Skip to content
kdepsPublic

About

AI appliance builder. Define AI agents and workflows in YAML. Ship them as Docker, Kubernetes, ISO, or one standalone binary.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

38 stars

Watchers

1 watching

Forks

Latest commit

 

History

3,561 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

kdeps

Build and Test Coverage Release Go License CodeQL Docs Documentation Registry GitHub stars

kdeps turns one workflow.yaml into an offline API, a binary, an image, or an ISO. You review that file as a pull request. kdeps test runs its evals.

  1. Workflows - a YAML pipeline is the one way to run kdeps. Feed it from an HTTP API, a bot, a file, or an interactive prompt.
  2. Agents - a chat with loop: is an AI agent with tools and memory, inside the same workflow. kdeps new helper --template assistant starts one.
  3. Deploy on your infrastructure - ship the same YAML as a Docker image, Kubernetes manifests, a bootable ISO, or one binary.

Install

brew install kdeps/tap/kdeps                                              # macOS or Linux
curl -LsSf https://raw.githubusercontent.com/kdeps/kdeps/main/install.sh | sh   # or the install script
irm https://raw.githubusercontent.com/kdeps/kdeps/main/install.ps1 | iex   # Windows PowerShell

For other options, see the installation guide. If you upgrade from v2, see what changed.

1. Workflows

Save as workflow.yaml:

apiVersion: kdeps.io/v1
kind: Workflow
metadata:
  name: my-agent
  version: "1.0.0"
  targetActionId: response      # the resource whose output is returned
deploy:
  apiServer:
    portNum: 16395
    routes:
      - path: /api/v1/chat
        methods: [POST]
resources:
  - actionId: llm
    name: Ask the AI
    validations:
      check:
        - get('q') != ''        # reject the request before any model call
      error:
        code: 400
        message: "'q' is required"
    chat:
      model:
        name: llama3.2:1b        # local model, no API key
        timeout: 60s
      context:
        prompt: "{{ get('q') }}"
  - actionId: response
    name: Return the answer
    flow:
      requires: [llm]             # runs after llm
    apiResponse:
      success: true
      response:
        answer: get('llm').message.content

Run it and ask a question:

export KDEPS_API_AUTH_TOKEN=dev-token   # local testing only
kdeps run workflow.yaml

curl -s -X POST http://localhost:16395/api/v1/chat \
  -H "Authorization: Bearer $KDEPS_API_AUTH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"q": "Explain entropy in one sentence."}'

Resources run in dependency order. Independent resources run in parallel. The model can write a different answer each time. But for the same request, kdeps always runs the same steps in the same order.

A chat puts its keys in these groups: model, context, harness, tools, rag, and guardrails. Guardrail judges review and revise the answer. tools.list names built-in tools (web_search, calculator, subagent, ...), or auto for all of them. Judges are opt-in.

kdeps test . runs the evals: of a workflow in the process. It runs assertions, judges, and repeated runs against a pass-rate threshold.

For more data, see the workflow docs, examples, and agencies (many agents as one system).

2. Agents

An agent is a workflow whose chat has a loop: block: the model calls tools over many rounds and keeps one conversation per session.

kdeps new helper --template assistant   # interactive prompt + chat with loop:
cd helper && kdeps                      # bare kdeps runs ./workflow.yaml
kdeps --agent-loop                      # the agent REPL, with slash commands and a model picker
# helper/resources/assistant.yaml
chat:
  context:
    prompt: "{{ input('message') }}"
  loop:
    tools: [read_file, edit_file, bash_exec]   # the tools the agent may call
    session: "{{ get('session') }}"           # one conversation across prompts

File tools stay inside the working directory. In the REPL, a path outside it asks you first; ~/.kdeps and /tmp are exceptions.

For more data, see the agent docs.

3. Deploy on your infrastructure

kdeps bundle build .                                          # container image
kdeps export k8s .                                            # Kubernetes manifests
kdeps export iso .                                            # bootable ISO
kdeps bundle package .                                        # my-agent-1.0.0.kdeps
kdeps bundle prepackage my-agent-1.0.0.kdeps --include-models # binary with the model

Connect agents to an LLM server that you host. Then prompts and data stay on your network:

# ~/.kdeps/config.yaml
llm:
  backend: openai
  base_url: http://192.168.1.50:8000/v1   # your OpenAI-compatible server
  models:
    - llama3.2

kdeps llm wizard builds that server. For more data, see deploy, LLM server, and security.

Contributing

Read CONTRIBUTING.md. kdeps has the Apache 2.0 license.

About

AI appliance builder. Define AI agents and workflows in YAML. Ship them as Docker, Kubernetes, ISO, or one standalone binary.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

38 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages