control which tools auto-approve, require user confirmation, or are blocked entirely.
- [Model routing](https://mintlify.wiki/docker/docker-agent/configuration/routing.md): Route requests to different models based on message content using rule-based routing.
- [Sandbox mode](https://mintlify.wiki/docker/docker-agent/configuration/sandbox.md): Run agents in an isolated Docker container for enhanced security.
- [Structured output](https://mintlify.wiki/docker/docker-agent/configuration/structured-output.md): Constrain agent responses to a predefined JSON schema for machine-readable output.
- [Tool configuration](https://mintlify.wiki/docker/docker-agent/configuration/tools.md): Complete reference for configuring built-in tools, MCP tools, and Docker-based tools.
- [A2A Protocol](https://mintlify.wiki/docker/docker-agent/features/a2a.md): Expose Docker Agent agents via the Agent-to-Agent (A2A) protocol for interoperability with other agent frameworks.
- [ACP (Agent Client Protocol)](https://mintlify.wiki/docker/docker-agent/features/acp.md): Expose Docker Agent agents via the Agent Client Protocol for integration with ACP-compatible hosts like IDEs and developer tools.
- [API Server](https://mintlify.wiki/docker/docker-agent/features/api-server.md): Expose your agents via an HTTP API for programmatic access, web frontends, and integrations.
- [CLI Reference](https://mintlify.wiki/docker/docker-agent/features/cli.md): Complete reference for all Docker Agent command-line commands and flags.
- [Evaluation](https://mintlify.wiki/docker/docker-agent/features/evaluation.md): Test agent behavior systematically with Docker Agent's built-in evaluation framework.
- [MCP Mode](https://mintlify.wiki/docker/docker-agent/features/mcp-mode.md): Expose Docker Agent agents as MCP tools for use in Claude Desktop, Claude Code, and other MCP-compatible applications.
- [RAG (Retrieval-Augmented Generation)](https://mintlify.wiki/docker/docker-agent/features/rag.md): Give your agents access to document knowledge bases with background indexing, multiple retrieval strategies, and hybrid search.
- [Skills](https://mintlify.wiki/docker/docker-agent/features/skills.md): Skills provide specialized instructions that agents can load on demand when a task matches a skill's description.
- [Terminal UI (TUI)](https://mintlify.wiki/docker/docker-agent/features/tui.md): Docker Agent's default interface is a rich, interactive terminal UI with file attachments, themes, session management, and more.
- [Installation](https://mintlify.wiki/docker/docker-agent/getting-started/installation.md): Get docker-agent running on your system in minutes.
- [Quickstart](https://mintlify.wiki/docker/docker-agent/getting-started/quickstart.md): Get up and running with docker-agent in under 5 minutes.
- [Go SDK](https://mintlify.wiki/docker/docker-agent/guides/go-sdk.md): Use docker-agent as a Go library to embed AI agents in your applications.
- [Tips & best practices](https://mintlify.wiki/docker/docker-agent/guides/tips.md): Expert guidance for building effective, efficient, and secure agents.
- [Docker Agent](https://mintlify.wiki/docker/docker-agent/introduction.md): Build, run, and share AI agents with a declarative YAML config, rich tool ecosystem, and multi-agent orchestration — by Docker.
- [Anthropic](https://mintlify.wiki/docker/docker-agent/providers/anthropic.md): Use Claude Sonnet 4, Claude Sonnet 4.5, and other Anthropic models with docker-agent.
- [AWS Bedrock](https://mintlify.wiki/docker/docker-agent/providers/bedrock.md): Access Claude, Nova, Llama, and more through AWS infrastructure with enterprise-grade security and compliance.
- [Custom providers](https://mintlify.wiki/docker/docker-agent/providers/custom.md): Connect docker-agent to any OpenAI-compatible API endpoint using the providers section.
- [Docker Model Runner](https://mintlify.wiki/docker/docker-agent/providers/dmr.md): Run AI models locally with Docker — no API keys, no costs, full data privacy.
- [Google Gemini](https://mintlify.wiki/docker/docker-agent/providers/google.md): Use Gemini 2.5 Flash, Gemini 3 Pro, and other Google models with docker-agent.
- [Local models](https://mintlify.wiki/docker/docker-agent/providers/local.md): Run docker-agent with locally hosted models using Ollama, vLLM, LocalAI, or any OpenAI-compatible server.
- [MiniMax](https://mintlify.wiki/docker/docker-agent/providers/minimax.md): Use MiniMax AI models with docker-agent.
- [Mistral](https://mintlify.wiki/docker/docker-agent/providers/mistral.md): Use Mistral AI models with docker-agent.
- [Nebius](https://mintlify.wiki/docker/docker-agent/providers/nebius.md): Use Nebius AI models with docker-agent.
- [OpenAI](https://mintlify.wiki/docker/docker-agent/providers/openai.md): Use GPT-4o, GPT-5, GPT-5-mini, and other OpenAI models with docker-agent.
- [Model providers](https://mintlify.wiki/docker/docker-agent/providers/overview.md): docker-agent supports multiple AI model providers. Choose the right one for your use case, or use multiple providers in the same configuration.
- [xAI (Grok)](https://mintlify.wiki/docker/docker-agent/providers/xai.md): Use xAI's Grok models with docker-agent.
- [A2A](https://mintlify.wiki/docker/docker-agent/tools/a2a.md): Connect to remote agents via the Agent-to-Agent protocol.
- [API](https://mintlify.wiki/docker/docker-agent/tools/api.md): Define HTTP API calls as named tools with typed parameters.
- [Background agents](https://mintlify.wiki/docker/docker-agent/tools/background-agents.md): Dispatch work to sub-agents concurrently and collect results asynchronously.
- [Fetch](https://mintlify.wiki/docker/docker-agent/tools/fetch.md): Make HTTP requests to external APIs and web pages.
- [Filesystem](https://mintlify.wiki/docker/docker-agent/tools/filesystem.md): Read, write, list, search, and navigate files and directories.
- [Handoff](https://mintlify.wiki/docker/docker-agent/tools/handoff.md): Transfer the conversation to another agent in the same configuration.
- [LSP](https://mintlify.wiki/docker/docker-agent/tools/lsp.md): Connect to Language Server Protocol servers for code intelligence.
- [Memory](https://mintlify.wiki/docker/docker-agent/tools/memory.md): Persistent key-value storage backed by SQLite for cross-session recall.
- [Script](https://mintlify.wiki/docker/docker-agent/tools/script.md): Define custom shell scripts as named tools with typed parameters.
- [Shell](https://mintlify.wiki/docker/docker-agent/tools/shell.md): Execute shell commands in the user's environment.
- [Think](https://mintlify.wiki/docker/docker-agent/tools/think.md): Step-by-step reasoning scratchpad for planning and decision-making.
- [Todo](https://mintlify.wiki/docker/docker-agent/tools/todo.md): Task list management for complex multi-step workflows.
- [Transfer task](https://mintlify.wiki/docker/docker-agent/tools/transfer-task.md): Delegate a task to a sub-agent and receive the result.
- [User prompt](https://mintlify.wiki/docker/docker-agent/tools/user-prompt.md): Pause execution and ask the user a question interactively.