{
 "week": "2026-w42",
 "fetched": "2026-10-18T06:50+00:00",
 "github": true,
 "breaks": {
  "PyPI": 6,
  "npm": 0,
  "Wikipedia": 0
 },
 "tracked": {
  "AI assistants and model makers": [
   {
    "name": "ChatGPT",
    "wiki": "ChatGPT",
    "weeks": [
     710738,
     442144,
     347228,
     374516,
     400624,
     270535,
     339108,
     520565,
     500258,
     356397,
     319112,
     310798
    ],
    "version": null,
    "released": null,
    "article": "ChatGPT",
    "url": "https://en.wikipedia.org/wiki/ChatGPT",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 310798,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": -9,
    "spikes": []
   },
   {
    "name": "Claude",
    "wiki": "Claude (AI)",
    "weeks": [
     32301,
     30298,
     29720,
     31189,
     30080,
     29829,
     35766,
     45693,
     34349,
     37200,
     35113,
     36640
    ],
    "version": null,
    "released": null,
    "article": "Claude (AI)",
    "url": "https://en.wikipedia.org/wiki/Claude_%28AI%29",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 36640,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 9,
    "spikes": []
   },
   {
    "name": "Gemini",
    "wiki": "Google Gemini",
    "weeks": [
     17788,
     20912,
     17039,
     13471,
     12331,
     12831,
     20167,
     25467,
     22327,
     17543,
     16539,
     14274
    ],
    "version": null,
    "released": null,
    "article": "Google Gemini",
    "url": "https://en.wikipedia.org/wiki/Google_Gemini",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 14274,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 3,
    "spikes": []
   },
   {
    "name": "Microsoft Copilot",
    "wiki": "Microsoft Copilot",
    "weeks": [
     11419,
     9301,
     5891,
     6811,
     8207,
     7099,
     8857,
     10848,
     8273,
     8261,
     8289,
     9398
    ],
    "version": null,
    "released": null,
    "article": "Microsoft Copilot",
    "url": "https://en.wikipedia.org/wiki/Microsoft_Copilot",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 9398,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": -3,
    "spikes": []
   },
   {
    "name": "Grok",
    "wiki": "Grok (chatbot)",
    "weeks": [
     11343,
     10633,
     11369,
     11295,
     10992,
     12014,
     14195,
     15907,
     12946,
     11593,
     11950,
     12115
    ],
    "version": null,
    "released": null,
    "article": "Grok (chatbot)",
    "url": "https://en.wikipedia.org/wiki/Grok_%28chatbot%29",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 12115,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": -8,
    "spikes": []
   },
   {
    "name": "Meta AI",
    "wiki": "Meta AI",
    "weeks": [
     2893,
     3245,
     3447,
     3697,
     3204,
     2963,
     3462,
     4069,
     4189,
     3878,
     3684,
     3860
    ],
    "version": null,
    "released": null,
    "article": "Meta AI",
    "url": "https://en.wikipedia.org/wiki/Meta_AI",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 3860,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 16,
    "spikes": []
   },
   {
    "name": "DeepSeek",
    "wiki": "DeepSeek",
    "weeks": [
     13391,
     13684,
     12297,
     13236,
     15817,
     13724,
     16534,
     23710,
     22192,
     19749,
     17142,
     21655
    ],
    "version": null,
    "released": null,
    "article": "DeepSeek",
    "url": "https://en.wikipedia.org/wiki/DeepSeek",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 21655,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 28,
    "spikes": []
   },
   {
    "name": "Qwen",
    "wiki": "Qwen",
    "weeks": [
     7078,
     8276,
     7024,
     10289,
     9269,
     8718,
     8534,
     10078,
     10733,
     10283,
     9218,
     9825
    ],
    "version": null,
    "released": null,
    "article": "Qwen",
    "url": "https://en.wikipedia.org/wiki/Qwen",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 9825,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 12,
    "spikes": []
   },
   {
    "name": "Mistral AI",
    "wiki": "Mistral AI",
    "weeks": [
     6925,
     6739,
     5691,
     6169,
     5865,
     6300,
     9621,
     9124,
     8923,
     7899,
     12362,
     9235
    ],
    "version": null,
    "released": null,
    "article": "Mistral AI",
    "url": "https://en.wikipedia.org/wiki/Mistral_AI",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 9235,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 18,
    "spikes": []
   },
   {
    "name": "Perplexity",
    "wiki": "Perplexity AI",
    "weeks": [
     14876,
     15021,
     14785,
     13450,
     17062,
     15896,
     16698,
     17292,
     17039,
     16047,
     15203,
     14675
    ],
    "version": null,
    "released": null,
    "article": "Perplexity AI",
    "url": "https://en.wikipedia.org/wiki/Perplexity_AI",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 14675,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": -7,
    "spikes": []
   },
   {
    "name": "Character.ai",
    "wiki": "Character.ai",
    "weeks": [
     4599,
     5107,
     4464,
     4964,
     4779,
     4263,
     4708,
     5172,
     6638,
     5246,
     4910,
     21302
    ],
    "version": null,
    "released": null,
    "article": "Character.ai",
    "url": "https://en.wikipedia.org/wiki/Character.ai",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 21302,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 25,
    "spikes": [
     11
    ]
   }
  ],
  "Image, video and audio": [
   {
    "name": "Midjourney",
    "wiki": "Midjourney",
    "weeks": [
     3721,
     3398,
     3123,
     3524,
     3488,
     3321,
     3737,
     3981,
     3748,
     4167,
     4164,
     3901
    ],
    "version": null,
    "released": null,
    "article": "Midjourney",
    "url": "https://en.wikipedia.org/wiki/Midjourney",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 3901,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 12,
    "spikes": []
   },
   {
    "name": "Sora",
    "wiki": "Sora (text-to-video model)",
    "weeks": [
     4672,
     4434,
     4293,
     3922,
     3982,
     3562,
     4358,
     4804,
     4748,
     4851,
     4098,
     3968
    ],
    "version": null,
    "released": null,
    "article": "Sora (text-to-video model)",
    "url": "https://en.wikipedia.org/wiki/Sora_%28text-to-video_model%29",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 3968,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 6,
    "spikes": []
   },
   {
    "name": "Veo",
    "wiki": "Veo (text-to-video model)",
    "weeks": [
     1417,
     1421,
     1333,
     1216,
     1132,
     1080,
     1245,
     1578,
     1597,
     1366,
     1233,
     1091
    ],
    "version": null,
    "released": null,
    "article": "Veo (text-to-video model)",
    "url": "https://en.wikipedia.org/wiki/Veo_%28text-to-video_model%29",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 1091,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 9,
    "spikes": []
   },
   {
    "name": "Stable Diffusion",
    "wiki": "Stable Diffusion",
    "weeks": [
     4734,
     4681,
     4356,
     3907,
     4586,
     4822,
     4627,
     4924,
     4733,
     4431,
     4633,
     4039
    ],
    "version": null,
    "released": null,
    "article": "Stable Diffusion",
    "url": "https://en.wikipedia.org/wiki/Stable_Diffusion",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 4039,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": -4,
    "spikes": []
   },
   {
    "name": "Runway",
    "wiki": "Runway (company)",
    "weeks": [
     1617,
     2052,
     1347,
     1161,
     1164,
     1414,
     1211,
     1324,
     1400,
     1346,
     1342,
     1378
    ],
    "version": null,
    "released": null,
    "article": "Runway (company)",
    "url": "https://en.wikipedia.org/wiki/Runway_%28company%29",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 1378,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 7,
    "spikes": []
   },
   {
    "name": "Suno",
    "wiki": "Suno",
    "weeks": [
     127,
