Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Trae

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 10

  1. TRAE launches developer assistant for project-level AI coding

    TRAE officially launched a developer personal assistant on October 29, combining cross-project context with task decomposition, parallel execution, and coordination for complex development work. GeekPark’s hands-on test on the go-kratos/kratos repository reported that the assistant handled documentation, example code, testing, build checks, and interface validation as coordinated subtasks, though the results come from a single promotional-leaning source.

    极客公园 · 🔥 3
  2. Why AI Product Retention May Outweigh Leaderboard Wins

    In an authorized TMTPost analysis, Zhixun Think Tank argues that model quality can win trials but does not necessarily create lasting user loyalty. It recommends comparing candidates on real task delivery, rework time, full cost, workflow integration, and continuity, rather than relying only on leaderboard positions.

    钛媒体 · 🔥 0
  3. AI coding agents are changing the identity of Programmer’s Day

    GeekPark argues that 1024 Programmer’s Day is unlikely to be canceled, but its traditional identity as a holiday for programmers may weaken as AI coding agents take on repetitive implementation work. This year’s event was renamed the “1024 Programmer’s Day and AI Builders Conference,” with a theme of “Everyone Can Build,” while a festival promotion expanded participation to people who direct AI tools. The article cites an Anthropic report saying junior employees’ share of its technical staff fell from 21% to 14% between the start of 2025 and the report date, while the share of junior roles among new technical hires fell from 27% to 9%. It also reports that Claude agent work time first exceeded employee work time in March and reached six times the amount of human work time by August, according to Anthropic’s report. The article describes programmers’ work increasingly shifting toward reviewing code, directing agents and validating results.

    极客公园 · 🔥 0
  4. WorkBuddy leads China desktop AI office-agent traffic ranking

    Analysysys’ September 2026 China desktop AI-native office-agent ranking, relayed by 36Kr, put Tencent’s WorkBuddy first with 85.34 million monthly visits. Alibaba’s Qwen Office followed with 46.55 million visits, ahead of ByteDance’s Doubao Work at 30.39 million, TRAE at 27.12 million and CodeBuddy at 25.88 million; Baidu’s Dazi was reported eighth with 9.26 million interactions.

    36氪 人工智能 · 🔥 0
  5. Doubao absorbs four agent lines as ByteDance makes it the trunk

    A commentary published by TMTPost and written by Han Gong Guancha says ByteDance folded four scattered agent product lines into Doubao: the Feishu product team merged into Doubao on July 30, TRAE and Coze teams joined the Doubao system on August 24, and the personal-assistant product Xiaodou (internal codename Spell) entered internal testing in late September. It also says that from August 10, hotel orders completed through the Doubao entry point and Douyin Laike carried a combined fee of about 12% (an 11.4% software service fee plus 0.6% payment fee), versus 8% before. The author argues Alibaba's merger of QoderWork, MuleRun and Wukong into Qwen Office, and Tencent's move of QClaw into WorkBuddy, mirror ByteDance's consolidation; the organizational and fee details are cited from Caixin, 36Kr and National Business Daily, and ByteDance has not confirmed each item.

    钛媒体 · 🔥 0
  6. Volcano Engine's OpenViking pitches a filesystem for agent memory

    Volcano Engine has open-sourced OpenViking, a context database for AI agents that organizes knowledge, memories and skills into one virtual filesystem under the viking:// scheme, navigable with file-like operations such as ls, tree, read, write and grep. Each directory carries generated summaries in three tiers — an L0 one-sentence abstract, an L1 overview and L2 full content — so agents can judge relevance before loading details, and committing a session archives the conversation and extracts memories as editable Markdown. The project says version 0.3.22 was evaluated on LoCoMo long-conversation user memory and tau2-bench multi-turn agent tasks, and it ships a no-install browser Studio plus memory plugin installers for Claude Code, Codex, Cursor, TRAE and OpenCode.

    GitHub Trending · Python · 🔥 0
  7. ByteDance showcases AI stack at Douyin's 2026 Wonderful Night

    According to a Lanmeihui report published by TMTPost, Douyin's 2026 Wonderful Night put AI at the center of the stage: singer Hu Yanbin and creators from the Trae community used AI Coding to build an interactive “laser strings” instrument, while tech creator Tim demonstrated an interactive scene based on a ByteDance world model that is still in development and unreleased. The report also says Seedance 2.5's motion-transfer feature let a digital peacock on screen dance in real time with Yang Liping's performance, and that many stage visuals were generated with video models such as Seedance. The article calls it the “most AI-dense” gala and says ByteDance used the event to show an AI stack spanning Volcano Engine compute, Seedance and Seedream models, Trae, and Doubao apps.

    钛媒体 · 🔥 0
  8. Hands-on: ByteDance's merged TRAE links Agent and IDE modes, but features lag

    ByteDance announced on Oct 9 that it merged TraeWork and TraeCode into a single TRAE, repositioning it from an AI coding tool to an "AI Development platform" with an Agent mode and an IDE mode that switch without re-importing a project. In a hands-on test republished by 钛媒体 and written by 光子星球, Agent mode produced a working browser-based bookkeeping web app in about 20 minutes, and the IDE mode then allowed direct code edits plus a click-to-target fix of a text-overlap bug. The review also found the template library's "做同款" button intermittently unresponsive, an always-empty "我的产物" area with generated files saved only locally, and hallucination risks in an automated AI daily-news briefing. It added that former TRAE lead 石扬 was reported to have left ByteDance on the same day as the merger announcement.

    钛媒体 · 🔥 0
  9. ByteDance AI roles reach 42.8% of job postings in 'full-stack' hiring push

    An analysis of ByteDance's careers site counted 11,187 open China social-recruitment roles on Oct 5, of which 4,791 (42.8%) relate to AI — with AI's share of newly posted roles rising from 33% to 55%. By unit, the Seed model team was 96.1% AI roles, Doubao and other AI-native apps 77.2% and CapCut 74.3%, while e-commerce (26.4%) and local services (16.9%) trailed. The author argues ByteDance is hiring across six layers — chips, compute, foundation models, cloud, applications and devices — a "saturated, full-stack" push that comes at the cost of focus.

    创业邦 科技 · 🔥 0
  10. TRAE merges Code and Work into one agent-plus-IDE workspace

    AI coding tool TRAE has folded its TraeCode and TraeWork apps into a single upgraded TRAE, with an Agent mode and an IDE mode that switch from the top-right corner. Agent mode acts as a global workbench where several agents can run tasks in parallel — writing code, producing documents, running tests — while IDE mode keeps the SOLO and IDE workflows for hands-on edits. In QbitAI's hands-on tests, outputs from each task were collected in a shared "My Artifacts" area and could be shared, and the tool also offers templates, @-mentions via Feishu or WeChat, and mobile sync.

    量子位(原生 RSS) · 🔥 0

Experience and discussion from the community

Share my Trae experienceAsk about Trae

I usually use the TRAE plugin's builder mode in IDEA to assist with development.

I usually use the TRAE plugin's builder mode in IDEA to assist with development. At the start of a conversation, after describing the basic requirements, add the following two paragraphs as instructions—the experience is much better. ---------- If any requirement is unclear, don't make your own inferences; ask me questions. Keep asking until you've gathered enough information and confirmed the tec…

Trae