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

How to point the desktop app at a remote model endpoint with Agent Workflow Platform

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

Short answer: Install desktop dependencies with npm --prefix apps/desktop ci; then set AWP_AGENT_MODEL to the model name your remote endpoint serves; set AWP_AGENT_API_BASE_URL to the endpoint base URL and AWP_AGENT_API_TOKEN to your token. All steps.

Authorization notice. Agent Workflow Platform is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. This path sends an API token to a remote endpoint, so store the token only in your environment and never commit it to the repository.

Who it is forA developer who wants the desktop workbench to use a remote compatible model service instead of a local one.

The problemA remote endpoint needs a token and an explicit opt-in, and mixing those up can send credentials to the wrong place.

The outcomeThe desktop app talks to the remote endpoint with the configured model, base URL, and token, and only after the opt-in is set.

What you need first

  • 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

Steps

  1. Install desktop dependencies with npm --prefix apps/desktop ci.
  2. Set AWP_AGENT_MODEL to the model name your remote endpoint serves.
  3. Set AWP_AGENT_API_BASE_URL to the endpoint base URL and AWP_AGENT_API_TOKEN to your token.
  4. Set AWP_AGENT_REMOTE_API_OPT_IN=1 to allow the remote call.
  5. Run npm --prefix apps/desktop run openai-compatible:electron and send a test message.

Prompt for your agent

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.

Caveat. The README requires the exact opt-in value AWP_AGENT_REMOTE_API_OPT_IN=1 for remote endpoints, and it does not describe how the token is stored beyond the environment variable.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for primorLee/agent-workflow-platform and "Point the desktop app at a remote model endpoint"

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

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