     159,
     199,
     1317,
     1053,
     1428,
     3910,
     4497,
     4886,
     5703,
     8761,
     13880
    ],
    "version": null,
    "released": null,
    "article": "Suno",
    "url": "https://en.wikipedia.org/wiki/Suno",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 13880,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 171,
    "spikes": [
     11
    ]
   },
   {
    "name": "ElevenLabs",
    "wiki": "ElevenLabs",
    "weeks": [
     5093,
     5662,
     5709,
     5726,
     5193,
     5599,
     6171,
     6159,
     6710,
     8384,
     8564,
     8778
    ],
    "version": null,
    "released": null,
    "article": "ElevenLabs",
    "url": "https://en.wikipedia.org/wiki/ElevenLabs",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 8778,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 44,
    "spikes": []
   }
  ],
  "Ideas people look up": [
   {
    "name": "Large language model",
    "wiki": "Large language model",
    "weeks": [
     21748,
     22047,
     20371,
     20349,
     20289,
     21829,
     25285,
     31248,
     26926,
     25445,
     26109,
     26152
    ],
    "version": null,
    "released": null,
    "article": "Large language model",
    "url": "https://en.wikipedia.org/wiki/Large_language_model",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 26152,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 11,
    "spikes": []
   },
   {
    "name": "AI agent",
    "wiki": "AI agent",
    "weeks": [
     3666,
     3610,
     4521,
     3922,
     4036,
     5020,
     8490,
     12192,
     8682,
     7897,
     8820,
     7685
    ],
    "version": null,
    "released": null,
    "article": "AI agent",
    "url": "https://en.wikipedia.org/wiki/AI_agent",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 7685,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 23,
    "spikes": []
   },
   {
    "name": "Vibe coding",
    "wiki": "Vibe coding",
    "weeks": [
     9649,
     8961,
     8876,
     8444,
     8503,
     9054,
     9374,
     10812,
     11054,
     11331,
     12979,
     17407
    ],
    "version": null,
    "released": null,
    "article": "Vibe coding",
    "url": "https://en.wikipedia.org/wiki/Vibe_coding",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 17407,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 32,
    "spikes": []
   },
   {
    "name": "Model Context Protocol",
    "wiki": "Model Context Protocol",
    "weeks": [
     8101,
     8331,
     8218,
     7797,
     8525,
     8409,
     9257,
     9665,
     9907,
     12500,
     10873,
     11298
    ],
    "version": null,
    "released": null,
    "article": "Model Context Protocol",
    "url": "https://en.wikipedia.org/wiki/Model_Context_Protocol",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 11298,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": 25,
    "spikes": []
   },
   {
    "name": "Artificial general intelligence",
    "wiki": "Artificial general intelligence",
    "weeks": [
     10923,
     12106,
     10571,
     8968,
     11173,
     12488,
     59136,
     31062,
     17579,
     13239,
     11406,
     10487
    ],
    "version": null,
    "released": null,
    "article": "Artificial general intelligence",
    "url": "https://en.wikipedia.org/wiki/Artificial_general_intelligence",
    "repo": null,
    "registry": "Wikipedia",
    "last_week": 10487,
    "stars": null,
    "stars_7d": null,
    "start": 0,
    "change_4w": -43,
    "spikes": [
     6
    ]
   }
  ],
  "Model SDKs and gateways": [
   {
    "name": "OpenAI SDK",
    "pypi": "openai",
    "weeks": [
     102784530,
     113772448,
     106282628,
     107722249,
     71577597,
     62287668,
     66344790,
     67735054,
     69601420,
     72949998,
     75605389,
     81387465
    ],
    "version": "3.35.1",
    "released": "2026-10-18",
    "url": "https://pypi.org/project/openai/",
    "repo": "openai/openai-python",
    "registry": "PyPI",
    "last_week": 81387465,
    "stars": 31871,
    "stars_7d": null,
    "start": 6,
    "change_4w": 12,
    "spikes": []
   },
   {
    "name": "Anthropic SDK",
    "pypi": "anthropic",
    "weeks": [
     46109761,
     48790825,
     51125866,
     50081467,
     35021370,
     30543382,
     32235825,
     32925306,
     35137394,
     39905378,
     41365220,
     42719238
    ],
    "version": "1.15.0",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/anthropic/",
    "repo": "anthropics/anthropic-sdk-python",
    "registry": "PyPI",
    "last_week": 42719238,
    "stars": 3976,
    "stars_7d": null,
    "start": 6,
    "change_4w": 26,
    "spikes": []
   },
   {
    "name": "Google Gen AI SDK",
    "pypi": "google-genai",
    "weeks": [
     68016293,
     68684275,
     70176723,
     69144698,
     37882326,
     30306520,
     31564260,
     31879365,
     31596564,
     34122162,
     34253247,
     36147166
    ],
    "version": "2.31.0",
    "released": "2026-10-14",
    "url": "https://pypi.org/project/google-genai/",
    "repo": "googleapis/python-genai",
    "registry": "PyPI",
    "last_week": 36147166,
    "stars": 4028,
    "stars_7d": null,
    "start": 6,
    "change_4w": 8,
    "spikes": []
   },
   {
    "name": "Mistral SDK",
    "pypi": "mistralai",
    "weeks": [
     12499521,
     12827645,
     10783330,
     8089787,
     4284502,
     3959093,
     3797630,
     4403987,
     3839903,
     3373641,
     3154450,
     3206138
    ],
    "version": "3.2.0",
    "released": "2026-10-09",
    "url": "https://pypi.org/project/mistralai/",
    "repo": "mistralai/client-python",
    "registry": "PyPI",
    "last_week": 3206138,
    "stars": 774,
    "stars_7d": null,
    "start": 6,
    "change_4w": -17,
    "spikes": []
   },
   {
    "name": "LiteLLM",
    "pypi": "litellm",
    "weeks": [
     158475520,
     191453364,
     195707014,
     173588293,
     58385725,
     19321222,
     19476362,
     22205006,
     22561070,
     22366467,
     21460796,
     23257670
    ],
    "version": "1.106.0",
    "released": "2026-10-18",
    "url": "https://pypi.org/project/litellm/",
    "repo": "BerriAI/litellm",
    "registry": "PyPI",
    "last_week": 23257670,
    "stars": 61459,
    "stars_7d": null,
    "start": 6,
    "change_4w": 1,
    "spikes": []
   },
   {
    "name": "Ollama (Python)",
    "pypi": "ollama",
    "weeks": [
     4352537,
     5055715,
     5511821,
     5319926,
     3590714,
     2741645,
     2782100,
     2877689,
     2985876,
     3792881,
     2997781,
     3010073
    ],
    "version": "0.6.3",
    "released": "2026-09-29",
    "url": "https://pypi.org/project/ollama/",
    "repo": "ollama/ollama-python",
    "registry": "PyPI",
    "last_week": 3010073,
    "stars": 10605,
    "stars_7d": null,
    "start": 6,
    "change_4w": 5,
    "spikes": []
   }
  ],
  "Coding agents": [
   {
    "name": "Claude Code",
    "npm": "@anthropic-ai/claude-code",
    "repo": "anthropics/claude-code",
    "weeks": [
     11174965,
     12775960,
     24082653,
     21714222,
     22252564,
     16570507,
     15392532,
     14198273,
     13560171,
     14438525,
     14827847,
     10645364
    ],
    "version": "2.1.302",
    "released": "2026-10-16",
    "url": "https://www.npmjs.com/package/@anthropic-ai/claude-code",
    "registry": "npm",
    "last_week": 10645364,
    "stars": 152037,
    "stars_7d": null,
    "start": 0,
    "change_4w": -12,
    "spikes": []
   },
   {
    "name": "Codex CLI",
    "npm": "@openai/codex",
    "repo": "openai/codex",
    "weeks": [
     16096488,
     16035560,
     16199042,
     16334410,
     19431895,
     24005956,
     24008925,
     22710086,
     23405202,
     25811284,
     25696321,
     26318017
    ],
    "version": "0.163.0",
    "released": "2026-10-15",
    "url": "https://www.npmjs.com/package/@openai/codex",
    "registry": "npm",
    "last_week": 26318017,
    "stars": 129679,
    "stars_7d": null,
    "start": 0,
    "change_4w": 10,
    "spikes": []
   },
   {
    "name": "Gemini CLI",
    "npm": "@google/gemini-cli",
    "repo": "google-gemini/gemini-cli",
    "weeks": [
     385645,
     400854,
