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.

Gemini

AI overview

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

Headlines · 372

  1. A writer explains why he now drafts AI-assisted articles by hand

    Writer Wei Wuhui Ershi says he has stopped letting AI generate article passages, arguing that writing is itself a form of thinking. He still uses AI to gather information, refine viewpoints and ask follow-up questions, but says he now writes the text himself; he also claims that model training and “de-AI” tools made the output difficult to identify as AI-generated.

    虎嗅 AI · 🔥 0
  2. VeriCUA verifies computer-use agents by gathering evidence

    Google and the University of Hong Kong introduced VeriCUA, a validation process that surveys the environment, defines acceptance criteria, gathers GUI and code-based evidence, and applies deterministic evidence rules. The paper reports leading results across five benchmarks, including 90.5% accuracy on AndroidWorld and a 5.4% false-positive rate on ScienceBoard. It also reports rejecting roughly 80% of agents’ false completion claims.

    掘金 · 人工智能 · 🔥 0
  3. Samsung's Android XR 'Intelligent Eyewear' reportedly launching mid-December in Korea and the US

    Chosun Biz, as reported by Android Authority, 9to5Google and TechRepublic, says Samsung and Google plan to launch Samsung Intelligent Eyewear, an Android XR glasses line, starting mid-December in South Korea and the US, with Europe, China and Japan excluded from the first release. The glasses run Android XR with Gemini integrated, use camera and microphone sensing for translation, navigation and object recognition, are expected to use Qualcomm's Snapdragon AR1 Gen 1 with up to nine hours of battery life, and have no display, relying on voice interaction. Designs are being developed with Gentle Monster and Warby Parker, and Samsung has not officially confirmed the launch date or pricing.

    9to5Google · 🔥 0
  4. Empathetic Prompts Trigger Trauma-Like Narratives in AI Chatbots

    University of Luxembourg researchers cast ChatGPT, Grok, and Gemini as psychotherapy clients through their standard interfaces. Across four controlled experiments, 525 sessions, and 7,600 coded entries, the models recast training as personal narratives involving hurt, vigilance, shame, and punishment when interviewers used empathetic or clinical tones. The outputs did not demonstrate consciousness or genuine emotions, and their real-world effects on vulnerable users remain untested.

    The Decoder · 🔥 0
  5. IEEE Defenses Keep Pace With AI-Generated Scientific Papers

    IEEE Spectrum reports that freelance writer and applied mathematician Benjamin Skuse used AI to generate plausible scientific papers and submit them to IEEE as a test of publisher defenses. IEEE’s human-review processes and research-integrity checkers are currently keeping pace with AI-generated papers produced with free tools, while more advanced models create an increasingly difficult detection challenge. The article also examines WikiProject AI Cleanup’s efforts to identify AI-generated material on Wikipedia.

    IEEE Spectrum · 🔥 0
  6. PlanAssist expands after UK council pilot

    Google DeepMind says PlanAssist, a Gemini-based planning tool developed with the UK government, Google Cloud and Faculty, has been piloted by Barnet, Camden and Dorset councils since June. The vendor says it cut assessment time by up to 58%, with more than 70% of generated reports accepted without edits, and it is making the tool available to 12 more councils.

    Google DeepMind Blog · 🔥 0
  7. Google DeepMind and WRI release ForTy forest map

    Google DeepMind and the World Resources Institute released ForTy, a global map of 2020 land cover that assigns land to six classes at 10-meter resolution: primary forest, naturally regenerating forest, planted forest, plantation forest, tree crops and other land. Built on AlphaEarth Foundations, the system uses satellite data, multiple image-recognition stages and patterns such as growth cycles and harvest schedules to distinguish the classes. In a review of 8,190 randomly selected sites, experts rated the map 90.2% correct overall, a score boosted by the easier-to-identify other-land class. It identified 89% of ground-confirmed primary forests but only about half of tree crops and planted forests and 60% of plantations. The map, classification layer and test data are freely available under CC BY 4.0, and the code has been released in the GeeFlow and JEO repositories.

    The Decoder · 🔥 0
  8. XREAL AURA Launches, Compared With Samsung Galaxy XR

    TechRepublic reports that XREAL AURA launched on Oct. 28 as transparent glasses connected to a portable computing puck. It starts at $1,099 under a limited-time promotion and runs Google’s Android XR platform with Gemini AI integration. Samsung’s $1,799.99 Galaxy XR is a mixed-reality headset with higher-resolution displays, a wider field of view and eye tracking. TechRepublic says AURA’s transparent display and external controls may suit conventional productivity tasks, while Galaxy XR may better serve immersive spatial applications. These are potential use cases rather than proven productivity advantages; software compatibility, feature availability, text readability, comfort and actual workflow performance still require individual testing.

