# docker/docker-agent

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/docker-docker-agent).**

3,099 stars · 395 forks · Go · Apache-2.0

## Links

- GitHub: https://github.com/docker/docker-agent
- Homepage: https://docker.github.io/docker-agent/
- awesome-repositories: https://awesome-repositories.com/repository/docker-docker-agent.md

## Topics

`agents` `ai`

## Description

This project is a container-native runtime designed for building, orchestrating, and executing autonomous AI agents. It provides a framework for managing multi-agent teams and complex workflows by packaging agent configurations as portable container images. By leveraging declarative configuration files, the system allows users to define agent personas, model routing, and tool access without requiring changes to application code.

The platform distinguishes itself through its deep integration with container infrastructure, ensuring that agent tasks and external tools run within isolated environments for secure and reproducible execution. It features a model-agnostic provider routing layer that enables automatic failover and cost-optimized request dispatching across multiple AI model providers. Furthermore, the runtime implements the Model Context Protocol to integrate specialized tools and external services, while supporting hierarchical delegation where root agents coordinate specialized sub-agents for modular task execution.

The system covers a broad capability surface including automated software development, retrieval-augmented generation pipelines, and stateful session management. It provides comprehensive tools for monitoring agent states, enforcing security through sandbox networking and granular permission controls, and optimizing performance via intelligent request routing and token generation acceleration.

The project is implemented in Go and supports embedding its agentic capabilities directly into external applications.

## Tags

### Artificial Intelligence & ML

- [Autonomous Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-orchestration.md) — Coordinates multi-agent teams and complex workflows by delegating tasks to specialized sub-agents within isolated containerized environments.
- [Hierarchical Task Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/hierarchical-task-delegation.md) — Supports complex workflows by allowing root agents to spawn and coordinate specialized sub-agents.
- [Agent Session Management](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-session-management.md) — Manages conversation history, context windows, and state persistence for long-running agent sessions. ([source](https://github.com/docker/docker-agent/blob/main/CHANGELOG.md))
- [Agent Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-configurations.md) — Defines agent behavior, model selection, and tool integration through structured configuration files. ([source](https://github.com/docker/docker-agent#readme))
- [Multi-Agent Orchestration Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/multi-agent-orchestration-platforms.md) — Manages multi-agent teams and complex workflows by packaging agent configurations as portable container images for consistent execution.
- [Model Context Protocol](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/model-context-protocol.md) — Integrates specialized tools and external services using the Model Context Protocol for consistent data exchange and system interoperability.
- [AI Agent Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-frameworks.md) — Defines agent personas, model routing, and tool access through declarative configuration files to standardize behavior across environments.
- [Collaborative AI Agent Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-execution-runtimes/collaborative-ai-agent-runtimes.md) — Provides a container-native runtime for building, orchestrating, and executing autonomous agents that interact with local files and tools.
- [Model Provider Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-abstractions.md) — Provides a unified abstraction layer for automatic failover and cost-optimized request dispatching across AI providers.
- [Model Provider Management](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-management.md) — Automates API key detection, model fallback, and connectivity across multiple AI model providers. ([source](https://github.com/docker/docker-agent/blob/main/CHANGELOG.md))
- [Multi-Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestrators.md) — Coordinates teams of specialized agents to solve complex, multi-step tasks through collaborative delegation. ([source](https://github.com/docker/docker-agent#readme))
- [Multi-Model AI Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-model-ai-orchestrators.md) — Orchestrates multiple AI model providers with automated failover and cost-optimized request dispatching to balance reasoning performance.
- [Sub-Agent Task Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-delegation/sub-agent-task-delegation.md) — Offloads complex tasks to specialized child agents that maintain their own context and tool sets. ([source](https://docker.github.io/docker-agent/concepts/multi-agent))
- [Local File Contexts](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-file-attachments/local-file-contexts.md) — Attaches local files to agent contexts for analysis while respecting project ignore patterns. ([source](https://docker.github.io/docker-agent/features/tui))
- [Hybrid Search Retrievers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-rag-development/knowledge-base-retrieval/hybrid-search-retrievers.md) — Combines multiple retrieval strategies in parallel and fuses results using ranking methods to improve search accuracy. ([source](https://docker.github.io/docker-agent/tools/rag))
- [Agentic Reasoning Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-reasoning-loops.md) — Provides scratchpads and interactive prompting to guide complex agent decision-making. ([source](https://docker.github.io/docker-agent/concepts/tools))
- [MCP Server Connections](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/model-context-protocol/mcp-server-management/mcp-server-connections.md) — Integrates specialized tools from local or remote servers using the Model Context Protocol. ([source](https://docker.github.io/docker-agent/concepts/tools))
- [Multi-Protocol Tool Exposures](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-integrations/ai-agent-tool-integrations/multi-protocol-tool-exposures.md) — Exposes custom agents as standardized tools compatible with the Model Context Protocol. ([source](https://docker.github.io/docker-agent/features/mcp-mode))
- [Conversation Context Routers](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-context-routers.md) — Transfers active conversation contexts to other agents to enable sequential pipelines or peer-to-peer workflows. ([source](https://docker.github.io/docker-agent/concepts/multi-agent))
- [Knowledge Indexing](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-indexing.md) — Processes documents into searchable chunks using semantic embeddings or keyword matching to enable retrieval by agents. ([source](https://docker.github.io/docker-agent/tools/rag))
- [Local Model Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-execution.md) — Executes open-source AI models locally within isolated environments for privacy. ([source](https://docker.github.io/docker-agent/providers/overview))
- [Local RAG Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-execution/local-rag-pipelines.md) — Provides retrieval-augmented generation pipelines that index local documentation using hybrid search strategies to ground agent responses. ([source](https://github.com/docker/docker-agent/tree/main/examples))
- [Model Context Protocol Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-context-protocol-implementations.md) — Implements the Model Context Protocol to integrate specialized tools and external services into agent workflows.
- [Agent Prediction Evaluations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-prediction-evaluation/agent-prediction-evaluations.md) — Evaluates agent trajectories and tool-call sequences against expected results using model-based judges. ([source](https://docker.github.io/docker-agent/features/cli))
- [Failover Mechanisms](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-management/failover-mechanisms.md) — Switches automatically between AI model providers to ensure continuous operation during outages. ([source](https://docker.github.io/docker-agent/concepts/agents))
- [Multi-Model Workflow Coordinators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-model-workflow-coordinators.md) — Sequences different AI models through logic paths to balance reasoning capability and operational costs. ([source](https://docker.github.io/docker-agent/providers/overview))
- [Retrieval Augmented Generation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/retrieval-augmented-generation-pipelines.md) — Grounds agent responses in project knowledge by indexing local documentation and source code for hybrid search and semantic retrieval.
- [Structured Output Enforcements](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-output-enforcements.md) — Constrains agent output to adhere to specific data schemas for reliable downstream integration. ([source](https://docker.github.io/docker-agent/configuration/overview))