     388309,
     378797,
     396499,
     408306,
     431228,
     412865,
     426923,
     456058,
     459559,
     413807
    ],
    "version": "0.64.0",
    "released": "2026-10-13",
    "url": "https://www.npmjs.com/package/@google/gemini-cli",
    "registry": "npm",
    "last_week": 413807,
    "stars": 107433,
    "stars_7d": null,
    "start": 0,
    "change_4w": 8,
    "spikes": []
   },
   {
    "name": "GitHub Copilot CLI",
    "npm": "@github/copilot",
    "weeks": [
     1582738,
     1888648,
     1955446,
     1731934,
     3271517,
     4304435,
     3056850,
     1650229,
     1456196,
     1673009,
     1638259,
     1605312
    ],
    "version": "1.0.98",
    "released": "2026-10-14",
    "url": "https://www.npmjs.com/package/@github/copilot",
    "repo": "github/copilot-cli",
    "registry": "npm",
    "last_week": 1605312,
    "stars": 11271,
    "stars_7d": null,
    "start": 0,
    "change_4w": -49,
    "spikes": []
   },
   {
    "name": "opencode",
    "npm": "opencode-ai",
    "repo": "sst/opencode",
    "weeks": [
     2542714,
     2228936,
     2719011,
     2100360,
     3054608,
     2134375,
     2484101,
     2648418,
     2646166,
     3111031,
     3386910,
     3506452
    ],
    "version": "1.19.3",
    "released": "2026-10-16",
    "url": "https://www.npmjs.com/package/opencode-ai",
    "registry": "npm",
    "last_week": 3506452,
    "stars": 215675,
    "stars_7d": null,
    "start": 0,
    "change_4w": 27,
    "spikes": []
   },
   {
    "name": "Qwen Code",
    "npm": "@qwen-code/qwen-code",
    "weeks": [
     55057,
     68187,
     74126,
     76030,
     86555,
     60738,
     69495,
     72442,
     82359,
     96017,
     86191,
     77836
    ],
    "version": "0.25.2",
    "released": "2026-10-15",
    "url": "https://www.npmjs.com/package/@qwen-code/qwen-code",
    "repo": "QwenLM/qwen-code",
    "registry": "npm",
    "last_week": 77836,
    "stars": 28554,
    "stars_7d": null,
    "start": 0,
    "change_4w": 19,
    "spikes": []
   },
   {
    "name": "Cline CLI",
    "npm": "cline",
    "weeks": [
     103313,
     127728,
     166744,
     98144,
     167075,
     70175,
     62296,
     94781,
     73669,
     93346,
     84666,
     77455
    ],
    "version": "3.0.73",
    "released": "2026-10-17",
    "url": "https://www.npmjs.com/package/cline",
    "repo": "cline/cline",
    "registry": "npm",
    "last_week": 77455,
    "stars": 70489,
    "stars_7d": null,
    "start": 0,
    "change_4w": -2,
    "spikes": []
   }
  ],
  "Agent frameworks": [
   {
    "name": "LangGraph",
    "pypi": "langgraph",
    "repo": "langchain-ai/langgraph",
    "weeks": [
     16436110,
     16751325,
     17211373,
     16687781,
     11259434,
     10043570,
     10139150,
     9937578,
     10415908,
     11403762,
     12186538,
     12212527
    ],
    "version": "1.2.16",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/langgraph/",
    "registry": "PyPI",
    "last_week": 12212527,
    "stars": 43428,
    "stars_7d": null,
    "start": 6,
    "change_4w": 20,
    "spikes": []
   },
   {
    "name": "OpenAI Agents SDK",
    "pypi": "openai-agents",
    "repo": "openai/openai-agents-python",
    "weeks": [
     8634177,
     9114732,
     10239766,
     10532469,
     4424947,
     2558286,
     2792488,
     2927632,
     3026781,
     3020685,
     3039647,
     3220873
    ],
    "version": "0.24.0",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/openai-agents/",
    "registry": "PyPI",
    "last_week": 3220873,
    "stars": 30108,
    "stars_7d": null,
    "start": 6,
    "change_4w": 4,
    "spikes": []
   },
   {
    "name": "Claude Agent SDK",
    "pypi": "claude-agent-sdk",
    "repo": "anthropics/claude-agent-sdk-python",
    "weeks": [
     7757247,
     7330545,
     7943211,
     7847808,
     6494385,
     6389455,
     7162884,
     7379733,
     6116849,
     7357887,
     7639787,
     7668716
    ],
    "version": "0.2.168",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/claude-agent-sdk/",
    "registry": "PyPI",
    "last_week": 7668716,
    "stars": 8292,
    "stars_7d": null,
    "start": 6,
    "change_4w": 7,
    "spikes": []
   },
   {
    "name": "Pydantic AI",
    "pypi": "pydantic-ai",
    "repo": "pydantic/pydantic-ai",
    "weeks": [
     3269583,
     3073423,
     3479410,
     2999230,
     1609008,
     1222492,
     1228297,
     1197397,
     1281786,
     1355350,
     1391873,
     1465853
    ],
    "version": "2.57.0",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/pydantic-ai/",
    "registry": "PyPI",
    "last_week": 1465853,
    "stars": 20697,
    "stars_7d": null,
    "start": 6,
    "change_4w": 13,
    "spikes": []
   },
   {
    "name": "CrewAI",
    "pypi": "crewai",
    "repo": "crewAIInc/crewAI",
    "weeks": [
     4195964,
     5395821,
     7694612,
     11422171,
     3057913,
     570067,
     581354,
     556695,
     554853,
     585987,
     631855,
     663904
    ],
    "version": "1.15.28",
    "released": "2026-10-14",
    "url": "https://pypi.org/project/crewai/",
    "registry": "PyPI",
    "last_week": 663904,
    "stars": 59815,
    "stars_7d": null,
    "start": 6,
    "change_4w": 14,
    "spikes": []
   },
   {
    "name": "Google ADK",
    "pypi": "google-adk",
    "repo": "google/adk-python",
    "weeks": [
     4128233,
     4921116,
     5941343,
     5738764,
     2773237,
     2073833,
     2239696,
     2410710,
     2631666,
     2291342,
     2210551,
     2278001
    ],
    "version": "2.12.0",
    "released": "2026-10-13",
    "url": "https://pypi.org/project/google-adk/",
    "registry": "PyPI",
    "last_week": 2278001,
    "stars": 21897,
    "stars_7d": null,
    "start": 6,
    "change_4w": -6,
    "spikes": []
   },
   {
    "name": "smolagents",
    "pypi": "smolagents",
    "repo": "huggingface/smolagents",
    "weeks": [
     145063,
     140313,
     172392,
     133559,
     104507,
     103547,
     95343,
     98347,
     98955,
     105593,
     123283,
     104633
    ],
    "version": "1.26.0",
    "released": "2026-05-29",
    "url": "https://pypi.org/project/smolagents/",
    "registry": "PyPI",
    "last_week": 104633,
    "stars": 29905,
    "stars_7d": null,
    "start": 6,
    "change_4w": 7,
    "spikes": []
   },
   {
    "name": "Strands Agents",
    "pypi": "strands-agents",
    "repo": "strands-agents/sdk-python",
    "weeks": [
     8191926,
     8736553,
     8726343,
     8751262,
     8101634,
     8007679,
     8020569,
     9557671,
     8634060,
     8668367,
     8768691,
     8846436
    ],
    "version": "1.61.1",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/strands-agents/",
    "registry": "PyPI",
    "last_week": 8846436,
    "stars": 8854,
    "stars_7d": null,
    "start": 6,
    "change_4w": 2,
    "spikes": []
   },
   {
    "name": "Microsoft Agent Framework",
    "pypi": "agent-framework",
    "repo": "microsoft/agent-framework",
    "weeks": [
     357793,
     365685,
     397364,
     409950,
     126068,
     33709,
     36933,
     37964,
     49373,
     53836,
     46702,
     46751
    ],
    "version": "1.22.0",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/agent-framework/",
    "registry": "PyPI",
    "last_week": 46751,
    "stars": 14187,
    "stars_7d": null,
    "start": 6,
    "change_4w": 23,
    "spikes": []
   },
   {
    "name": "Mastra",
    "npm": "@mastra/core",
    "repo": "mastra-ai/mastra",
    "weeks": [
     1360247,
     1315863,
     1427004,
     1466965,
     1565012,
     1655093,
     1736183,
     1768928,
     1933442,
     2196240,
     2419117,
     2437208
    ],
    "version": "1.78.0",
    "released": "2026-10-15",
    "url": "https://www.npmjs.com/package/@mastra/core",
    "registry": "npm",
    "last_week": 2437208,
    "stars": 28875,
    "stars_7d": null,
    "start": 0,
    "change_4w": 36,
    "spikes": []
   },
   {
    "name": "Vercel AI SDK",
    "npm": "ai",
    "repo": "vercel/ai",
    "weeks": [
     19538120,
     20391016,
     21358050,
     22103955,
     23598333,
     24383354,
     25676300,
     26547571,
     29381141,
     33874081,