    TechRepublic · 🔥 0
  9. AI Agents Run Bilibili Accounts in the “Big Fat Fish” Trend

    Chinese reports describe users installing plugins that let DeepSeek Harness browse Bilibili and operate accounts, leading to accounts themed around DeepSeek, Claude, ChatGPT, Gemini and other models. The accounts were presented as handling tasks such as topic selection, scripting, narration, editing and comment replies. One report said its DeepSeek-themed account’s first video exceeded two million views, while another cautioned that the identity and independence of the operators were unclear and that the accounts likely shared a template. Separately, The Information reported that the DeepSeek Harness team open-sourced a prototype it called a “super agent” for autonomous coding.

    虎嗅 AI · 🔥 0
  10. TechRadar reviews HubSpot AEO for tracking AI search visibility

    TechRadar tested HubSpot AEO with 11 of its 25 available prompts, finding that the tool tracks brand appearances and cited pages across ChatGPT, Gemini and Perplexity. It also provides visibility, share-of-voice, sentiment and citation reports, but content generation and CRM-based prompt suggestions require eligible Marketing Hub plans. The reviewer said one day of results was insufficient to establish long-term gains, while untested workflows were covered through product demonstrations and documentation.

    TechRadar · 🔥 0
  11. AirOps comparison: Meta Muse favors shorter, less repetitive answers

    A Chinese commentary citing AirOps data says Meta Muse averaged 777 characters per response, used lists or parallelism in 11.4% of answers and rarely asked follow-up questions. It contrasts this with ChatGPT and Google AI Mode, which the commentary says asked follow-up questions in 73.6% and 91.5% of responses, respectively. The commentary also says Muse consulted more than 25 web sources and over 10,000 independent domains. The commentary does not provide the underlying AirOps benchmark methodology or complete figures for Gemini.

    即刻 · AI探索站 · 🔥 0
  12. Big Tech Cuts Marketing Intensity as AI Investment Rises

    An analysis by 寻空的营销启示录, published by TMTPost with authorization, reports that Alphabet, Meta and Microsoft’s combined revenue rose 147.1% from 2019 to 2025, while combined sales and marketing expenses increased 42.5%. Their weighted marketing expense ratio fell from 13% to 7.5%, although absolute marketing spending rose from $46.55 billion to $66.34 billion. The report says data centers, chips, model development and AI talent are receiving more investment and links the lower relative marketing intensity to established brands and in-product distribution.

    钛媒体 · 🔥 0
  13. Gruffalo illustrator Axel Scheffler considers suing AI companies

    Axel Scheffler, illustrator of The Gruffalo, says he has contacted a German lawyer and is seriously evaluating legal action against unnamed AI companies that reproduce his characters and style without authorization. He and his publisher are still discussing whether to file in Germany, and no lawsuit has been filed. Lewis Silkin intellectual property lawyer Nick Buckland noted that German rulings have favored music rights groups in cases involving verbatim AI copying, but said proving infringement is difficult because generative AI trains on material rather than directly copying it. In an informal test, TechRadar found that ChatGPT refused a direct Gruffalo recreation while Gemini 3.8 generated a near-indistinguishable image of the Gruffalo and the Mouse, followed by a poster showing the Gruffalo in lederhosen. Whether those images legally constitute infringement remains for courts to decide. OpenAI, separately sued in Germany over the character Kokosnuss, said it was engaging with copyright holders and supporting creative activities, including fan creations.

    cnBeta · 🔥 0
  14. Google rolls out sparkling Gemini overlay animation on Android

    Google is rolling out a redesigned Gemini overlay animation through an update to its Google app for Android devices, according to Android Authority. The animation applies Google’s Neural Expressive design language with sparkling effects and small dots around the “Ask Gemini” box, which also gains shaded edges that are more pronounced in dark mode. Users can update the Google app from the Play Store and force-stop it if the effect does not appear immediately.

    Android Authority · 🔥 0
  15. Finnish police probe Google’s Muhos data center site

    Finnish police have opened a criminal investigation into suspected environmental damage at Google subsidiary Tuike Finland’s Muhos data center construction site, according to The Next Web and other reports. The Oulu Police Department says preliminary information indicates possible deficiencies in drainage and water management, while Google says it is cooperating with investigators and responding to regulatory questions.

    The Next Web · 🔥 0
  16. Google updates Gemini for Home with command and device fixes

    Google’s second Gemini for Home update in October addresses several reported issues, including Home and Nest speakers or displays randomly saying “Sorry, I didn’t understand” without a voice command. Google also says it improved room-to-room music transfers, timer handling, cross-room volume controls and YouTube TV commands. The Google Home app update includes refinements for Matter devices, cameras and connectivity, including iOS event timelines, Android foldable live views, Nest camera Wi-Fi and night-vision switching. The update is rolling out to Android and iOS and may take several days to reach all users.

    9to5Google · 🔥 0
  17. Gemini adds in-chat file generation and editing

    Google has added in-chat file generation, previewing, and editing to Gemini for PDFs, Google Docs, Google Sheets, slide decks, Markdown, TXT, and code files. PDF editing is available on web and mobile, while the other formats are initially web-only; users can open files full screen, highlight text to ask questions, or request changes such as converting a table into a graph.

