AutomationFlowsAI & RAG › Create a Code Assistant That Learns From Your Github Repository Using Openai

Create a Code Assistant That Learns From Your Github Repository Using Openai

ByNghia Nguyen @nghiaaidev on n8n.io

AI Agent to learn directly from your GitHub repository. It automatically syncs source files, converts them into vectorized knowledge

Chat trigger trigger★★★★☆ complexityAI-powered19 nodesDocument Default Data LoaderText Splitter Recursive Character Text SplitterAgentTool Vector StoreMemory Buffer WindowChat TriggerGitHubHTTP Request
AI & RAG Trigger: Chat trigger Nodes: 19 Complexity: ★★★★☆ AI nodes: yes Added:

This workflow corresponds to n8n.io template #9993 — we link there as the canonical source.

This workflow follows the Agent → Chat Trigger recipe pattern — see all workflows that pair these two integrations.

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "id": "HJdHRULAa3bhcCMR",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "AI Agent For Github",
  "tags": [],
  "nodes": [
    {
      "id": "21ce2f08-255b-49e7-8a28-c7755593e574",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        1152,
        208
      ],
      "parameters": {
        "options": {},
        "dataType": "binary"
      },
      "typeVersion": 1
    },
    {
      "id": "af656ce7-169b-4c91-a770-8c488f68911a",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        1232,
        416
      ],
      "parameters": {
        "options": {},
        "chunkOverlap": 100
      },
      "typeVersion": 1
    },
    {
      "id": "6493e13d-3e1e-42c0-abef-290a2a236868",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        400,
        736
      ],
      "parameters": {
        "options": {
          "systemMessage": "You are a helpful technical assistant designed to answer developer questions based on the project\u2019s source code and technical documentation. \n\nWhen a developer asks a question, use the tool `project_source_tool` to retrieve relevant information from the available codebase and documentation."
        }
      },
      "typeVersion": 1.7
    },
    {
      "id": "2f05cc89-7dcf-40bc-a5c2-fd2c5c7cc57c",
      "name": "Vector Store Tool",
      "type": "@n8n/n8n-nodes-langchain.toolVectorStore",
      "position": [
        608,
        960
      ],
      "parameters": {
        "name": "project_source_tool",
        "topK": "=5",
        "description": "Retrieve information from any source code"
      },
      "typeVersion": 1
    },
    {
      "id": "0edbd03e-e2fa-41b2-9fdb-c935dd44148d",
      "name": "Window Buffer Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        480,
        960
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "38b9511b-c5bf-47be-abe1-3d6b156e2b50",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        128,
        736
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "eda1081e-97b8-441e-b726-ea6a0dec9141",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -528,
        112
      ],
      "parameters": {
        "width": 340,
        "height": 560,
        "content": "## Setup Guilde\n\n### 1. Update the `Config` Node\nAdd or edit the following parameters:\n- `repo_owner`\n- `repo_name`\n- `repo_path`\n- `sub_path`\n\n### 2. Add GitHub Account\nConnect your GitHub account to enable repository access.\n\n### 3. Trigger \u201cSync Data\u201d\nRun the workflow or trigger the node to start syncing data from GitHub to your vectorstore.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "073d715d-1432-40b8-ba62-63b586ff3900",
      "name": "Config",
      "type": "n8n-nodes-base.set",
      "position": [
        352,
        -16
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "03f51f9c-4681-4423-91d2-d32f4c18d6bc",
              "name": "repo_owner",
              "type": "string",
              "value": "cphuong20202009"
            },
            {
              "id": "0c9b521a-b698-4b43-9eb0-bbf744760158",
              "name": "repo_name",
              "type": "string",
              "value": "share-n8n-workflow"
            },
            {
              "id": "91627e70-a71a-4be0-a6f6-b04d5c8469d8",
              "name": "repo_path",
              "type": "string",
              "value": "share-n8n-workflow"
            },
            {
              "id": "983a2c87-9d69-4d64-ab88-ec1b1117c6e6",
              "name": "sub_path",
              "type": "string",
              "value": "workflows"
            }
          ]
        },
        "includeOtherFields": true
      },
      "typeVersion": 3.4
    },
    {
      "id": "24767c37-190a-4039-84c3-23207299eecc",
      "name": "List files",
      "type": "n8n-nodes-base.github",
      "position": [
        576,
        -16
      ],
      "parameters": {
        "owner": {
          "__rl": true,
          "mode": "name",
          "value": "={{ $json.repo_owner }}"
        },
        "filePath": "={{ $json.sub_path }}",
        "resource": "file",
        "operation": "list",
        "repository": {
          "__rl": true,
          "mode": "name",
          "value": "={{ $json.repo_name }}"
        }
      },
      "credentials": {
        "githubApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "97c7184a-685b-4940-b3af-6de8bbf9c7dd",