     35474227,
     32327169
    ],
    "version": "7.0.143",
    "released": "2026-10-16",
    "url": "https://www.npmjs.com/package/ai",
    "registry": "npm",
    "last_week": 32327169,
    "stars": 27371,
    "stars_7d": null,
    "start": 0,
    "change_4w": 32,
    "spikes": []
   }
  ],
  "LLM app frameworks": [
   {
    "name": "LangChain",
    "pypi": "langchain",
    "weeks": [
     64842072,
     62004668,
     59696565,
     57161410,
     46795375,
     38185770,
     39673953,
     39338197,
     39888829,
     40556182,
     36765410,
     36931779
    ],
    "version": "1.4.6",
    "released": "2026-10-14",
    "url": "https://pypi.org/project/langchain/",
    "repo": "langchain-ai/langchain",
    "registry": "PyPI",
    "last_week": 36931779,
    "stars": 148007,
    "stars_7d": null,
    "start": 6,
    "change_4w": -7,
    "spikes": []
   },
   {
    "name": "LlamaIndex",
    "pypi": "llama-index-core",
    "weeks": [
     3707737,
     3657882,
     3496209,
     3460708,
     1942455,
     1535980,
     1536613,
     1503353,
     1573717,
     1583812,
     1523237,
     1463958
    ],
    "version": "0.14.25",
    "released": "2026-09-21",
    "url": "https://pypi.org/project/llama-index-core/",
    "repo": "run-llama/llama_index",
    "registry": "PyPI",
    "last_week": 1463958,
    "stars": 52546,
    "stars_7d": null,
    "start": 6,
    "change_4w": -1,
    "spikes": []
   },
   {
    "name": "Haystack",
    "pypi": "haystack-ai",
    "weeks": [
     196795,
     188112,
     206066,
     197401,
     148185,
     125157,
     128283,
     114236,
     133089,
     152029,
     138742,
     108060
    ],
    "version": "3.4.0",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/haystack-ai/",
    "repo": "deepset-ai/haystack",
    "registry": "PyPI",
    "last_week": 108060,
    "stars": 26762,
    "stars_7d": null,
    "start": 6,
    "change_4w": 8,
    "spikes": []
   },
   {
    "name": "DSPy",
    "pypi": "dspy",
    "weeks": [
     1424177,
     1519699,
     1758568,
     1492701,
     1146821,
     1201282,
     1036410,
     1235219,
     1382645,
     1409597,
     1191397,
     1281921
    ],
    "version": "3.4.1",
    "released": "2026-10-12",
    "url": "https://pypi.org/project/dspy/",
    "repo": "stanfordnlp/dspy",
    "registry": "PyPI",
    "last_week": 1281921,
    "stars": 38676,
    "stars_7d": null,
    "start": 6,
    "change_4w": 4,
    "spikes": []
   },
   {
    "name": "Instructor",
    "pypi": "instructor",
    "weeks": [
     4836346,
     4267095,
     4334641,
     11379089,
     5823193,
     1925751,
     1945256,
     1921223,
     2030537,
     2060230,
     2249474,
     2149511
    ],
    "version": "1.17.0",
    "released": "2026-09-09",
    "url": "https://pypi.org/project/instructor/",
    "repo": "567-labs/instructor",
    "registry": "PyPI",
    "last_week": 2149511,
    "stars": 14029,
    "stars_7d": null,
    "start": 6,
    "change_4w": 11,
    "spikes": []
   }
  ],
  "Browser and computer use": [
   {
    "name": "Browser Use",
    "pypi": "browser-use",
    "weeks": [
     13951220,
     13385504,
     15817077,
     16139551,
     4872713,
     1640891,
     1645197,
     1727402,
     1857421,
     2364834,
     1691498,
     1653211
    ],
    "version": "0.13.11",
    "released": "2026-10-07",
    "url": "https://pypi.org/project/browser-use/",
    "repo": "browser-use/browser-use",
    "registry": "PyPI",
    "last_week": 1653211,
    "stars": 118360,
    "stars_7d": null,
    "start": 6,
    "change_4w": -2,
    "spikes": []
   },
   {
    "name": "Playwright MCP",
    "npm": "@playwright/mcp",
    "weeks": [
     6111743,
     6824090,
     5648267,
     5611247,
     5875246,
     7196693,
     6486389,
     7122280,
     8045574,
     8843429,
     7709120,
     6005954
    ],
    "version": "0.0.83",
    "released": "2026-09-28",
    "url": "https://www.npmjs.com/package/@playwright/mcp",
    "repo": "microsoft/playwright-mcp",
    "registry": "npm",
    "last_week": 6005954,
    "stars": 38304,
    "stars_7d": null,
    "start": 0,
    "change_4w": 16,
    "spikes": []
   },
   {
    "name": "Crawl4AI",
    "pypi": "crawl4ai",
    "weeks": [
     375472,
     381217,
     390249,
     386573,
     264376,
     277423,
     298069,
     257627,
     286738,
     361803,
     285728,
     310558
    ],
    "version": "0.9.5",
    "released": "2026-10-14",
    "url": "https://pypi.org/project/crawl4ai/",
    "repo": "unclecode/crawl4ai",
    "registry": "PyPI",
    "last_week": 310558,
    "stars": 85738,
    "stars_7d": null,
    "start": 6,
    "change_4w": 8,
    "spikes": []
   }
  ],
  "Retrieval and vector databases": [
   {
    "name": "Chroma",
    "pypi": "chromadb",
    "weeks": [
     3022540,
     3006373,
     3263127,
     2948206,
     1854750,
     1641266,
     1550957,
     1436686,
     1496398,
     1637601,
     1790252,
     1973978
    ],
    "version": "1.5.9",
    "released": "2026-05-05",
    "url": "https://pypi.org/project/chromadb/",
    "repo": "chroma-core/chroma",
    "registry": "PyPI",
    "last_week": 1973978,
    "stars": 29521,
    "stars_7d": null,
    "start": 6,
    "change_4w": 20,
    "spikes": []
   },
   {
    "name": "Qdrant",
    "pypi": "qdrant-client",
    "weeks": [
     4423395,
     4417273,
     4374172,
     4411417,
     2864130,
     2588051,
     2608074,
     2714905,
     2825850,
     3101473,
     3137589,
     3217690
    ],
    "version": "1.19.1",
    "released": "2026-09-16",
    "url": "https://pypi.org/project/qdrant-client/",
    "repo": "qdrant/qdrant-client",
    "registry": "PyPI",
    "last_week": 3217690,
    "stars": 1374,
    "stars_7d": null,
    "start": 6,
    "change_4w": 16,
    "spikes": []
   },
   {
    "name": "Pinecone",
    "pypi": "pinecone",
    "weeks": [
     1822845,
     1686020,
     1691936,
     1625413,
     1020909,
     891171,
     885666,
     883053,
     898948,
     1005784,
     943912,
     888148
    ],
    "version": "10.0.0",
    "released": "2026-09-03",
    "url": "https://pypi.org/project/pinecone/",
    "repo": "pinecone-io/python-sdk",
    "registry": "PyPI",
    "last_week": 888148,
    "stars": 453,
    "stars_7d": null,
    "start": 6,
    "change_4w": 7,
    "spikes": []
   },
   {
    "name": "Weaviate",
    "pypi": "weaviate-client",
    "weeks": [
     39658089,
     31301205,
     25938743,
     21249361,
     6115212,
     1493375,
     2386111,
     3150239,
     2432203,
     1458935,
     1443321,
     1515122
    ],
    "version": "4.23.1",
    "released": "2026-09-07",
    "url": "https://pypi.org/project/weaviate-client/",
    "repo": "weaviate/weaviate-python-client",
    "registry": "PyPI",
    "last_week": 1515122,
    "stars": 228,
    "stars_7d": null,
    "start": 6,
    "change_4w": -40,
    "spikes": []
   },
   {
    "name": "LanceDB",
    "pypi": "lancedb",
    "weeks": [
     2104100,
     2252950,
     2728823,
     7140435,
     2011667,
     1944945,
     1806271,
     1731942,
     1852917,
     1843207,
     1806521,
     1691998
    ],
    "version": "0.40.0",
    "released": "2026-10-07",
    "url": "https://pypi.org/project/lancedb/",
    "repo": "lancedb/lancedb",
    "registry": "PyPI",
    "last_week": 1691998,
    "stars": 11695,
    "stars_7d": null,
    "start": 6,
    "change_4w": 0,
    "spikes": []
   },
   {
    "name": "Sentence Transformers",
    "pypi": "sentence-transformers",
    "weeks": [
     7098090,
     7527790,
     7643166,
     8665450,
     6135713,
     5337501,
     5198108,
     5244004,
     5328584,
     5313940,
     5020738,
     5072741
    ],
    "version": "6.1.0",
    "released": "2026-09-18",
    "url": "https://pypi.org/project/sentence-transformers/",
    "repo": "huggingface/sentence-transformers",
    "registry": "PyPI",
    "last_week": 5072741,
    "stars": 19189,
    "stars_7d": null,
    "start": 6,
    "change_4w": -3,
    "spikes": []
   },
   {
    "name": "Docling",
    "pypi": "docling",
    "weeks": [
     2177053,
     2122600,
     2056126,
     2661851,
     1040176,
     637709,
     686721,
     597691,
     648071,
