Zed Editor + Docker Agent + ACP: coding with a local agent plugged into llmman

A developer walkthrough shows how to connect the Zed code editor to Docker Agent, a YAML-configurable code agent runtime, through the open Agent Client Protocol (ACP), with Docker Agent pointed at llmman, a local model server that exposes an OpenAI-compatible API and uses llama.cpp as its inference engine. The setup installs Docker Agent via `brew install docker-agent`, runs `llmman serve`, and pulls a model such as huggingface.co/jetbrains/mellum2-12b-a2.5b-instruct-gguf-q4_k_m:Q4_K_M, with Docker Model Runner, Ollama, or any other OpenAI-API-compatible server offered as alternatives to llmman.

Zed Editor + Docker Agent + ACP: coding with a local agent plugged into llmman In two minutes in-two-minutes Today I'm showing you how to plug Zed https://zed.dev/ , my code editor, into an agent that runs locally , thanks to the ACP https://agentclientprotocol.com/get-started/introduction protocol. The agent in question is Docker Agent https://docker.github.io/docker-agent/ . And for the language model, I'm not going to call a cloud API: I'm going to point Docker Agent at llmman https://llmmanorg.github.io/ , which serves my local model behind an OpenAI-compatible API. I wrote an article on how to use llmman : k33g.org/p/20261001-llmman https://k33g.org/p/20261001-llmman . Here's a summary of my setup for this article: Of course, you can use other LLM engines instead of llmman : Docker Model Runner , Ollama , or any other server that speaks the OpenAI API will work just fine. More on that at the end of the article. Quick reminder on the 4 building blocks used quick-reminder-on-the-4-building-blocks-used Zed Editor zed-editor Zed https://zed.dev/ is a code editor that supports the ACP Agent Client Protocol protocol. Concretely, that means you can plug any ACP-compatible agent directly into Zed's agent panel, and chat with it just like you would with a built-in agent for example the Claude Code extension in VSCode . Documentation: zed.dev/acp/editor/zed https://zed.dev/acp/editor/zed ACP: Agent Client Protocol acp-agent-client-protocol ACP https://agentclientprotocol.com/get-started/introduction is an open protocol on the same model as LSP, but for agents that standardizes communication between a code editor the ACP client and a code agent the ACP server . The agent runs as a separate process, "speaks JSON-RPC" over stdin / stdout , and since it's a standard, the editor doesn't need to know the "inner workings" of the agent to use it. Documentation: agentclientprotocol.com https://agentclientprotocol.com/get-started/introduction and zed.dev/acp https://zed.dev/acp Docker Agent docker-agent Docker Agent https://docker.github.io/docker-agent/ is a code agent runtime even multi-agent configurable via a simple YAML file: you describe your providers how to connect to the model s , your agents instructions, model used, allowed tools and your models . It knows how to expose these agents through several interfaces, including... ACP . That's exactly what I need to bridge Zed and my local models. llmman llmman llmman https://llmmanorg.github.io/ is the tool that serves my local models behind a single API compatible with OpenAI but also Ollama and Anthropic . It relies on llama.cpp https://github.com/ggml-org/llama.cpp as the inference engine and manages models as OCI images Docker Hub, Hugging Face, private registry... . For this article, it'll be the server that Docker Agent queries to get the model's responses. I talked about it recently over here: k33g.org/p/20261001-llmman https://k33g.org/p/20261001-llmman , to explain how to install and use it a kind of first contact . Setting up all the components setting-up-all-the-components Install Docker Agent on macOS install-docker-agent-on-macos brew install docker-agent For other platforms, check the documentation: docker.github.io/docker-agent https://docker.github.io/docker-agent/ Start llmman as an LLM server start-llmman-as-an-llm-server If it's not already done see my dedicated article https://k33g.org/p/20261001-llmman for the installation : llmman serve Then you download a model from Hugging Face for example and check that everything went well: llmman pull huggingface.co/jetbrains/mellum2-12b-a2.5b-instruct-gguf-q4 k m:Q4 K M llmman list Configure Docker Agent to talk to llmman configure-docker-agent-to-talk-to-llmman Here's the configuration file I use, llmman.docker-agent.yaml : providers: llmman: api type: openai chatcompletions base url: http://127.0.0.1:17434/v1 agents: root: model: mellum description: A local code agent, powered by a small LLM. instruction: | Your name is Riker. You are a developer expert. You act as a mentor and coding partner. Tool discipline Built-in tools: - shell: use the shell tool to explore the project, read files, or run commands. Chain commands as long as it is useful, then give a clear final answer. Style Be concise. Prefer a small, correct, compilable example over prose. toolsets: - type: shell models: mellum: provider: llmman model: huggingface.co/jetbrains/mellum2-12b-a2.5b-instruct-gguf-q4 k m:Q4 K M The important bit is base url: http://127.0.0.1:17434/v1 : that's the address where llmman exposes its OpenAI-compatible API. Everything else agent, instructions, tools is standard Docker Agent configuration. Now that we have a model and a way to connect to it via an API and Docker Agent, let's make the connection with Zed. Declare the agent in Zed declare-the-agent-in-zed In Zed's settings settings.json , we add an agent servers section that contains a sub-section pointing to the docker-agent serve acp command with the path to our YAML file: "agent servers": { "🤖 Docker Agent llmman ": { "type": "custom", "command": "docker-agent", "args": "serve", "acp", "/Users/k33g/kDrive/Rickub/demo-docker-agent-acp/llmman.docker-agent.yaml" , "env": {} } } Of course, adapt the path to your own Docker Agent configuration file. Let's go lets-go Open Zed's agent panel, pick "🤖 Docker Agent llmman " from the list of available agents, and chat with it like with any code agent: it explores your project, reads files, runs shell commands, all while running entirely locally, on your own model: The agent asks whether you want to run a command: What if I don't want to use llmman? what-if-i-dont-want-to-use-llmman Nothing forces you to. The only contract between Docker Agent and the model server is an OpenAI-compatible API . So in the providers file, you can replace base url with any server that exposes this type of API: - Docker Model Runner https://docs.docker.com/ai/model-runner/ , which, like llmman , relies on llama.cpp internally. - Ollama https://ollama.com/ — with its OpenAI-compatible API. - ... or any other runtime that knows how to expose this same kind of endpoint. To sum up to-sum-up - Zed speaks ACP to Docker Agent . - Docker Agent speaks OpenAI API to a model server, here llmman , which relies on llama.cpp . - Everything runs locally. There you go, it's a simple setup to put in place, and it lets you keep full control over your model while enjoying Zed's developer/user experience. Feel free to ask questions 🙂 Written by Keep reading Zed Editor + Docker Agent + ACP, but in a sandbox: running the agent with sbx Run Docker Agent inside a Docker sandbox sbx and connect Zed to it over ACP, keeping llmman local while isolating the agent from your machine. Oct 4, 2026 Docker Agent + llama.cpp: a local code agent in 5 minutes 🤖💙🦙 Serve a GGUF model with llama.cpp, point Docker Agent at it with a short agent.yaml, and get a fully local code agent running in minutes. Sep 15, 2026 A mini code agent with Docker Agent - Part 8: a local agent to learn Rust Assemble a local Rust learning companion with Docker Agent: a cookbook RAG, a rust-analyzer LSP toolset, and the context caps that keep a small model alive. Aug 11, 2026 From other blogs