🐦 Twitter Post Details

Viewing enriched Twitter post

@llama_index

Files are becoming the primary interface for AI agents to manage context, store conversations, and access skills 📁 @jerryjliu0 breaks down how coding agents like Claude Code and @cursor_ai are centralizing around filesystems as core abstractions, moving away from complex tool ecosystems: 📝 Agents store long conversation histories in searchable files to overcome context window limitations 🔍 File-based retrieval with semantic search outperforms traditional RAG patterns for dynamic context traversal ⚡ Skills defined as simple files are replacing complex MCP tools - just copy API specs into markdown files 🛠️ Agents need only ~5-10 core tools (CLI, code interpreter, web fetch) plus filesystem access to be highly capable The challenges ahead include parsing non-plaintext documents (PDFs, Word, Excel) and scaling file search to massive collections. That's exactly why we built LlamaCloud's Parse, Extract, and Sheets capabilities - to convert any document format into agent-ready context. Read the full analysis: https://t.co/Dy5cWYzUc6

Media 2
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "type": "video",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2011846444156645438/media_0.mp4?",
      "filename": "media_0.mp4"
    },
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2011846444156645438/media_1.png?",
      "filename": "media_1.png"
    }
  ],
  "processed_at": "2026-01-18T17:29:41.241104",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2011846444156645438",
  "url": "https://x.com/llama_index/status/2011846444156645438",
  "twitterUrl": "https://twitter.com/llama_index/status/2011846444156645438",
  "text": "Files are becoming the primary interface for AI agents to manage context, store conversations, and access skills 📁\n\n@jerryjliu0 breaks down how coding agents like Claude Code and @cursor_ai are centralizing around filesystems as core abstractions, moving away from complex tool ecosystems:\n\n📝 Agents store long conversation histories in searchable files to overcome context window limitations\n🔍 File-based retrieval with semantic search outperforms traditional RAG patterns for dynamic context traversal\n⚡ Skills defined as simple files are replacing complex MCP tools - just copy API specs into markdown files\n🛠️ Agents need only ~5-10 core tools (CLI, code interpreter, web fetch) plus filesystem access to be highly capable\n\nThe challenges ahead include parsing non-plaintext documents (PDFs, Word, Excel) and scaling file search to massive collections. That's exactly why we built LlamaCloud's Parse, Extract, and Sheets capabilities - to convert any document format into agent-ready context.\n\nRead the full analysis: https://t.co/Dy5cWYzUc6",
  "source": "Twitter for iPhone",
  "retweetCount": 12,
  "replyCount": 8,
  "likeCount": 129,
  "quoteCount": 4,
  "viewCount": 43769,
  "createdAt": "Thu Jan 15 17:02:25 +0000 2026",
  "lang": "en",
  "bookmarkCount": 143,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2011846444156645438",
  "displayTextRange": [
    0,
    302
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "llama_index",
    "url": "https://x.com/llama_index",
    "twitterUrl": "https://twitter.com/llama_index",
    "id": "1604278358296055808",
    "name": "LlamaIndex 🦙",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": "Business",
    "profilePicture": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_normal.png",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1604278358296055808/1758023766",
    "description": "",
    "location": "",
    "followers": 106126,
    "following": 29,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Sun Dec 18 00:52:44 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1467,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1801,
    "statusesCount": 3684,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2008587677680234659"
    ],
    "profile_bio": {
      "description": "AI Agents for document OCR + workflows\n\nGithub: https://t.co/HC19j7veGE\nDocs: https://t.co/QInqg2yMCJ\nLlamaCloud: https://t.co/yQGTiRSfFL",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "github.com/run-llama/llam…",
              "expanded_url": "http://github.com/run-llama/llama_index",
              "indices": [
                48,
                71
              ],
              "url": "https://t.co/HC19j7veGE"
            },
            {
              "display_url": "docs.llamaindex.ai",
              "expanded_url": "http://docs.llamaindex.ai",
              "indices": [
                78,
                101
              ],
              "url": "https://t.co/QInqg2yMCJ"
            },
            {
              "display_url": "cloud.llamaindex.ai",
              "expanded_url": "https://cloud.llamaindex.ai/",
              "indices": [
                114,
                137
              ],
              "url": "https://t.co/yQGTiRSfFL"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/epzefqPT9Z"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "additional_media_info": {
          "monetizable": false
        },
        "display_url": "pic.twitter.com/BO8DQktNzO",
        "expanded_url": "https://twitter.com/llama_index/status/2011846444156645438/video/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "id_str": "2011846382466760704",
        "indices": [
          303,
          326
        ],
        "media_key": "13_2011846382466760704",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARvrg6AplgAAAAA=",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAAECgABG+uDoCmWAAAAAA==",
            "media_key": "13_2011846382466760704"
          }
        },
        "media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2011846382466760704/img/yOirwY6sIn2lY2kk.jpg",
        "original_info": {
          "focus_rects": [],
          "height": 1080,
          "width": 1592
        },
        "sizes": {
          "large": {
            "h": 1080,
            "w": 1592
          }
        },
        "type": "video",
        "url": "https://t.co/BO8DQktNzO",
        "video_info": {
          "aspect_ratio": [
            199,
            135
          ],
          "duration_millis": 38250,
          "variants": [
            {
              "content_type": "application/x-mpegURL",
              "url": "https://video.twimg.com/amplify_video/2011846382466760704/pl/jkLn77s3WGGjC7pX.m3u8?tag=14"
            },
            {
              "bitrate": 288000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2011846382466760704/vid/avc1/398x270/Que6Q4WstQ4rrKKO.mp4?tag=14"
            },
            {
              "bitrate": 832000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2011846382466760704/vid/avc1/530x360/ty_1fNkAeBMX51vo.mp4?tag=14"
            },
            {
              "bitrate": 2176000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2011846382466760704/vid/avc1/1060x720/-4SSTxGNCc6EPK23.mp4?tag=14"
            }
          ]
        }
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "urls": [
      {
        "display_url": "llamaindex.ai/blog/files-are…",
        "expanded_url": "https://www.llamaindex.ai/blog/files-are-all-you-need?utm_source=socials&utm_medium=li_social",
        "indices": [
          1022,
          1045
        ],
        "url": "https://t.co/Dy5cWYzUc6"
      }
    ],
    "user_mentions": [
      {
        "id_str": "369777416",
        "indices": [
          116,
          127
        ],
        "name": "Jerry Liu",
        "screen_name": "jerryjliu0"
      },
      {
        "id_str": "1695890961094909952",
        "indices": [
          179,
          189
        ],
        "name": "Cursor",
        "screen_name": "cursor_ai"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}