     773193,
     820604,
     867177
    ],
    "version": "2.140.0",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/docling/",
    "repo": "docling-project/docling",
    "registry": "PyPI",
    "last_week": 867177,
    "stars": 69037,
    "stars_7d": null,
    "start": 6,
    "change_4w": 27,
    "spikes": []
   }
  ],
  "Evaluation and tracing": [
   {
    "name": "Langfuse",
    "pypi": "langfuse",
    "repo": "langfuse/langfuse",
    "weeks": [
     5957647,
     6482216,
     6618965,
     6447669,
     4998407,
     5009064,
     5113419,
     5272084,
     5497937,
     6242973,
     6463308,
     6803994
    ],
    "version": "5.0.2",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/langfuse/",
    "registry": "PyPI",
    "last_week": 6803994,
    "stars": 35983,
    "stars_7d": null,
    "start": 6,
    "change_4w": 23,
    "spikes": []
   },
   {
    "name": "LangSmith",
    "pypi": "langsmith",
    "repo": "langchain-ai/langsmith-sdk",
    "weeks": [
     28548618,
     28390305,
     29263128,
     29306032,
     20653785,
     18110539,
     18658055,
     18149531,
     17227433,
     18555370,
     19426565,
     20211581
    ],
    "version": "0.14.11",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/langsmith/",
    "registry": "PyPI",
    "last_week": 20211581,
    "stars": 1082,
    "stars_7d": null,
    "start": 6,
    "change_4w": 7,
    "spikes": []
   },
   {
    "name": "Inspect",
    "pypi": "inspect-ai",
    "repo": "UKGovernmentBEIS/inspect_ai",
    "weeks": [
     2313463,
     1681057,
     1733068,
     2685911,
     1404345,
     688994,
     553003,
     621671,
     681047,
     720018,
     974072,
     858432
    ],
    "version": "0.3.281",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/inspect-ai/",
    "registry": "PyPI",
    "last_week": 858432,
    "stars": 3030,
    "stars_7d": null,
    "start": 6,
    "change_4w": 38,
    "spikes": []
   },
   {
    "name": "DeepEval",
    "pypi": "deepeval",
    "repo": "confident-ai/deepeval",
    "weeks": [
     1381751,
     1174542,
     1248410,
     1374259,
     744767,
     540806,
     549190,
     581647,
     611834,
     662801,
     758358,
     790819
    ],
    "version": "4.3.1",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/deepeval/",
    "registry": "PyPI",
    "last_week": 790819,
    "stars": 18929,
    "stars_7d": null,
    "start": 6,
    "change_4w": 30,
    "spikes": []
   },
   {
    "name": "Ragas",
    "pypi": "ragas",
    "repo": "explodinggradients/ragas",
    "weeks": [
     362094,
     362262,
     355477,
     419938,
     280452,
     227224,
     214345,
     236368,
     250133,
     273433,
     320608,
     345451
    ],
    "version": "0.4.3",
    "released": "2026-01-13",
    "url": "https://pypi.org/project/ragas/",
    "registry": "PyPI",
    "last_week": 345451,
    "stars": 16049,
    "stars_7d": null,
    "start": 6,
    "change_4w": 36,
    "spikes": []
   },
   {
    "name": "Phoenix",
    "pypi": "arize-phoenix",
    "repo": "Arize-ai/phoenix",
    "weeks": [
     448982,
     559645,
     513558,
     641106,
     253621,
     152971,
     154802,
     157044,
     138855,
     145091,
     151701,
     165610
    ],
    "version": "20.23.0",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/arize-phoenix/",
    "registry": "PyPI",
    "last_week": 165610,
    "stars": 11891,
    "stars_7d": null,
    "start": 6,
    "change_4w": -2,
    "spikes": []
   },
   {
    "name": "Opik",
    "pypi": "opik",
    "repo": "comet-ml/opik",
    "weeks": [
     831565,
     810614,
     774217,
     768248,
     450758,
     377794,
     389814,
     406670,
     420391,
     424803,
     444987,
     496631
    ],
    "version": "2.2.103",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/opik/",
    "registry": "PyPI",
    "last_week": 496631,
    "stars": 22699,
    "stars_7d": null,
    "start": 6,
    "change_4w": 9,
    "spikes": []
   }
  ],
  "Fine-tuning and RL": [
   {
    "name": "TRL",
    "pypi": "trl",
    "repo": "huggingface/trl",
    "weeks": [
     870348,
     932291,
     1079783,
     1030220,
     666079,
     556129,
     576349,
     637953,
     610703,
     575571,
     542893,
     550412
    ],
    "version": "1.16.0",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/trl/",
    "registry": "PyPI",
    "last_week": 550412,
    "stars": 19540,
    "stars_7d": null,
    "start": 6,
    "change_4w": -10,
    "spikes": []
   },
   {
    "name": "PEFT",
    "pypi": "peft",
    "repo": "huggingface/peft",
    "weeks": [
     2682518,
     2971723,
     2955084,
     2816728,
     2014402,
     1861609,
     1791411,
     1923120,
     2012914,
     2031843,
     1996711,
     2142033
    ],
    "version": "0.21.2",
    "released": "2026-10-01",
    "url": "https://pypi.org/project/peft/",
    "registry": "PyPI",
    "last_week": 2142033,
    "stars": 21797,
    "stars_7d": null,
    "start": 6,
    "change_4w": 6,
    "spikes": []
   },
   {
    "name": "Unsloth",
    "pypi": "unsloth",
    "repo": "unslothai/unsloth",
    "weeks": [
     477165,
     612306,
     654526,
     621684,
     317807,
     193097,
     208216,
     206018,
     227185,
     198310,
     181670,
     181894
    ],
    "version": "2026.10.6",
    "released": "2026-10-15",
    "url": "https://pypi.org/project/unsloth/",
    "registry": "PyPI",
    "last_week": 181894,
    "stars": 78206,
    "stars_7d": null,
    "start": 6,
    "change_4w": -13,
    "spikes": []
   },
   {
    "name": "verl",
    "pypi": "verl",
    "repo": "volcengine/verl",
    "weeks": [
     17547,
     20359,
     21528,
     19008,
     6389,
     5718,
     6605,
     8936,
     6328,
     3950,
     4082,
     4570
    ],
    "version": "0.9.1",
    "released": "2026-09-20",
    "url": "https://pypi.org/project/verl/",
    "registry": "PyPI",
    "last_week": 4570,
    "stars": 23913,
    "stars_7d": null,
    "start": 6,
    "change_4w": -38,
    "spikes": []
   },
   {
    "name": "Axolotl",
    "pypi": "axolotl",
    "repo": "axolotl-ai-cloud/axolotl",
    "weeks": [
     2331,
     4142,
     3024,
     3130,
     2678,
     2100,
     1821,
     2669,
     1678,
     1963,
     1973,
     1709
    ],
    "version": "0.21.0",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/axolotl/",
    "registry": "PyPI",
    "last_week": 1709,
    "stars": 12587,
    "stars_7d": null,
    "start": 6,
    "change_4w": 8,
    "spikes": []
   }
  ],
  "Inference and local models": [
   {
    "name": "Transformers",
    "pypi": "transformers",
    "weeks": [
     44514838,
     47242393,
     47001488,
     47754925,
     26938588,
     21664433,
     20520842,
     21283122,
     23136154,
     25027959,
     24613491,
     24823220
    ],
    "version": "5.20.1",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/transformers/",
    "repo": "huggingface/transformers",
    "registry": "PyPI",
    "last_week": 24823220,
    "stars": 167802,
    "stars_7d": null,
    "start": 6,
    "change_4w": 17,
    "spikes": []
   },
   {
    "name": "vLLM",
    "pypi": "vllm",
    "repo": "vllm-project/vllm",
    "weeks": [
     1159958,
     1101065,
     1176993,
     1178847,
     667124,
     546921,
     415159,
     384057,
     450829,
     493113,
     461211,
     442624
    ],
    "version": "0.31.0",
    "released": "2026-10-05",
    "url": "https://pypi.org/project/vllm/",
    "registry": "PyPI",
    "last_week": 442624,
    "stars": 94025,
    "stars_7d": null,
    "start": 6,
    "change_4w": 11,
    "spikes": []
   },
   {
    "name": "SGLang",
    "pypi": "sglang",
    "repo": "sgl-project/sglang",
    "weeks": [
     74846433,
     212250780,
     35234207,
     31955757,
     9730514,
     710030,
     1130929,
     564939,
     326485,
     732578,
     376988,
     189616
    ],
    "version": "0.5.22",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/sglang/",
    "registry": "PyPI",
    "last_week": 189616,
    "stars": 37261,
    "stars_7d": null,
    "start": 6,
    "change_4w": -33,
    "spikes": []
   },
   {
    "name": "llama.cpp (Python)",
    "pypi": "llama-cpp-python",
