I went down a rabbit hole this morning reading three late-2025 Juejin AI tool roundups back to back, and the thing that finally crystallized for me is that the Juejin 2025年度盘点 and the December 2025 AI IDE ranking and the 2025 AI tool pricing guide are all rating the same Chinese-language AI market on the same five axes they were using a year ago, and almost none of the projects that have been dominating GitHub trending in 2025 show up on any of those scorecards. I would not have written that sentence six months ago, and I want to put it down somewhere I can find it.
The piece that pushed me over the edge was the 2025年度盘点 that ran across the Juejin front page this week. Twelve scenarios, twelve categories, every entry rated as首选 or 其他, prices listed in 人民币 per month. Cursor sits at the top of the IDE list with the same two-axis argument it had in 2024, GitHub Copilot sits below it for the same ecosystem reason, Codeium sits below that for the same free-tier reason, v0 sits in the front-end slot for the same Vercel integration reason. The December 2025 IDE ranking that came out the same week gave Tencent CodeBuddy a 9.6, Sourcegraph Cody an 8.2, Replit Ghostwriter an 8.0, Codeium a 7.8, Tabnine a 7.6, Amazon CodeWhisperer a 7.5, JetBrains AI Assistant a 7.4, Blackbox a 7.2, on the same five axes as the post before it. To be fair the post that gave CodeBuddy the 9.6 was transparently written by an advocate, and I am taking the exact decimal scores with a grain of salt because the benchmark methodology is never disclosed, but the shape of the scorecard is the part that has been rattling around in my head all morning. We are scoring 2026 tools on 2024 criteria, and the gap is visible to anyone who reads a Juejin 年度盘点 and a GitHub trending recap in the same week.
The April, May, June, and October 2025 GitHub trending recaps surfaced Agent-S for GUI automation, Graphiti for memory graphs, supermemory for persistent context, mem0 for the memory layer pattern, FastMCP for plugin frameworks, claude-cookbooks as the Anthropic reference, TradingAgents-CN for multi-agent finance, and most recently AGENTS.md as a proposed standard for handing project context to AI coding agents. None of those projects compete on autocomplete latency. None of them have a SOC2 score. None of them show up in the Juejin 年度盘点, and the absence is the data point. Honestly I am a little skeptical of any Chinese-language AI tool ranking that scores tools on the enterprise procurement axis and ignores the agent runtime and memory layer axis, because the engineers I know who are picking tools right now are not buying autocomplete with chat. They are buying the ability to hand off an ambiguous problem to an agent and get back a multi-file edit with a hypothesis walk-through, and the Juejin scorecards do not even have a column for that.
The practical takeaway I want to call out is that the late-2025 Juejin roundups are still useful for tracking domestic-only products like Tencent CodeBuddy and 即梦 AI and 灵绘 AI and for getting a read on enterprise procurement preferences in the Asia-Pacific region, and the 2025年度盘点 does a good job of bucketing the chat and image and video categories by 谁先选 and 谁备选. But if you are a working engineer trying to decide which AI coding tool to pay for in 2026, the answer is almost certainly going to come from the GitHub trending recaps and the English-language reviews of Cursor and Claude Code and the memory layer projects like mem0 and supermemory, not from a list that scored Codeium at 7.8 in December 2025 on a five-axis scorecard that has not been updated since 2024. I have not stress-tested Agent-S or Graphiti the way I have with Cursor and Claude Code, so I want to actually ship something on top of them before I oversell or undersell them, but the fact that three separate Chinese-language roundups converged on the same five-axis scorecard with the same decimal scores tells me the roundup format itself is being copy-pasted rather than written from scratch, and that is a structural problem the format is going to have to solve if it wants to stay relevant for working engineers rather than enterprise procurement teams.
I will reassess in three months. The last time I said that I was mostly on Cursor and Claude Code for coding and ChatGPT for everything else, which is still roughly where I land. What has changed is that I now read the Juejin AI tool roundups as a useful artifact for the enterprise procurement market and the 国产 AI tool ecosystem specifically, and I read the GitHub trending recaps as the source of truth for what to actually build with, and I think that split is going to age well. Give it six months and I expect the Chinese-language roundups to start including the agent runtime layer and the memory layer projects on the scorecard, and when that happens I will know the format has finally caught up with what the engineers have been shipping on GitHub all year.
Top comments (0)