🐦 Twitter Post Details

Viewing enriched Twitter post

@socialwithaayan

🚨 BREAKING: Someone just built the exact tool Andrej Karpathy said someone should build. 48 hours after Karpathy posted his LLM Knowledge Bases workflow, this showed up on GitHub. It's called Graphify. One command. Any folder. Full knowledge graph. Point it at any folder. Run /graphify inside Claude Code. Walk away. Here is what comes out the other side: -> A navigable knowledge graph of everything in that folder -> An Obsidian vault with backlinked articles -> A wiki that starts at index. md and maps every concept cluster -> Plain English Q&A over your entire codebase or research folder You can ask it things like: "What calls this function?" "What connects these two concepts?" "What are the most important nodes in this project?" No vector database. No setup. No config files. The token efficiency number is what got me: 71.5x fewer tokens per query compared to reading raw files. That is not a small improvement. That is a completely different paradigm for how AI agents reason over large codebases. What it supports: -> Code in 13 programming languages -> PDFs -> Images via Claude Vision -> Markdown files Install in one line: pip install graphify && graphify install Then type /graphify in Claude Code and point it at anything. Karpathy asked. Someone delivered in 48 hours. That is the pace of 2026. Open Source. Free.

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041192946369007924/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041192946369007924/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-04-06T23:32:05.199577",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2041192946369007924",
  "url": "https://x.com/socialwithaayan/status/2041192946369007924",
  "twitterUrl": "https://twitter.com/socialwithaayan/status/2041192946369007924",
  "text": "🚨 BREAKING: Someone just built the exact tool Andrej Karpathy said someone should build.\n\n48 hours after Karpathy posted his LLM Knowledge Bases workflow, this showed up on GitHub.\n\nIt's called Graphify. One command. Any folder. Full knowledge graph.\n\nPoint it at any folder. Run /graphify inside Claude Code. Walk away.\n\nHere is what comes out the other side:\n\n-> A navigable knowledge graph of everything in that folder\n-> An Obsidian vault with backlinked articles\n-> A wiki that starts at index. md and maps every concept cluster\n-> Plain English Q&A over your entire codebase or research folder\n\nYou can ask it things like:\n\n\"What calls this function?\"\n\"What connects these two concepts?\"\n\"What are the most important nodes in this project?\"\n\nNo vector database. No setup. No config files.\n\nThe token efficiency number is what got me:\n\n71.5x fewer tokens per query compared to reading raw files.\n\nThat is not a small improvement. That is a completely different paradigm for how AI agents reason over large codebases.\n\nWhat it supports:\n\n-> Code in 13 programming languages\n-> PDFs\n-> Images via Claude Vision\n-> Markdown files\n\nInstall in one line:\n\npip install graphify && graphify install\n\nThen type /graphify in Claude Code and point it at anything.\n\nKarpathy asked. Someone delivered in 48 hours.\n\nThat is the pace of 2026.\n\nOpen Source. Free.",
  "source": "Twitter for iPhone",
  "retweetCount": 524,
  "replyCount": 107,
  "likeCount": 5002,
  "quoteCount": 37,
  "viewCount": 276343,
  "createdAt": "Mon Apr 06 16:34:56 +0000 2026",
  "lang": "en",
  "bookmarkCount": 10864,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2041192946369007924",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "socialwithaayan",
    "url": "https://x.com/socialwithaayan",
    "twitterUrl": "https://twitter.com/socialwithaayan",
    "id": "1575650469787369473",
    "name": "Muhammad Ayan",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/2020385471701086209/wK66uFBP_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1575650469787369473/1773128138",
    "description": "",
    "location": "X",
    "followers": 65074,
    "following": 689,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 30 00:55:58 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 45364,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 7861,
    "statusesCount": 44014,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2041192946369007924"
    ],
    "profile_bio": {
      "description": "Breaking down AI media tools & no-code workflows | ✉️ socialwithayan@gmail.com",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "linktr.ee/socialwithayan",
              "expanded_url": "https://linktr.ee/socialwithayan",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/ZqKup9cisi"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/ouxGwMmHoN",
        "expanded_url": "https://twitter.com/socialwithaayan/status/2041192946369007924/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": [
              {
                "h": 73,
                "w": 73,
                "x": 1459,
                "y": 1121
              },
              {
                "h": 169,
                "w": 169,
                "x": 1224,
                "y": 805
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 73,
                "w": 73,
                "x": 1459,
                "y": 1121
              },
              {
                "h": 169,
                "w": 169,
                "x": 1224,
                "y": 805
              }
            ]
          }
        },
        "id_str": "2041192943118422019",
        "indices": [
          280,
          303
        ],
        "media_key": "3_2041192943118422019",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxTxirEm5ADCgACHFPGK4ZbkTQAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHFPGKsSbkAMKAAIcU8YrhluRNAAA",
            "media_key": "3_2041192943118422019"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HFPGKsSbkAMwa8y.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 983,
              "w": 1756,
              "x": 0,
              "y": 0
            },
            {
              "h": 1710,
              "w": 1710,
              "x": 0,
              "y": 0
            },
            {
              "h": 1710,
              "w": 1500,
              "x": 0,
              "y": 0
            },
            {
              "h": 1710,
              "w": 855,
              "x": 0,
              "y": 0
            },
            {
              "h": 1710,
              "w": 1756,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1710,
          "width": 1756
        },
        "sizes": {
          "large": {
            "h": 1710,
            "w": 1756
          }
        },
        "type": "photo",
        "url": "https://t.co/ouxGwMmHoN"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}