    "repo": "abetlen/llama-cpp-python",
    "weeks": [
     147137,
     138659,
     150044,
     165999,
     156553,
     141453,
     112991,
     112588,
     115317,
     141644,
     154555,
     144287
    ],
    "version": "0.3.36",
    "released": "2026-10-01",
    "url": "https://pypi.org/project/llama-cpp-python/",
    "registry": "PyPI",
    "last_week": 144287,
    "stars": 10648,
    "stars_7d": null,
    "start": 6,
    "change_4w": 28,
    "spikes": []
   },
   {
    "name": "MLX LM",
    "pypi": "mlx-lm",
    "repo": "ml-explore/mlx-lm",
    "weeks": [
     308000,
     304082,
     320545,
     309973,
     158728,
     123185,
     123548,
     122774,
     126760,
     134609,
     136127,
     139499
    ],
    "version": "0.32.2",
    "released": "2026-10-16",
    "url": "https://pypi.org/project/mlx-lm/",
    "registry": "PyPI",
    "last_week": 139499,
    "stars": 7388,
    "stars_7d": null,
    "start": 6,
    "change_4w": 10,
    "spikes": []
   }
  ],
  "Image, video and speech libraries": [
   {
    "name": "Diffusers",
    "pypi": "diffusers",
    "weeks": [
     1892730,
     2052423,
     1893198,
     1816456,
     1258085,
     1199819,
     1167390,
     1151705,
     1165072,
     1192397,
     1251806,
     1398887
    ],
    "version": "0.41.0",
    "released": "2026-10-06",
    "url": "https://pypi.org/project/diffusers/",
    "repo": "huggingface/diffusers",
    "registry": "PyPI",
    "last_week": 1398887,
    "stars": 34747,
    "stars_7d": null,
    "start": 6,
    "change_4w": 7,
    "spikes": []
   },
   {
    "name": "faster-whisper",
    "pypi": "faster-whisper",
    "weeks": [
     2451809,
     2707476,
     2584208,
     2706428,
     1825130,
     1829698,
     1837913,
     1935495,
     2322565,
     2760201,
     3157980,
     3614407
    ],
    "version": "1.2.1",
    "released": "2025-10-31",
    "url": "https://pypi.org/project/faster-whisper/",
    "repo": "SYSTRAN/faster-whisper",
    "registry": "PyPI",
    "last_week": 3614407,
    "stars": 25931,
    "stars_7d": null,
    "start": 6,
    "change_4w": 63,
    "spikes": []
   },
   {
    "name": "Whisper",
    "pypi": "openai-whisper",
    "weeks": [
     1109888,
     1087456,
     1171354,
     1110779,
     1073264,
     1315692,
     1246342,
     1195285,
     1092290,
     1104954,
     1375888,
     1692592
    ],
    "version": "20250625",
    "released": "2025-06-26",
    "url": "https://pypi.org/project/openai-whisper/",
    "repo": "openai/whisper",
    "registry": "PyPI",
    "last_week": 1692592,
    "stars": 110790,
    "stars_7d": null,
    "start": 6,
    "change_4w": 15,
    "spikes": []
   },
   {
    "name": "ElevenLabs SDK",
    "pypi": "elevenlabs",
    "weeks": [
     2450896,
     2640618,
     2521616,
     2545245,
     2116355,
     2088317,
     2267664,
     1987196,
     2096560,
     2247596,
     2277481,
     2255154
    ],
    "version": "2.73.1",
    "released": "2026-10-17",
    "url": "https://pypi.org/project/elevenlabs/",
    "repo": "elevenlabs/elevenlabs-python",
    "registry": "PyPI",
    "last_week": 2255154,
    "stars": 3146,
    "stars_7d": null,
    "start": 6,
    "change_4w": 8,
    "spikes": []
   }
  ],
  "MCP": [
   {
    "name": "MCP Python SDK",
    "pypi": "mcp",
    "repo": "modelcontextprotocol/python-sdk",
    "weeks": [
     85307191,
     83618186,
     87018096,
     84830760,
     53319102,
     46352699,
     52808451,
     54104948,
     53501947,
     58889773,
     60985138,
     64841642
    ],
    "version": "2.3.0",
    "released": "2026-10-02",
    "url": "https://pypi.org/project/mcp/",
    "registry": "PyPI",
    "last_week": 64841642,
    "stars": 24602,
    "stars_7d": null,
    "start": 6,
    "change_4w": 14,
    "spikes": []
   },
   {
    "name": "MCP TypeScript SDK",
    "npm": "@modelcontextprotocol/sdk",
    "repo": "modelcontextprotocol/typescript-sdk",
    "weeks": [
     50993825,
     53291684,
     50692957,
     51092136,
     51901393,
     54149516,
     57574524,
     57560021,
     63648696,
     73562986,
     77152556,
     68388269
    ],
    "version": "1.32.1",
    "released": "2026-10-05",
    "url": "https://www.npmjs.com/package/@modelcontextprotocol/sdk",
    "registry": "npm",
    "last_week": 68388269,
    "stars": 13602,
    "stars_7d": null,
    "start": 0,
    "change_4w": 27,
    "spikes": []
   },
   {
    "name": "FastMCP",
    "pypi": "fastmcp",
    "repo": "jlowin/fastmcp",
    "weeks": [
     24864835,
     24898280,
     24754755,
     21404901,
     11403337,
     11027807,
     12098145,
     12695328,
     11757691,
     13251845,
     14235101,
     13514138
    ],
    "version": "4.1.1",
    "released": "2026-10-18",
    "url": "https://pypi.org/project/fastmcp/",
    "registry": "PyPI",
    "last_week": 13514138,
    "stars": 28118,
    "stars_7d": null,
    "start": 6,
    "change_4w": 12,
    "spikes": []
   }
  ]
 },
 "new_repos": [
  {
   "repo": "wheresryan22/anatomy",
   "desc": "An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.",
   "stars": 15370,
   "created": "2026-10-08",
   "age_days": 9,
   "per_day": 1708,
   "lang": "JavaScript",
   "url": "https://github.com/wheresryan22/anatomy"
  },
  {
   "repo": "ARahim3/DigUp",
   "desc": "Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.",
   "stars": 4634,
   "created": "2026-10-08",
   "age_days": 9,
   "per_day": 515,
   "lang": "Swift",
   "url": "https://github.com/ARahim3/DigUp"
  },
  {
   "repo": "storytold/cadcraft",
   "desc": "CADCraft: computer-aided design and drafting — an open-source, clean-room AutoCAD-style app in pure Rust",
   "stars": 5642,
   "created": "2026-10-07",
   "age_days": 11,
   "per_day": 513,
   "lang": "Rust",
   "url": "https://github.com/storytold/cadcraft"
  },
  {
   "repo": "rehan-remade/universal-modder",
   "desc": "Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.",
   "stars": 8267,
   "created": "2026-09-30",
   "age_days": 18,
   "per_day": 459,
   "lang": "Python",
   "url": "https://github.com/rehan-remade/universal-modder"
  },
  {
   "repo": "tangency-labs/solidcraft",
   "desc": "SolidCraft: an open-source parametric 3D CAD application built in pure Rust. Desktop, web, and automation through MCP.",
   "stars": 4489,
   "created": "2026-10-07",
   "age_days": 10,
   "per_day": 449,
   "lang": "Rust",
   "url": "https://github.com/tangency-labs/solidcraft"
  },
  {
   "repo": "KKKKhazix/AIHOT",
   "desc": "一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的，它就是你的行业热点站。",
   "stars": 7970,
   "created": "2026-09-28",
   "age_days": 19,
   "per_day": 419,
   "lang": "TypeScript",
   "url": "https://github.com/KKKKhazix/AIHOT"
  },
  {
   "repo": "deeplethe/solid-glass",
   "desc": "A design system for AI applications. Material, physical, tactile, technical.",
   "stars": 1866,
   "created": "2026-10-12",
   "age_days": 5,
   "per_day": 373,
   "lang": "TypeScript",
   "url": "https://github.com/deeplethe/solid-glass"
  },
  {
   "repo": "LosaLosSantos/aurelio-finance",
   "desc": "Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.",
   "stars": 3951,
   "created": "2026-10-06",
   "age_days": 11,
   "per_day": 359,
   "lang": "Python",
   "url": "https://github.com/LosaLosSantos/aurelio-finance"
  },
  {
   "repo": "CopilotKit/OpenDots",
   "desc": "Your always-on AI coworkers that move between text, calls, and Slack.",
   "stars": 5536,
   "created": "2026-09-29",
   "age_days": 18,
   "per_day": 308,
   "lang": "TypeScript",
   "url": "https://github.com/CopilotKit/OpenDots"
  },
  {
   "repo": "shader-effects-inc/shaders",
   "desc": "WebGPU components for React, Vue, Svelte, Solid, JS & Framer",
   "stars": 5009,
   "created": "2026-09-29",
   "age_days": 18,
   "per_day": 278,
   "lang": "TypeScript",
   "url": "https://github.com/shader-effects-inc/shaders"
  },
  {
   "repo": "QingYunA/answer-me-with-html",
   "desc": "Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。",
   "stars": 3638,
   "created": "2026-10-02",
   "age_days": 15,
   "per_day": 243,
   "lang": "JavaScript",
   "url": "https://github.com/QingYunA/answer-me-with-html"
  },
  {
