# Create a code assistant that learns from your GitHub repository: n8n workflow

> Started by someone opening a chat with it, and works across GitHub and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/create-a-code-assistant-that-learns-from-your-github-reposit (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library)

# Create a code assistant that learns from your GitHub repository

Started by someone opening a chat with it, and works across GitHub and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 16 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-a-code-assistant-that-learns-from-your-github-reposit)

**16 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 2 Model 11 Logic 1 Service 2

The steps in the order they run, from what starts it.

- 1 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 2 **Window Buffer Memory** Memory Buffer Window *Model*
- 3 **When chat message received** Chat trigger *Starts it*
- 4 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 5 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 6 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 7 **OpenAI Chat Model1** Lm Chat Open Ai *Model*
- 8 **Sync Data** Manual trigger *Starts it*
- 9 **Default Data Loader** Document Default Data Loader *Model*
- 10 **AI Agent** Agent *Model*
- 11 **Simple Vector Store1** Vector Store In Memory *Model*
- 12 **Simple Vector Store** Vector Store In Memory *Model*
- 13 **Vector Store Tool** Tool Vector Store *Model*
- 14 **Config** Set *Logic*
- 15 **List files** Github *Service*
- 16 **Get File** Http Request *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 16
- **Size:** Medium: a working afternoon
- **Connects to:** GitHub, in-memory vectors
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own GitHub and in-memory vectors accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 16 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 16 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-a-code-assistant-that-learns-from-your-github-reposit)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[GitHub](https://millionrounds.com/workflows?service=GitHub#library)[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**Gmail smart auto-responder with OpenAI and Google Drive** 17 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/gmail-smart-auto-responder-with-openai-and-google-drive)
- [**Optimize unstructured data for RAG with Blockify IdeaBlocks** 15 steps · calls a model · Google Drive, in-memory vectors](https://millionrounds.com/workflow/optimize-unstructured-data-for-rag-with-blockify-ideablocks)
- [**Send AI-curated weekly news digests with RSS and Vector DB** 17 steps · calls a model · Gmail, RSS](https://millionrounds.com/workflow/send-ai-curated-weekly-news-digests-with-rss-and-vector-db)
- [**README generator with GitHub** 14 steps · calls a model · GitHub](https://millionrounds.com/workflow/readme-generator-with-github)
- [**Automate GitHub README & LICENSE generation with Gemini** 13 steps · calls a model · GitHub](https://millionrounds.com/workflow/automate-github-readme-and-license-generation-with-gemini)
- [**Fetch dynamic prompts from GitHub** 13 steps · calls a model · GitHub](https://millionrounds.com/workflow/fetch-dynamic-prompts-from-github)