### Data & Databases

- [Agent State Persistence](https://awesome-repositories.com/f/data-databases/agent-state-persistence.md) — Maintains persistent task lists, key-value data, and shared databases across sessions to ensure continuity in long-running agent workflows. ([source](https://docker.github.io/docker-agent/concepts/tools))
- [File System Restoration](https://awesome-repositories.com/f/data-databases/consistency-tuning/point-in-time-snapshots/file-system-restoration.md) — Records filesystem states at turn boundaries to allow reverting workspace changes to previous points. ([source](https://docker.github.io/docker-agent/features/tui))

### Security & Cryptography

- [Secure Sandboxing](https://awesome-repositories.com/f/security-cryptography/secure-sandboxing.md) — Enforces secure execution by isolating agent tasks within containers and applying path-level filesystem controls and secret redaction. ([source](https://github.com/docker/docker-agent/blob/main/examples/README.md))
- [Agent Sandboxing Policies](https://awesome-repositories.com/f/security-cryptography/network-access-control/agent-sandboxing-policies.md) — Manages agent container security through persistent network allowlists and granular access policies. ([source](https://docker.github.io/docker-agent/features/cli))
- [Tool Execution Permissions](https://awesome-repositories.com/f/security-cryptography/permission-based-access-control/tool-execution-permissions.md) — Governs agent tool usage through granular pattern-based rules and configurable automatic approval modes. ([source](https://docker.github.io/docker-agent/features/tui))

