{"slug": "i-tracked-every-trending-ai-repo-s-stars-daily-for-3-weeks-the-growth-is-not-i", "title": "I tracked every trending AI repo's stars daily for 3 weeks. The growth is not where I expected", "summary": "A developer tracked star counts of 611 trending AI repos daily for three weeks, finding that growth is concentrated in agent skill packs and job-specific tools rather than new frameworks. Top gainers include OpenMontage (agentic video production) and ai-job-search, while old tools like Spiderfoot are experiencing second lives as agent-compatible utilities.", "body_md": "I run a small AI trends site, and three weeks ago I started doing something simple: every day, snapshot the star count of every repo that crosses my GitHub trending scan for AI. No judgment, no curation, just append-only rows in a database.\n\n611 repos and 2,671 data points later (June 19 to July 10), the picture of what's actually growing looks pretty different from what my feeds told me was hot. Here's what the data says.\n\nBefore publishing this I re-checked every number below against GitHub's live API. Star counts drift by the hour, so treat them as of July 10.\n\n| Repo | Gained | Window | From → To |\n|---|---|---|---|\n| calesthio/OpenMontage | +30,253 | 21 days | 5,899 → 36,152 |\n| DeusData/codebase-memory-mcp | +20,483 | 19 days | 7,516 → 27,999 |\n| mattpocock/skills | +19,053 | 15 days | 137,485 → 156,538 |\n| obra/superpowers | +16,887 | 20 days | 232,908 → 249,795 |\n| NousResearch/hermes-agent | +14,896 | 21 days | 197,297 → 212,193 |\n| Panniantong/Agent-Reach | +14,334 | 14 days | 34,780 → 49,114 |\n| usestrix/strix | +13,243 | 12 days | 26,363 → 39,606 |\n| addyosmani/agent-skills | +12,685 | 21 days | 63,156 → 75,841 |\n| asgeirtj/system_prompts_leaks | +11,720 | 21 days | 43,415 → 55,135 |\n| msitarzewski/agency-agents | +11,055 | 10 days | 118,241 → 129,296 |\n\nWindows differ because I only hold snapshots for the days a repo appeared in my scan; each row states its own real window.\n\nThree things in this data genuinely surprised me.\n\nFour of the top ten are not agent frameworks. They are collections of packaged expertise that plug into an existing agent: obra/superpowers (still compounding at roughly 840 stars a day on a 250k base), mattpocock/skills, addyosmani/agent-skills, msitarzewski/agency-agents.\n\nA year ago this table would have been full of new frameworks. Now the framework layer looks settled and the growth is in what you load INTO the agent. The moat moved from orchestration code to encoded judgment.\n\nThe steepest sustained climb from a newcomer in my dataset is MadsLorentzen/ai-job-search: +10,591 stars in 3 days, roughly 3,500 a day. It is an AI job application framework. Not a model, not a devtool.\n\nSame pattern elsewhere: OpenMontage (agentic video production) went 6x in three weeks and topped the whole table. xbtlin/ai-berkshire, a Chinese-language value-investing research agent, went from 1,518 to 12,339 in 15 days, an 8x. People are starring things that do a job for them, not things that help them build things.\n\nsmicallef/spiderfoot was created in April 2012. It is a classic OSINT automation tool. Between my June 21 and June 23 snapshots it gained 10,413 stars, the fastest burst I recorded from any repo.\n\nOld tools that happen to be perfect agent tools are getting second lives. If your decade-old project has a clean CLI and does one thing well, it is suddenly relevant again, because agents can drive it.\n\nThe live version of this table updates daily on [the rising repos page](https://whatstrending.ai/repos), and there's a [daily AI briefing](https://whatstrending.ai/pulse) built from the same tracked data (model usage movers, funding, and rising repos), archived per day.\n\nI'll keep the snapshots running. If this is useful I can post the four-week edition with week-over-week velocity, which the raw data already supports.", "url": "https://wpnews.pro/news/i-tracked-every-trending-ai-repo-s-stars-daily-for-3-weeks-the-growth-is-not-i", "canonical_source": "https://dev.to/codelong888/i-tracked-every-trending-ai-repos-stars-daily-for-3-weeks-the-growth-is-not-where-i-expected-4j8a", "published_at": "2026-07-10 00:38:14+00:00", "updated_at": "2026-07-10 01:05:48.939059+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-tools", "developer-tools", "generative-ai"], "entities": ["OpenMontage", "DeusData", "mattpocock", "obra", "NousResearch", "MadsLorentzen", "smicallef", "Spiderfoot"], "alternates": {"html": "https://wpnews.pro/news/i-tracked-every-trending-ai-repo-s-stars-daily-for-3-weeks-the-growth-is-not-i", "markdown": "https://wpnews.pro/news/i-tracked-every-trending-ai-repo-s-stars-daily-for-3-weeks-the-growth-is-not-i.md", "text": "https://wpnews.pro/news/i-tracked-every-trending-ai-repo-s-stars-daily-for-3-weeks-the-growth-is-not-i.txt", "jsonld": "https://wpnews.pro/news/i-tracked-every-trending-ai-repo-s-stars-daily-for-3-weeks-the-growth-is-not-i.jsonld"}}