# Docker Agent Define agent teams in YAML and run them with tools on your own infrastructure. Canonical profile: https://ki-agentenkompass.de/en/agents/docker-agent/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-19 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Formerly cagent; a framework for custom agent teams. Docker Gordon is a separate offering. - Provider: Docker - Product family: Docker Agent - Profile type: Agent orchestration - Environment: Terminal; own computer or server - Connections: Define roles, Delegate, Combine models, Connect MCP, Share teams - Setup: Install standalone or use Docker Desktop 4.63 or later; configure model access. - Pricing model: Apache-2.0 software; models and operations are separate, with Docker Desktop licensing where applicable. ## Key features ### Define roles YAML describes tasks and instructions. Source: https://docs.docker.com/ai/docker-agent/ ### Delegate A root agent delegates work to subagents. Source: https://docs.docker.com/ai/docker-agent/ ### Combine models Agents can use different models. Source: https://docs.docker.com/ai/docker-agent/ ### Connect MCP External tools supplement built-in tools. Source: https://docs.docker.com/ai/docker-agent/ ### Share teams Distribute configurations through OCI registries. Source: https://docs.docker.com/ai/docker-agent/ ## Example workflows ### Example task 1 - Your input: Split bug diagnosis and repair between two agents. - Possible result: A draft for expert review. - What to check: Check inputs, output and performed actions. ### Example task 2 - Your input: Have a second agent review documentation. - Possible result: A draft for expert review. - What to check: Check inputs, output and performed actions. ## Requirements and limits ### Setup Requirement: Install standalone or use Docker Desktop 4.63 or later; configure model access. Source: https://docs.docker.com/ai/docker-agent/ ### Product boundaries Limitation: Configure and restrict tool permissions and model access yourself. Source: https://docs.docker.com/ai/docker-agent/ ### Output quality Not yet confirmed: Success rates and German-language operation have not been tested here. Source: https://docs.docker.com/ai/docker-agent/ ## A good fit if … - you want to define agent teams as a YAML file and run them in the terminal - you want to choose safety modes and permissions for tool calls yourself - you want to keep sessions locally in SQLite and resume them ## Less suitable if … - you expect a hosted interface with accounts, roles and admin management - you need ready-made schedules and failure notifications without building them yourself Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice You set the model per agent in the YAML file and supply your own API key, for example for OpenAI, Anthropic, Gemini, Mistral or xAI. OpenRouter is supported as well. Models run locally through Docker Model Runner, Nativ or any OpenAI-compatible server such as Ollama and vLLM, with no key needed. - Model families named: OpenAI (GPT), Anthropic (Claude), Google (Gemini), Mistral, xAI (Grok), DeepSeek · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes Documented · Sources accessed on: 2026-11-05 - [Docker Agent: Model providers](https://docs.docker.com/ai/docker-agent/model-providers/) - [Docker Agent: Repository](https://github.com/docker/docker-agent) ## Europe & regional availability Installation instructions and model prerequisites reviewed. The assessment covers the local operating path described; complete country and feature availability of all connected services remains open. Reviewed scope: Local software and documented self-hosting; external services assessed separately Reviewed on: 2026-10-19 ### Self-hosting with own model access With requirements Docker Agent can be installed as a standalone binary or Docker CLI plugin. The quickstart requires credentials for the selected model provider; check its regional availability and optional tools separately. Region covered: Europe: own computer or server; model services are country-specific Documented reason: Technical assessment based on installation and provider selection. These sources do not establish a legal cause for regional restrictions. Official source: https://docs.docker.com/ai/docker-agent/ ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Docker Agent (open source, Apache-2.0) in the terminal or as a local API server on your own machine Sources reviewed: 2026-11-05 ### Account used Documented: The reviewed pages mention no separate Docker Agent account. You set model access as environment variables such as ANTHROPIC_API_KEY or OPENAI_API_KEY; for local models the repository offers Docker Model Runner. Evidence: https://docs.docker.com/ai/docker-agent/ Evidence: https://github.com/docker/docker-agent ### Admin approval Open in reviewed sources: The CLI documentation mentions no central approval or restriction by an organisation admin. You configure restrictions yourself through safety modes and permissions. Evidence: https://docs.docker.com/ai/docker-agent/features/cli/ ### Data access & team sharing Documented: Agent configurations are YAML files; according to the docs each agent has its own context and shares no knowledge, and can use built-in tools such as todo lists, memory and task delegation. Configurations are packaged as OCI artifacts. The API server requires an auth token on non-loopback TCP listeners. Evidence: https://docs.docker.com/ai/docker-agent/ Evidence: https://docker.github.io/docker-agent/features/api-server/ ## Prices and included usage Pricing checked: 2026-10-19 Apache-2.0 software; models and operations are separate, with Docker Desktop licensing where applicable. Billing depends on plan, usage and setup. Pricing details: https://github.com/docker/docker-agent ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Docker Agent as a CLI (interactive or --exec) and as an API server on your own infrastructure Sources reviewed: 2026-11-05 ### Files and working state Documented: The agent is stateless between runs, the session is not: it is stored in a SQLite file in the data directory, by default ~/.cagent. According to the API docs, sessions survive server restarts. Evidence: https://docs.docker.com/ai/docker-agent/features/sessions/ Evidence: https://docker.github.io/docker-agent/features/api-server/ ### Sign-ins Open in reviewed sources: Access is via environment variables or tokens; the reviewed pages say nothing about expiry or renewal. Evidence: https://github.com/docker/docker-agent ### Starting further runs Documented with conditions: You start runs by command, headless with --exec, or through the API server. Scheduling appears in the API docs only as a tool named Scheduler, without details. Evidence: https://docker.github.io/docker-agent/features/api-server/ Evidence: https://docs.docker.com/ai/docker-agent/features/cli/ ### Human intervention Documented with conditions: Safety modes range from strict to autonomous; restricted fails closed for unattended runs. The docs advise configuring permissions or a safety mode for unattended use. With --yolo tool calls are approved automatically unless explicitly denied. The page does not state the default behaviour without configuration. Evidence: https://docs.docker.com/ai/docker-agent/features/cli/ ### Detecting errors Documented with conditions: --debug writes a log file (by default ~/.cagent/cagent.debug.log), --json emits newline-delimited events (with --exec), and docker agent doctor exits non-zero when an issue would prevent an agent from running. The CLI docs mention no notifications for failed runs. Evidence: https://docs.docker.com/ai/docker-agent/features/cli/ ### Resuming after failures Documented: With --session you resume an earlier session, with -1 the most recently created one. Through the API, POST /api/sessions/:id/resume continues a session paused after a tool confirmation. Evidence: https://docs.docker.com/ai/docker-agent/features/sessions/ Evidence: https://docker.github.io/docker-agent/features/api-server/ ### Editorial assessment Sessions, safety modes and resumption are documented, but you build operation, scheduling and failure alerts around the tool yourself. For unattended runs you need to choose the safety mode deliberately. ## Memory and conversation continuity Scope: Docker Agent with memory toolset enabled Sources accessed: 2026-11-04 Configurable SQLite storage with targeted search and full CRUD tools. ### Storage and scope Documented: The memory tool stores entries in SQLite; the default is ~/.cagent/memory//memory.db, with a configurable path. - [Memory Tool](https://docs.docker.com/ai/docker-agent/tools/memory/) - [Troubleshooting](https://docs.docker.com/ai/docker-agent/guides/troubleshooting/) ### Selection and timing Partly documented: The agent writes through add_memory and update_memory. Configuration and agent instructions determine usage; no universal extraction schedule is documented. - [Memory Tool](https://docs.docker.com/ai/docker-agent/tools/memory/) - [Troubleshooting](https://docs.docker.com/ai/docker-agent/guides/troubleshooting/) ### Inspect, edit and delete Documented: get_memories, update_memory and delete_memory provide reading, editing and targeted deletion by ID. - [Memory Tool](https://docs.docker.com/ai/docker-agent/tools/memory/) - [Troubleshooting](https://docs.docker.com/ai/docker-agent/guides/troubleshooting/) ### Agent and channel boundaries Documented: Agents in the same configuration share the database by default. Separate paths per toolset isolate their memories. - [Memory Tool](https://docs.docker.com/ai/docker-agent/tools/memory/) - [Troubleshooting](https://docs.docker.com/ai/docker-agent/guides/troubleshooting/) ### Retrieval Documented: search_memories searches by keywords and/or categories; get_memories retrieves all entries. - [Memory Tool](https://docs.docker.com/ai/docker-agent/tools/memory/) - [Troubleshooting](https://docs.docker.com/ai/docker-agent/guides/troubleshooting/) ### Session reset and compaction Documented: Memory survives sessions. /compact summarizes conversation history; stored sessions and memory are distinct stores. - [Memory Tool](https://docs.docker.com/ai/docker-agent/tools/memory/) - [Troubleshooting](https://docs.docker.com/ai/docker-agent/guides/troubleshooting/) ## Context Configure and restrict tool permissions and model access yourself. Provider sources reviewed; examples are editorial suggestions. No hands-on test. ## Open points Requirements and limits, not yet confirmed: - Output quality ## Sources - https://docs.docker.com/ai/docker-agent/ - https://github.com/docker/docker-agent ## Provider Product and provider are documented through the linked original sources. - Operator: Docker - Organization: Provider - Website: https://docs.docker.com/ai/docker-agent/ - Reviewed: 2026-10-19 - Provider source: https://docs.docker.com/ai/docker-agent/ - Provider source: https://github.com/docker/docker-agent [Sources and method](https://ki-agentenkompass.de/en/sources/)