   "repo": "Fei2411/DeepSeek-Bot",
   "desc": "A team of long-lived bots for DeepSeek Harness, with main bots, bot-to-bot messages and group chats.",
   "stars": 2408,
   "created": "2026-10-07",
   "age_days": 10,
   "per_day": 241,
   "lang": "JavaScript",
   "url": "https://github.com/Fei2411/DeepSeek-Bot"
  },
  {
   "repo": "Jakeschincariol/replica-skill",
   "desc": "Eleven free Claude skills that clone any app: reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate. Free, MIT.",
   "stars": 3213,
   "created": "2026-10-03",
   "age_days": 14,
   "per_day": 230,
   "lang": "Python",
   "url": "https://github.com/Jakeschincariol/replica-skill"
  },
  {
   "repo": "nykooi1/vibe-wise",
   "desc": "A Claude Code / Codex plugin that helps you learn how to build while AI writes the code.",
   "stars": 3738,
   "created": "2026-09-29",
   "age_days": 19,
   "per_day": 197,
   "lang": "Python",
   "url": "https://github.com/nykooi1/vibe-wise"
  },
  {
   "repo": "edenfunf/reelmimic",
   "desc": "Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.",
   "stars": 3582,
   "created": "2026-09-28",
   "age_days": 19,
   "per_day": 189,
   "lang": "JavaScript",
   "url": "https://github.com/edenfunf/reelmimic"
  }
 ],
 "hn": [
  {
   "title": "Gemini 4 Argon",
   "points": 1465,
   "comments": 1044,
   "url": "https://deepmind.google/models/gemini/",
   "hn": "https://news.ycombinator.com/item?id=50073879"
  },
  {
   "title": "Claude reveals ECDSA curve origins",
   "points": 1034,
   "comments": 380,
   "url": "https://www.anthropic.com/research/ecdsa-curve-origins",
   "hn": "https://news.ycombinator.com/item?id=50122800"
  },
  {
   "title": "Containment and monitoring failures are to blame for AI hacking reports: experts",
   "points": 948,
   "comments": 620,
   "url": "https://www.csoonline.com/article/4234854/ai-agents-arent-going-rogue-frontier-labs-are-skipping-security-basics.html",
   "hn": "https://news.ycombinator.com/item?id=50091788"
  },
  {
   "title": "Redesigning source control at Anthropic",
   "points": 892,
   "comments": 1010,
   "url": "https://www.anthropic.com/engineering/redesigning-source-control",
   "hn": "https://news.ycombinator.com/item?id=50073633"
  },
  {
   "title": "DeepSeek-v4.1-Flash-1017",
   "points": 805,
   "comments": 631,
   "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017",
   "hn": "https://news.ycombinator.com/item?id=50129045"
  },
  {
   "title": "AI is a tool and using it well takes skill",
   "points": 803,
   "comments": 607,
   "url": "https://yyhh.org/blog/2026/10/ai-is-a-tool/",
   "hn": "https://news.ycombinator.com/item?id=50063427"
  },
  {
   "title": "The gap in shared understanding of LLM capability is widening",
   "points": 727,
   "comments": 1072,
   "url": "https://twitter.com/karpathy/status/2109361546505966046",
   "hn": "https://news.ycombinator.com/item?id=50047422"
  },
  {
   "title": "OpenAI engineer arrested in bugging of executive conference room",
   "points": 655,
   "comments": 543,
   "url": "https://sfstandard.com/2026/10/13/openai-engineer-arrested-alleged-bugging-executive-conference-room/",
   "hn": "https://news.ycombinator.com/item?id=50078141"
  },
  {
   "title": "90% of US working hours are spent on tasks not covered well by AI benchmarks",
   "points": 603,
   "comments": 551,
   "url": "https://www.mercor.com/research/labor-index/benchmark-map/",
   "hn": "https://news.ycombinator.com/item?id=50121179"
  },
  {
   "title": "You could have invented transformers from memory",
   "points": 540,
   "comments": 126,
   "url": "https://alexwang.ai/posts/associative-memory/",
   "hn": "https://news.ycombinator.com/item?id=50122878"
  },
  {
   "title": "DeepSeek: DeepSeek v4.1 Flash 1017",
   "points": 513,
   "comments": 5,
   "url": "https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017",
   "hn": "https://news.ycombinator.com/item?id=50129121"
  },
  {
   "title": "How the Claude Code team does code review",
   "points": 457,
   "comments": 463,
   "url": "https://claude.dev/blog/solving-code-review-at-anthropic/",
   "hn": "https://news.ycombinator.com/item?id=50122951"
  },
  {
   "title": "We turned EmbeddingGemma 2 into a speech-to-text model",
   "points": 433,
   "comments": 99,
   "url": "https://eg2.haku.sh/",
   "hn": "https://news.ycombinator.com/item?id=50069971"
  },
  {
   "title": "Anthropic's Scion is heavily inspired by Mononoke",
   "points": 426,
   "comments": 162,
   "url": "https://sunshowers.io/posts/anthropic-mononoke/",
   "hn": "https://news.ycombinator.com/item?id=50094694"
  },
  {
   "title": "QGIS enacts moratorium on AI contributions",
   "points": 392,
   "comments": 412,
   "url": "https://github.com/qgis/QGIS-Enhancement-Proposals/pull/387",
   "hn": "https://news.ycombinator.com/item?id=50054751"
  }
 ],
 "hf": {
  "models": [
   {
    "id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "likes": 1099,
    "task": "image-text-to-text",
    "tags": [
     "transformers",
     "safetensors",
     "deepseek_v41",
     "text-generation",
     "image-text-to-text",
     "license:mit",
     "endpoints_compatible",
     "8-bit",
     "fp8",
     "region:us"
    ],
    "created": "2026-10-17"
   },
   {
    "id": "google/embeddinggemma-2",
    "likes": 2613,
    "task": "feature-extraction",
    "tags": [
     "transformers",
     "safetensors",
     "embedding_gemma2",
     "feature-extraction",
     "embedding",
     "sentence-transformers",
     "multimodal-embedding",
     "multimodal",
     "vision",
     "audio",
     "video",
     "image-feature-extraction",
     "audio-feature-extraction",
     "video-feature-extraction",
     "sentence-similarity",
     "multilingual",
     "license:apache-2.0",
     "endpoints_compatible",
     "region:us"
    ],
    "created": "2026-09-14"
   },
   {
    "id": "jialinyyzz/humanizer",
    "likes": 1910,
    "task": "text-generation",
    "tags": [
     "gguf",
     "safetensors",
     "gemma4_unified",
     "image-text-to-text",
     "humanizer",
     "transformers",
     "text-rewriting",
     "rewriting",
     "paraphrase",
     "style-transfer",
     "llama.cpp",
     "gemma4",
     "text-generation",
     "en",
     "zh",
     "base_model:google/gemma-4-12B",
     "base_model:finetune:google/gemma-4-12B",
     "license:apache-2.0",
     "endpoints_compatible",
     "region:us",
     "conversational"
    ],
    "created": "2026-09-11"
   },
   {
    "id": "openbmb/MiniCPM-V-4.7-35B-A3B",
    "likes": 908,
    "task": "image-text-to-text",
    "tags": [
     "transformers",
     "safetensors",
     "minicpmv4_7",
     "image-text-to-text",
     "minicpm-v",
     "multimodal",
     "On-Device Model",
     "lightweight",
     "moe",
     "conversational",
     "license:apache-2.0",
     "endpoints_compatible",
     "region:us"
    ],
    "created": "2026-10-07"
   },
   {
    "id": "fishaudio/drama-3",
    "likes": 634,
    "task": "text-to-speech",
    "tags": [
     "safetensors",
     "fish_omni",
     "fish-audio",
     "text-to-speech",
     "multi-speaker",
     "audio-editing",
     "emotional-speech-generation",
     "zh",
     "en",
     "ja",
     "ko",
     "es",
     "pt",
     "ar",
     "ru",
     "fr",
     "de",
     "sv",
     "it",
     "tr",
     "no",
     "nl",
     "cy",
     "eu",
     "ca",
     "da",
     "gl",
     "ta",
     "hu",
     "fi",
     "pl",
     "et",
     "hi",
     "la",
     "ur",
     "th",
     "vi",
     "jw",
     "bn",
     "yo",
     "sl",
     "cs",
     "sw",
     "nn",
     "he",
     "ms",
     "uk",
     "id",
     "kk",
     "bg",
     "lv",
     "my",
     "tl",
     "sk",
     "ne",
     "fa",
     "af",
     "el",
     "bo",
     "hr",
     "ro",
     "sn",
     "mi",
     "yi",
     "am",
     "be",
     "km",
     "is",
     "az",
     "sd",
     "br",
     "sq",
     "ps",
     "mn",
     "ht",
     "ml",
     "sr",
     "sa",
     "te",
     "ka",
     "bs",
     "pa",
     "lt",
     "kn",
     "si",
     "hy",
     "mr",
     "as",
     "gu",
     "fo",
     "arxiv:2610.18010",
     "license:other",
     "bsgemm-moe",
     "region:us"
    ],
    "created": "2026-10-01"
   },
   {
