AWF - AI Workflow Framework

The problem with AI workflows today

Unreliable execution

AI workflows fail silently. No audit trail. No reproducibility.

Vendor lock-in

Switching LLM providers means rewriting your entire workflow.

Production nightmares

No validation, no monitoring, no guarantees for production use.

AWF transforms AI workflows

Lightning Fast

Written in Go for blazing performance. Every millisecond counts.

Provider Agnostic

Switch between OpenAI, Anthropic, Mistral without changing workflows.

Production Ready

Audit, validate, and verify every step. Built for reliability.

Fully Extensible

Custom plugins and step types. Make it yours.

Simple YAML, powerful results

code-review.yaml

# Code review workflow
name: code-review
version: "1.0.0"

inputs:
  - name: file
    type: string
    required: true

states:
  initial: read

  read:
    type: step
    command: cat "{{.inputs.file}}"
    on_success: analyze

  analyze:
    type: agent
    provider: claude
    prompt: |
      Review this code for bugs and security issues:
      {{.states.read.Output}}
    on_success: report

  report:
    type: step
    command: echo "Analysis complete"
    on_success: done

  done:
    type: terminal
    status: success

Define your entire workflow in a single YAML file. Human-readable, version-controllable, and production-ready.

See it in action

Execute your workflows with a single command. AWF provides detailed logging, step tracking, and clear completion status with workflow IDs for reproducibility.

Terminal

$ awf run code-review --input file=service.go --output=streaming --verbose=true

registered desktop notification backend
registered webhook notification backend
Running workflow: code-review
starting workflow workflow=code-review id=3eb274fa-186e-4070-a6a0-c26eea61ad28
executing step step=read
executing step step=analyze
executing agent step step=analyze provider=claude
executing step step=report
[OUT] Analysis complete
recorded execution history workflow_id=3eb274fa-186e-4070-a6a0-c26eea61ad28 status=completed
workflow completed step=done status=completed
  ✓ read: completed successfully
Workflow completed successfully in 36.6s
Workflow ID: 3eb274fa-186e-4070-a6a0-c26eea61ad28

--- Execution Details ---
Status: completed
Steps executed:
  report:    completed (1ms)
  read:      completed (1ms)
  analyze:   completed (36.585s)

AWF provides detailed execution logs, validation feedback, and clear success/failure status for every workflow run.

Start Building

Get up and running in seconds. Choose your preferred installation method.

install.sh

curl -fsSL https://raw.githubusercontent.com/awf-project/cli/main/scripts/install.sh | sh

go install

go install github.com/awf-project/cli/cmd/awf@latest

build from source

git clone https://github.com/awf-project/cli.git
cd cli
make build
make install

...and every other tool in your terminal

gh rtk jq grepai make curl ripgrep sed awk tree-sitter npm go cargo composer cat grep find

If it's in your PATH, it's in your workflow. AWF orchestrates any CLI utility with zero configuration.

Orchestrate AI workflows
with precision