### Software Engineering & Architecture

- [Orchestration Configuration Files](https://awesome-repositories.com/f/software-engineering-architecture/application-lifecycle-management/configuration-management/configuration-formats-and-schemas/yaml-configuration-files/agent-configuration-files/orchestration-configuration-files.md) — Defines agent personas, tool access, and model selection through structured declarative configuration files.
- [Container Isolation](https://awesome-repositories.com/f/software-engineering-architecture/execution-control/namespace-isolation/namespace-provisioners/container-isolation.md) — Ensures secure and reproducible execution by running agent tasks within isolated container environments.
- [Automated Development Workflows](https://awesome-repositories.com/f/software-engineering-architecture/automated-development-workflows.md) — Automates the software development lifecycle by analyzing requirements, modifying code, and validating changes. ([source](https://github.com/docker/docker-agent/blob/main/golang_developer.yaml))
- [Headless Runtimes](https://awesome-repositories.com/f/software-engineering-architecture/headless-runtimes.md) — Provides a headless interface for embedding conversational agent capabilities into external applications. ([source](https://github.com/docker/docker-agent/blob/main/CHANGELOG.md))
- [Parallel Task Execution](https://awesome-repositories.com/f/software-engineering-architecture/parallel-task-execution.md) — Executes multiple independent agent tasks concurrently and aggregates their results. ([source](https://docker.github.io/docker-agent/concepts/multi-agent))
- [Agentic Error Recovery](https://awesome-repositories.com/f/software-engineering-architecture/self-healing-architectures/agentic-error-recovery.md) — Resumes interrupted agent turns from the point of failure using persistent retry controls to ensure continuous operation. ([source](https://docker.github.io/docker-agent/features/tui))
- [Model-Aware Request Routings](https://awesome-repositories.com/f/software-engineering-architecture/service-request-routing/model-aware-request-routings.md) — Dispatches tasks to different models based on complexity and tool requirements to balance performance with operational costs. ([source](https://github.com/docker/docker-agent/blob/main/examples/README.md))
- [Standardized Protocol-Based Integrations](https://awesome-repositories.com/f/software-engineering-architecture/standardized-protocol-based-integrations.md) — Uses standardized communication protocols to ensure consistent data exchange between agents and external utilities.

### Part of an Awesome List

- [Agent Endpoints](https://awesome-repositories.com/f/awesome-lists/devtools/rest-apis/agent-endpoints.md) — Exposes agent capabilities via HTTP and chat-compatible endpoints for external integration. ([source](https://docker.github.io/docker-agent/features/cli))

### Development Tools & Productivity

- [Autonomous Coding Agents](https://awesome-repositories.com/f/development-tools-productivity/autonomous-coding-agents.md) — Automates software engineering tasks by delegating code analysis, testing, and infrastructure management to specialized autonomous agents.
- [Custom Command Definitions](https://awesome-repositories.com/f/development-tools-productivity/cli-command-frameworks/custom-command-definitions.md) — Creates custom prompts that function as commands with dynamic environment variable interpolation. ([source](https://docker.github.io/docker-agent/concepts/agents))
- [Session State Persistence](https://awesome-repositories.com/f/development-tools-productivity/database-session-management/session-state-persistence.md) — Maintains conversation history and filesystem snapshots to enable continuity across long-running operations.
- [Shell Command Execution](https://awesome-repositories.com/f/development-tools-productivity/shell-command-execution.md) — Triggers and controls operating system shell commands for system-level interactions. ([source](https://docker.github.io/docker-agent/concepts/tools))

### DevOps & Infrastructure

- [Containerized Task Execution](https://awesome-repositories.com/f/devops-infrastructure/container-deployment/containerized-task-execution.md) — Executes autonomous agent tasks within isolated container environments to securely manage filesystem access and shell operations.
- [Agent Container Deployments](https://awesome-repositories.com/f/devops-infrastructure/container-orchestration/container-runtimes/runtime-configuration-interfaces/docker-socket-orchestrators/docker-target-configurators/docker-container-deployments/agent-container-deployments.md) — Packages agent configurations as portable container images to enable versioning, sharing, and consistent execution across environments. ([source](https://docker.github.io/docker-agent/))
- [Container Registries](https://awesome-repositories.com/f/devops-infrastructure/container-registries.md) — Packages agent configurations as container images for versioning and distribution via standard registries.
- [Containerized Tooling](https://awesome-repositories.com/f/devops-infrastructure/containerized-tooling.md) — Runs external tools and services as isolated processes within containerized environments. ([source](https://docker.github.io/docker-agent/getting-started/quickstart))

### Operating Systems & Systems Programming

- [Filesystem Operations](https://awesome-repositories.com/f/operating-systems-systems-programming/filesystem-operations.md) — Provides low-level operations for reading, writing, and navigating files to support automated manipulation tasks. ([source](https://docker.github.io/docker-agent/concepts/tools))

### Programming Languages & Runtimes

- [Libraries](https://awesome-repositories.com/f/programming-languages-runtimes/c-library-embedding/runtime-embedding/libraries.md) — Allows embedding agentic capabilities directly into external applications via library imports. ([source](https://github.com/docker/docker-agent/blob/main/examples/README.md))

### Web Development

- [Agent Lifecycle Hooks](https://awesome-repositories.com/f/web-development/third-party-api-integrations/model-tool-calls/standardized-tool-execution/tool-call-wrappers/agent-tool-interception/agent-lifecycle-hooks.md) — Triggers custom logic before or after tool execution and model calls to handle state and post-processing. ([source](https://github.com/docker/docker-agent/blob/main/examples/README.md))