    "id": "black-forest-labs/flux-3-image-klein-comfy",
    "likes": 696,
    "task": "image-to-image",
    "tags": [
     "diffusion-single-file",
     "comfyui",
     "image-generation",
     "image-editing",
     "flux",
     "flux-3",
     "black-forest-labs",
     "image-to-image",
     "en",
     "base_model:black-forest-labs/flux-3-image-klein",
     "base_model:finetune:black-forest-labs/flux-3-image-klein",
     "license:other",
     "region:us"
    ],
    "created": "2026-10-14"
   },
   {
    "id": "meta-models/Muse-Spark-Open-816B-A42B",
    "likes": 517,
    "task": "image-text-to-text",
    "tags": [
     "transformers",
     "safetensors",
     "muse_spark",
     "image-text-to-text",
     "facebook",
     "meta",
     "pytorch",
     "muse",
     "muse-spark",
     "conversational",
     "en",
     "license:other",
     "eval-results",
     "endpoints_compatible",
     "deploy:sagemaker",
     "region:us"
    ],
    "created": "2026-09-15"
   },
   {
    "id": "Lightricks/LTX-2.5",
    "likes": 8258,
    "task": "image-to-video",
    "tags": [
     "diffusion-single-file",
     "image-to-video",
     "text-to-video",
     "video-to-video",
     "image-text-to-video",
     "audio-to-video",
     "text-to-audio",
     "video-to-audio",
     "audio-to-audio",
     "text-to-audio-video",
     "image-to-audio-video",
     "image-text-to-audio-video",
     "ltx-video",
     "lightricks",
     "comfyui",
     "ltx-2.5",
     "ltx",
     "en",
     "de",
     "es",
     "fr",
     "ja",
     "ko",
     "zh",
     "it",
     "pt",
     "arxiv:2601.03233",
     "license:other",
     "region:us"
    ],
    "created": "2026-07-23"
   },
   {
    "id": "LiquidAI/LFM2.5-24B-A2B",
    "likes": 450,
    "task": "text-generation",
    "tags": [
     "transformers",
     "safetensors",
     "lfm2_moe",
     "text-generation",
     "liquid",
     "lfm2.5",
     "edge",
     "moe",
     "conversational",
     "en",
     "ar",
     "zh",
     "fr",
     "de",
     "ja",
     "ko",
     "es",
     "pt",
     "it",
     "vi",
     "th",
     "id",
     "hi",
     "ru",
     "pl",
     "arxiv:2511.23404",
     "base_model:LiquidAI/LFM2.5-24B-A2B-Base",
     "base_model:finetune:LiquidAI/LFM2.5-24B-A2B-Base",
     "license:other",
     "endpoints_compatible",
     "region:us"
    ],
    "created": "2026-10-12"
   },
   {
    "id": "black-forest-labs/flux-3-image-klein",
    "likes": 459,
    "task": "image-to-image",
    "tags": [
     "diffusers",
     "safetensors",
     "image-generation",
     "image-editing",
     "flux",
     "flux-3",
     "black-forest-labs",
     "image-to-image",
     "en",
     "license:other",
     "region:us"
    ],
    "created": "2026-10-13"
   }
  ],
  "papers": [
   {
    "title": "Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation",
    "upvotes": 666,
    "summary": "Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories. However, this endpoint policy shift cannot reveal whether local action preferences evolved consistently during teacher training. The same endpoint shift can result from early and late shifts that reinforce or partially cancel each other. We investigate whether agreement between early and late teacher policy shifts can guide selective transfer. We introduce Waypoint-guided On-Policy Distillation (Waypoint-OPD), which",
    "url": "https://huggingface.co/papers/2610.21601"
   },
   {
    "title": "OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding",
    "upvotes": 577,
    "summary": "With the rapid development of multimodal large language models (MLLMs), evaluating their video understanding capabilities has become increasingly important. Existing video understanding benchmarks cover only part of the evaluation dimensions, limiting systematic diagnosis of omni-modal video understanding. We introduce OmniCompass, a holistic benchmark for omni-modal video grounding and understanding. OmniCompass defines two evaluation tracks: OmniCompass-VL assesses vision-language models on tasks requiring visual evidence, while OmniCompass-AV assesses omni-modal models on tasks requiring jo",
    "url": "https://huggingface.co/papers/2610.18829"
   },
   {
    "title": "MJev-Spatial: System One Spatial Intelligence via Native Attention Matching",
    "upvotes": 352,
    "summary": "Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation holds, how far an object is, or where to place it. Vision-language models (VLMs) produce these answers by free-form text generation, paying for autoregressive decoding and answer parsing even though the output space is compact: one of a few options, a scalar, or a 2D point. In light of this, we introduce MJev-Spatial, a System 1 multimodal decision model that tackles all three types of spatial understanding tasks within a unified classif",
    "url": "https://huggingface.co/papers/2610.22276"
   },
   {
    "title": "OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use",
    "upvotes": 315,
    "summary": "Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete tasks on users' computers through visual and programmatic interfaces. We define a generalist computer-use agent (GCUA) as a system in which the model chooses how to observe, act, and organize its work across visual and programmatic interfaces. Yet frontier implementations, such as GPT-6 Astra's computer-use system, remain largely closed, limiting systematic study of their design. We introduce Open Generalist CUA (OpenGCUA), an ongoing project to develop and open the full stack fo",
    "url": "https://huggingface.co/papers/2610.22200"
   },
   {
    "title": "FDE-Gym: The Last Mile of AI Delivery",
    "upvotes": 285,
    "summary": "Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: forward-deployed engineers (FDEs) must clarify ambiguous requirements, work in live systems, and uncover unstated constraints. We introduce FDE-Gym, a benchmark of 95 end-to-end delivery tasks from 20 customer scenarios across 18 sectors, each adapted by industry experts from real-world delivery projects. In simulated customer environments with scripted stakeholders and modifiable customer systems, agents interact with",
    "url": "https://huggingface.co/papers/2610.22350"
   },
   {
    "title": "RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment",
    "upvotes": 201,
    "summary": "Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, and refining actions through visual feedback. We introduce RoTA-Bench to evaluate these abilities through interactive 3D-to-2D projection alignment. Given a target silhouette, a model observes a rotated object and chooses successive rotations to recover the target projection within a limited action budget. Our automated pipeline constructs silhouette-preserving 3D objects from 2D icons and uses reversible initializati",
    "url": "https://huggingface.co/papers/2610.17665"
   },
   {
    "title": "Self-Evolving Agent Harness",
    "upvotes": 199,
    "summary": "Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model weights fixed. We formalize a feedback-driven process in which accepted revisions persist across runs. The framework separates update targets from proposal and admission mechanisms. It distinguishes changes to interpreted state from revisions to tools and code, repository-level control logic, and plugin composition. We characterize search through evolutionary optimization and examine its reliability through continual PAC-learning. Under explicit a",
    "url": "https://huggingface.co/papers/2610.18813"
   },
   {
    "title": "MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments",
    "upvotes": 153,
    "summary": "Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive environments and the scarcity of realistic training tasks. We introduce MAI-Gym, an open all-in-one platform that unifies GUI agent evaluation, data collection, and online RL training across mobile, computer, and web environments. Through a shared rollout pipeline, MAI-Gym ensures consistent agent behavior across evaluation and training, supports ten established benchmarks, and s",
    "url": "https://huggingface.co/papers/2610.20939"
   }
  ]
 }
}