🐦 Twitter Post Details

Viewing enriched Twitter post

@kevinnguyendn

Open-source Memory for Agents - OpenClaw, Hermes, Claude Code and more @karpathy just validated the exact memory architecture we open-sourced today. Detailed in our new arXiv paper. The idea here is that structured Markdown vaults are the gold standard for agent memory. However, the "compilation" of these vaults is usually too tedious for manual maintenance. It turns out you can just automate the whole curation layer. ByteRover solves this by automating the curation layer: Connecting nodes, links and context graphs while maintaining a human-readable Obsidian format. Token Efficiency: Save you tons of tokens (50-70% on average) because the tiered retrieval only pulls exactly the context the agent needs, instead of dumping massive files into the prompt. Proven Scalability: Benchmarked on Locomo & LongMemEval for production-grade latency and accuracy. Collaboration: Native support to sync and manage knowledge with your teammates and other agents. No vector DBs, zero infra. Just a native "second brain" for your agents that actually works out of the box.

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2040090413865026043/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2040090413865026043/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-04-04T04:47:10.054520",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2040090413865026043",
  "url": "https://x.com/kevinnguyendn/status/2040090413865026043",
  "twitterUrl": "https://twitter.com/kevinnguyendn/status/2040090413865026043",
  "text": "Open-source Memory for Agents - OpenClaw, Hermes, Claude Code and more\n\n@karpathy just validated the exact memory architecture we open-sourced today. Detailed in our new arXiv paper.\n\nThe idea here is that structured Markdown vaults are the gold standard for agent memory. However, the \"compilation\" of these vaults is usually too tedious for manual maintenance.\n\nIt turns out you can just automate the whole curation layer. ByteRover solves this by automating the curation layer: Connecting nodes, links and context graphs while maintaining a human-readable Obsidian format.\n\nToken Efficiency: Save you tons of tokens (50-70% on average) because the tiered retrieval only pulls exactly the context the agent needs, instead of dumping massive files into the prompt.\n\nProven Scalability: Benchmarked on Locomo & LongMemEval for production-grade latency and accuracy.\n\nCollaboration: Native support to sync and manage knowledge with your teammates and other agents.\n\nNo vector DBs, zero infra. Just a native \"second brain\" for your agents that actually works out of the box.",
  "source": "Twitter for iPhone",
  "retweetCount": 54,
  "replyCount": 26,
  "likeCount": 558,
  "quoteCount": 1,
  "viewCount": 29241,
  "createdAt": "Fri Apr 03 15:33:52 +0000 2026",
  "lang": "en",
  "bookmarkCount": 1008,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2040090413865026043",
  "displayTextRange": [
    0,
    272
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "kevinnguyendn",
    "url": "https://x.com/kevinnguyendn",
    "twitterUrl": "https://twitter.com/kevinnguyendn",
    "id": "3725210712",
    "name": "andy nguyen",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1911971622375874560/wToJWcGC_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3725210712/1772632420",
    "description": "Creator of https://t.co/EMx6p0sbuD | Building an agentic memory layer for coding agents to help millions of devs vibe code better! 🚀 #VibeCoding",
    "location": "",
    "followers": 2846,
    "following": 547,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Tue Sep 29 11:34:53 +0000 2015",
    "entities": {
      "description": {
        "urls": [
          {
            "display_url": "byterover.dev",
            "expanded_url": "https://www.byterover.dev",
            "indices": [
              11,
              34
            ],
            "url": "https://t.co/EMx6p0sbuD"
          }
        ]
      },
      "url": {
        "urls": [
          {
            "display_url": "byterover.dev",
            "expanded_url": "https://byterover.dev/",
            "indices": [
              0,
              23
            ],
            "url": "https://t.co/KaE9A86CqL"
          }
        ]
      }
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1268,
    "hasCustomTimelines": false,
    "isTranslator": false,
    "mediaCount": 146,
    "statusesCount": 1220,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2031339287472423167"
    ],
    "profile_bio": {},
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.x.com/P0cxcaSwTk",
        "expanded_url": "https://x.com/kevinnguyendn/status/2040090413865026043/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "medium": {
            "faces": []
          },
          "orig": {
            "faces": []
          },
          "small": {
            "faces": []
          }
        },
        "id_str": "2040089833658560512",
        "indices": [
          273,
          296
        ],
        "media_key": "3_2040089833658560512",
        "media_results": {
          "result": {
            "media_key": "3_2040089833658560512"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HE_a5RUasAA77NB.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 557,
              "w": 994,
              "x": 0,
              "y": 317
            },
            {
              "h": 994,
              "w": 994,
              "x": 0,
              "y": 98
            },
            {
              "h": 1133,
              "w": 994,
              "x": 0,
              "y": 2
            },
            {
              "h": 1135,
              "w": 568,
              "x": 0,
              "y": 0
            },
            {
              "h": 1135,
              "w": 994,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1135,
          "width": 994
        },
        "sizes": {
          "large": {
            "h": 1135,
            "resize": "fit",
            "w": 994
          },
          "medium": {
            "h": 1135,
            "resize": "fit",
            "w": 994
          },
          "small": {
            "h": 680,
            "resize": "fit",
            "w": 596
          },
          "thumb": {
            "h": 150,
            "resize": "crop",
            "w": 150
          }
        },
        "type": "photo",
        "url": "https://t.co/P0cxcaSwTk"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": [
      {
        "id_str": "33836629",
        "indices": [
          72,
          81
        ],
        "name": "Andrej Karpathy",
        "screen_name": "karpathy"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "article": null
}