KDeps

Straightforward LLM dependency orchestration for multi-agent workflows.

Compose chat, code, and data into declarative pipelines in YAML. Export AI workflows as a single binary, ISO, Docker, or Kubernetes pods. Use Ollama, llamafile, or any cloud AI provider.

Get Started

Why kdeps?

Registry

workflow.yaml

run:
  chat:
    model: llama3.2:1b
    prompt: "Summarize: {{ get('q') }}"

  apiResponse:
    success: true
    response:
      data: "{{ get('chat') }}"

# No glue code. No legacy code.

running · port 16395startup: 0.1s

🏗️

Declarative Pipelines

Compose chat, code, and data into YAML pipelines with explicit control flow. No glue code, no boilerplate.

📦

Self-Contained Exports

Export AI workflows as a single binary, Docker image, bootable ISO, or Kubernetes pod.

🤖

Multi-Agent Orchestration

Coordinate specialized agents with dependency-based execution order. Chain LLM calls with code and data.

🛡️

Defined Control Flow

Predictable and auditable pipelines. Inputs are declared, outputs are typed, validations enforced before any LLM call.