One file, four outputs
The same workflow.yaml runs as an HTTP API, one binary, a container image, or a bootable ISO.
Ship the file
One YAML file, offline
kdeps turns one workflow.yaml into an offline API, a binary, an image, or an ISO. You review the YAML as a pull request, and kdeps test runs the evals. A check returns 400 before any model call. A chat with loop: is a bounded step in that file.
actionId: llmname: Ask the AIvalidations: check: - get('q') != '' # 400 before any model call error: code: 400 message: "'q' is required"chat: model: name: llama3.2:1b # local, no API key context: prompt: "{{ get('q') }}" loop: # a bounded agent step tools: [read_file] maxRounds: 5runs on
inside kdeps
Each box is something you get without writing glue code.
kdeps runs it. A request comes from an API, a bot, a file, or an interactive prompt.
A chat with loop: calls only the tools you name. maxRounds stops that step.
Pass --include-models to kdeps bundle prepackage. The llamafile stays in the executable, and the machine needs no network.
kdeps test runs the evals: in the process. The same judges review the answer before the resource finishes.
llamafile runs the model on your machine. No API key, no data leaves it.
Ship the same file as a Docker image, Kubernetes manifests, a bootable ISO, or one binary. Write the ISO to a USB stick.
who it's for
kdeps packages the model with the workflow. As a result, all of it runs in your boundary.
Deploy an internal RAG or document agent fully in the VPC of your customer. No prompts, documents, or embeddings go out of their infrastructure.
on-prem · regulatedShip the model and the workflow as a bootable ISO or one binary. Write the ISO to a USB stick. It runs on a disconnected device, with no network at inference time.
edge · offlineChange a YAML workflow into a production HTTP API and container. You do not need FastAPI, LangChain code, or a Dockerfile that you write manually. You declare the validation, the order, and the response shape.
workflowWorking examples. Each example is a project that you can run:
git-native
The YAML in your repository fully defines what the appliance does: the model, the validation, the step order, and the response shape. When you change the YAML and commit it, the behavior changes. Your git history is the changelog of the agent behavior. Only the model binding is outside the repository. As a result, the same commit runs with a local model on a laptop and with a cloud model in production.
validations:
check:
- get('q') != ''
+ - len(get('q')) < 2000 # reject prompts over 2000 characters
chat:
model:
- name: llama3.2:1b
+ name: qwen2.5:7b
context:
prompt: "{{ get('q') }}"One commit makes two behavior changes: a larger model, and a 400 error for input that is too large. You do not change a deploy configuration or a console setting. The diff is the change.
A change to an agent is a diff: a new resource, a stricter validation, or a different response shape. Review it in a pull request, as you review all other code.
A git tag is a release. kdeps test runs the evals on that tag. The built appliance also pins the runtime and the model.
In CI, check out a tag and run kdeps test. Then run kdeps validate and kdeps bundle build. The same commit always makes the same appliance.
With the registry, you can install and publish agents by name. kdeps install owner/repo pulls from a GitHub repository. You do not need the registry to build or deploy your own agent.
getting started
Write YAML. Run it. Ship the same file.
Put the steps in one workflow.yaml. A check can return 400 before the model runs. A chat with loop: is an agent, and maxRounds bounds it.
kdeps runs ./workflow.yaml as an API, a bot, a file processor, or a prompt. kdeps test runs the evals: in the process.
Ship that file as a Docker image, Kubernetes manifests, a bootable ISO, or one binary. Pass --include-models to kdeps bundle prepackage. That flag puts the llamafile in the binary.
compared to manual code
You do not write Python scripts, connection code, or boilerplate.
| Traditional approach | kdeps |
|---|---|
| Python script + Flask + OpenAI SDK + retry logic | One workflow.yaml file |
| Dependency code that you write manually | flow.requires: in YAML |
| Error handling that you write manually | onError: block (continue / retry / fail) |
| A Dockerfile and a CI pipeline for deployment | kdeps bundle build --tag then docker push |
| Agent chains that you write manually | agent: resource. One agent calls a different agent declaratively |
| A test server that you write | kdeps test runs evals: in the process |
| Handler code that checks the body after the model call | validations.check returns 400 before any model call |
book
From your first agent to production deployment, in one book.
Build & Deploy Autonomous AI Agents and Agencies in YAML
Your AI prototype works. Now ship it. This practical guide covers deterministic pipelines, multi-agent orchestration, error handling, and vendor-agnostic deployment. Most AI frameworks leave these production problems to you.
Read the book ->