docker/docker-agent

AI Agent Builder and Runtime by Docker Engineering

What it solves

Docker Agent provides a no-code way to build, run, and share AI agents. It simplifies the process of creating intelligent assistants that can collaborate to solve complex problems by using a declarative YAML configuration instead of writing custom code.

How it works

It operates as a Docker CLI plugin. Users define agents, their instructions, and their toolsets in a YAML file. The system supports multi-agent orchestration where specialized agents can delegate tasks to one another. It integrates with various AI providers (OpenAI, Anthropic, Gemini, etc.) and supports the Model Context Protocol (MCP) for tool integration, as well as pluggable RAG capabilities for retrieval.

Who it’s for

Developers and users who want to deploy AI agents without writing code, as well as those who want to run agents locally via Docker Model Runner or via cloud APIs.

Highlights

  • Multi-agent architecture: Automatically delegates tasks between specialized agents.
  • Rich tool ecosystem: Supports built-in tools and any MCP server (local, remote, or Docker-based).
  • AI provider agnostic: Works with OpenAI, Anthropic, Gemini, AWS Bedrock, Mistral, xAI, and Docker Model Runner.
  • OCI Registry support: Agents can be pushed to and pulled from any OCI registry for easy sharing and versioning.
  • Built-in RAG: Includes pluggable retrieval with BM25, embeddings, hybrid search, and reranking.
  • YAML-based configuration: Declarative and versionable setup.

Related

  • Project
    microsoft/conductor

    A CLI tool for defining and running deterministic, version-controlled multi-agent workflows using YAML configurations and the GitHub Copilot SDK.

  • Project
    Ingenimax/agent-sdk-go

    A powerful Go framework for building production-ready AI agents with integrated memory management, multi-LLM support, and enterprise-grade observability.

  • Project
    evalstate/fast-agent

    A flexible framework for building multimodal AI agents and workflows with deep Model Context Protocol (MCP) integration and advanced orchestration patterns.

  • Project
    jnMetaCode/agency-orchestrator

    Agency Orchestrator is an npm‑based tool (CLI + web UI) that automatically composes and runs multi‑agent AI workflows from a single sentence or a tiny YAML file. It ships 276 pre‑built Chinese (and 191 English) role definitions, supports 15 LLM providers (many key‑less), builds a DAG for parallel execution, validates outputs, and produces shareable HTML reports. Ideal for solo entrepreneurs, product analysts, and developers who want an "AI team" without writing code.

  • Project
    microsoft/Agents

    A software development kit for creating AI agents that can be deployed across Microsoft 365 Copilot, Teams, and custom apps while remaining agnostic to the underlying AI provider.