DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Agent Workflow Platform: what you can do with it

What is Agent Workflow Platform? Agent Workflow Platform is an open-source TypeScript starter stack with an Electron desktop app, a FastAPI control plane, Python and Go workers, and a standalone workflow runtime for building Agent products.

How do I use it? Clone the repository with git clone https://github.com/primorLee/agent-workflow-platform.git and enter it with cd agent-workflow-platform; then start the stack with docker compose -f deploy/local/docker-compose.local-dev.yml up -d --build; wait for readiness with python scripts/wait_for_http.py http://127.0.0.1:8100/v1/health/ready --timeout 120 --json-field database. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

4 use cases

  • Verify a task round trip from control plane to worker

    Start the local Compose stack and confirm a submitted task completes through the FastAPI control plane and Python worker.

    View prompt
    In the agent-workflow-platform repository, start the Docker Compose local dev stack, wait for the health endpoint to report ready, and submit one task with scripts/submit_local_task.py. Report the printed result and confirm that scripts/verify_task_lifecycle.py finishes with every task in a terminal state.

  • Chat with a local model in the AWP desktop app

    Connect the Electron desktop workbench to an OpenAI-compatible local endpoint and get streamed replies.

    View prompt
    In the agent-workflow-platform repository, install the desktop app dependencies and launch the OpenAI-compatible Electron path with AWP_AGENT_MODEL set to the model name served by my local endpoint. Report whether a streamed reply appears in the window, and confirm that the conversation is still there after a restart.

  • Point the desktop app at a remote model endpoint

    Use a hosted OpenAI-compatible endpoint with an API token and an explicit opt-in flag.

    View prompt
    In the agent-workflow-platform repository, configure AWP_AGENT_MODEL, AWP_AGENT_API_BASE_URL, AWP_AGENT_API_TOKEN, and AWP_AGENT_REMOTE_API_OPT_IN=1 for the endpoint at <endpoint-url>, then launch the openai-compatible Electron path. Report whether one test message gets a streamed reply, and check that the token is read from the environment and is not written into the repository.

  • Add a durable task ledger with resume instructions

    Track tasks, heartbeats, and checkpoints in a file-backed ledger that a new session can resume from.

    View prompt
    In the agent-workflow-platform repository, add a task to the scheduler, send a heartbeat, and save a checkpoint with the status of <your-task>. Then run guardian.py resume in a new session and report the rebuilt resume instruction, confirming it comes from the durable state under .agent-workflow/.

Quick start with Agent Workflow Platform

  1. Check you have what it needs: Docker Engine or Docker Desktop with Compose, and Python 3.12, for the local round trip; Node.js 22.12 or newer, for the desktop workbench; A compatible Agent CLI or model endpoint, such as a local Ollama-compatible endpoint, for real model responses.
  2. Open primorLee/agent-workflow-platform on GitHub and read the README and license.
  3. Clone the repository with git clone https://github.com/primorLee/agent-workflow-platform.git and enter it with cd agent-workflow-platform.
  4. Start the stack with docker compose -f deploy/local/docker-compose.local-dev.yml up -d --build.
  5. Wait for readiness with python scripts/wait_for_http.py http://127.0.0.1:8100/v1/health/ready --timeout 120 --json-field database.
  6. Submit one task with python scripts/submit_local_task.py --timeout 60 and read the printed result.

These steps come from our top use case, Verify a task round trip from control plane to worker, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for primorLee/agent-workflow-platform

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Agent Workflow Platform alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers building an Agent product who want a local, runnable baseline for the desktop, control plane, and worker layers instead of building them from scratch.
  • Why it is hot105 stars, launched 65 days ago
  • LanguageTypeScript
  • Sourcegithub.com/primorLee/agent-workflow-platform · Back to Hot repos

Requirements

  • Docker Engine or Docker Desktop with Compose, and Python 3.12, for the local round trip
  • Node.js 22.12 or newer, for the desktop workbench
  • A compatible Agent CLI or model endpoint, such as a local Ollama-compatible endpoint, for real model responses
  • Python 3.10 or newer, for the standalone workflow runtime

Add this badge to your README

Maintain Agent Workflow Platform? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/primorLee/agent-workflow-platform.svg)](https://dedupedai.com/use-cases/primorlee-agent-workflow-platform/?utm_source=github&utm_medium=badge&utm_campaign=primorLee-agent-workflow-platform)

HTML 

<a href="https://dedupedai.com/use-cases/primorlee-agent-workflow-platform/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=primorLee-agent-workflow-platform"><img src="https://dedupedai.com/badge/primorLee/agent-workflow-platform.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Agent Workflow Platform

What is Agent Workflow Platform?

Agent Workflow Platform is an open-source TypeScript starter stack with an Electron desktop app, a FastAPI control plane, Python and Go workers, and a standalone workflow runtime for building Agent products. It is an open-source project on GitHub: https://github.com/primorLee/agent-workflow-platform.

How do I use Agent Workflow Platform?

Clone the repository with git clone https://github.com/primorLee/agent-workflow-platform.git and enter it with cd agent-workflow-platform; then start the stack with docker compose -f deploy/local/docker-compose.local-dev.yml up -d --build; wait for readiness with python scripts/wait_for_http.py http://127.0.0.1:8100/v1/health/ready --timeout 120 --json-field database. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Agent Workflow Platform for?

Developers building an Agent product who want a local, runnable baseline for the desktop, control plane, and worker layers instead of building them from scratch.

What can I do with Agent Workflow Platform?

4 use cases so far, for example: Verify a task round trip from control plane to worker; Chat with a local model in the AWP desktop app; Point the desktop app at a remote model endpoint. Each has steps and a copy-paste agent prompt.

What do I need to run Agent Workflow Platform?

Docker Engine or Docker Desktop with Compose, and Python 3.12, for the local round trip; Node.js 22.12 or newer, for the desktop workbench; A compatible Agent CLI or model endpoint, such as a local Ollama-compatible endpoint, for real model responses; Python 3.10 or newer, for the standalone workflow runtime.

What are alternatives to Agent Workflow Platform?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Agent Workflow Platform safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.