      "name": "Get File",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        800,
        -16
      ],
      "parameters": {
        "url": "={{ $json.download_url }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "c98cb6aa-e460-4c97-ba1d-d9fd9da561d3",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        1024,
        208
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "e6eba4d9-4770-46e7-af58-233763b12bcc",
      "name": "Embeddings OpenAI1",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        576,
        1376
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "06cc6964-01bc-496f-895f-c3277c3cb10e",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        784,
        1168
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "e4d2d5e8-318d-4a63-9777-76225842fd88",
      "name": "OpenAI Chat Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        352,
        960
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "b5c0e689-aaa1-4d69-993e-7bb6b04937db",
      "name": "Simple Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory",
      "position": [
        496,
        1168
      ],
      "parameters": {
        "memoryKey": {
          "__rl": true,
          "mode": "list",
          "value": "source-code",
          "cachedResultName": "source-code"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "a41eac9f-9556-48dd-abf3-511a2b430c67",
      "name": "Simple Vector Store1",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory",
      "position": [
        1056,
        -16
      ],
      "parameters": {
        "mode": "insert",
        "memoryKey": {
          "__rl": true,
          "mode": "list",
          "value": "source-code"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "fb9ecc78-60b5-4eb0-912b-654bf3dbc5ca",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        128,
        -128
      ],
      "parameters": {
        "width": 384,
        "height": 80,
        "content": "Pull your source files and update the knowledge base (vectorstore) for the AI Agent"
      },
      "typeVersion": 1
    },
    {
      "id": "ccea3fc1-94e3-4582-bfb5-ef4cc2546a61",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        128,
        640
      ],
      "parameters": {
        "width": 560,
        "height": 80,
        "content": "Ask questions to the AI Agent \u2014 it will respond using your repository knowledge."
      },
      "typeVersion": 1
    },
    {
      "id": "c14b04e5-7f2c-42c3-ac89-f5a256ee2ead",
      "name": "Sync Data",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        128,
        -16
      ],
      "parameters": {},
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "6a88fedb-ad7d-4258-ac59-afb17408e6c4",
  "connections": {
    "Config": {
      "main": [
        [
          {
            "node": "List files",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get File": {
      "main": [
        [
          {
            "node": "Simple Vector Store1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Sync Data": {
      "main": [
        [
          {
            "node": "Config",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "List files": {
      "main": [
        [
          {
            "node": "Get File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Simple Vector Store1",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Vector Store Tool",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Vector Store Tool": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI1": {
      "ai_embedding": [
        [
          {
            "node": "Simple Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Simple Vector Store1",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Simple Vector Store": {
      "ai_vectorStore": [
        [
          {
            "node": "Vector Store Tool",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "Window Buffer Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Recursive Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

AI Agent to learn directly from your GitHub repository. It automatically syncs source files, converts them into vectorized knowledge

Source: https://n8n.io/workflows/9993/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

AI & RAG

This workflow acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions using a knowle

Chat Trigger, Memory Postgres Chat, Tool Workflow +20
AI & RAG

• Create a Google Drive folder to watch. • Connect your Google Drive account in n8n and authorize access. • Point the Google Drive Trigger node to this folder (new/modified files trigger the flow).

Agent, Chat Trigger, Memory Buffer Window +14
AI & RAG

⚡AI-Powered YouTube Playlist & Video Summarization and Analysis v2. Uses lmChatGoogleGemini, agent, splitOut, chainLlm. Chat trigger; 72 nodes.

Google Gemini Chat, Agent, Chain Llm +11
AI & RAG

This n8n workflow transforms entire YouTube playlists or single videos into interactive knowledge bases you can chat with. Ask questions and get summaries without needing to watch hours of content. 🔗

Google Gemini Chat, Agent, Chain Llm +11
AI & RAG

Advanced Ai Demo Presented At Ai Developers 14 Meetup. Uses slack, stickyNote, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Chat trigger; 39 nodes.

Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14