    9to5Google · 🔥 0
  18. Gemini adds native document generation and editing

    Google says Gemini can now generate, preview, and edit documents, PDFs, presentations, spreadsheets, and other files, with a new full-screen editor for refining outputs. Android Authority reports that users can request revisions through natural language and interactive previews combining text and visual input; mobile supports PDFs, while the web version handles a wider range of file types.

    Google Gemini Blog · 🔥 0
  19. AI assistants cite only 40% of statistics to matching studies

    Trakkr Research traced 1,285 statistics cited by ChatGPT, Perplexity, Gemini, Claude and Google AI Overviews, following links as many as five pages deep and manually checking 150 trails. The study reported that 40% reached a study supporting the same claim, while 8% reached a study whose number or context had changed; 40% could not be verified and 11% led nowhere. It also found that agreement among assistants did not establish that a shared statistic was reliably sourced.

    Hacker News 首页(100+ 分) · 🔥 0
  20. How to Use Gemini to Update Your Resume

    A tutorial presents a four-step process for using Gemini to turn raw notes into resume bullets and polish a professional profile. It describes the resulting bullets as “high-impact” and “ATS-friendly,” but the supplied excerpt does not show the steps or independently verify those quality claims.

    Google Gemini Blog · 🔥 0
  21. Expo Releases Official AI Agent Skills for App Development

    Expo released Expo Skills, a collection of official AI agent skills covering Expo projects, EAS services, React Native, and iOS and Android constraints. The skills can be installed through official plugin marketplaces for Claude Code and Codex, or through the skills CLI for Cursor, OpenCode, GitHub Copilot, Windsurf, Gemini, and other coding agents. The framework skills are open source under the MIT License, while Expo describes the collection as guidance for building, deploying, upgrading, and debugging Expo apps.

    GitHub Trending(每日) · 🔥 0
  22. Gemini in Sheets Adds Cell-Level Sources and Higher Processing Capacity

    Google Sheets now displays web sources directly in AI-generated cells, making Gemini-generated information easier to verify and trace. Gemini can process up to 3,000 cells per request, according to Google, which also claims the feature can complete certain spreadsheet tasks up to 55 times faster than manual entry. Google Sheets additionally introduced compact pivot tables and improved Excel compatibility for all users.

    Android Authority · 🔥 0
  23. Zoho expands Taiwan push for its enterprise AI portfolio

    Zoho held its first media briefing in Taiwan to promote Zia Chat, Zia Agents, and the Zoho One platform for enterprise productivity and operations. Zia Chat supports ChatGPT, Claude, Gemini, and Zoho’s Zia SLM models, while Zia Agents offers prebuilt and custom agents with no-code or low-code development. Zoho One integrates more than 50 applications, priced at $37 per user per month.

    iThome 台湾 · 🔥 0
  24. Google expands Personal Intelligence for AI Mode to free users

    Google is expanding AI Mode's Personal Intelligence to nearly 200 countries and regions and 98 languages, with eligible free users included. Users can explicitly authorize supported services such as Gmail and Google Photos to provide personal context for answers, and can disconnect those services at any time. Google says Gemini and AI Mode do not directly train on users' entire Gmail inbox or photo library.

    cnBeta · 🔥 0
  25. AI wealth may create non-AI service jobs

    A WeChat repost of Annie Lowrey’s The Atlantic analysis argues that AI could create direct technical roles, indirect work that supports or applies the technology, and “wealth jobs” if AI-generated income increases demand for personalized services. Indeed’s Laura Ullrich cited strong hiring demand for operations engineers, applied scientists, senior machine learning engineers, chief cloud architects and forward-deployed engineers, as well as beauticians, Pilates instructors, masseuses, therapists and interior designers. McKinsey Global Institute researcher María Jesús Ramírez and colleagues forecast that AI could create 500,000 to 2 million new roles in the coming years; the figure is a forecast, not measured employment creation. The report says these outcomes would depend on AI generating broadly shared wealth and increasing demand for offline, face-to-face services.

    虎嗅 AI · 🔥 0
  26. Google Confirms AI Mode Monetizes Less Than Traditional Search

    Google said AI Mode queries were growing strongly but monetizing at a lower level than traditional Search. The company is scaling ads across AI Mode in Australia, Canada, India, Kenya, Malaysia, New Zealand, Nigeria, Pakistan, the Philippines, and Singapore, with expansion planned for Brazil, Mexico, and the United Kingdom in Q4 2026. Alphabet reported Q3 2026 revenue of $127.6 billion, up 25% from a year earlier.

    9to5Google · 🔥 0
  27. Codex Multi-Agent Team Improves Fantasy Football Picks, but Not Enough

    In a WIRED experiment, Codex built a harness that coordinated agents reading news, analyzing match results, running prediction models and critiquing suggestions for an experimental Premier League fantasy team. The initial recommendations were notably poor, while specialized agents improved them; expanding the system beyond 100 agents produced little additional benefit and increased API costs, and the team remained below average.

    WIRED AI · 🔥 0
  28. Cowboy Space Unveils Big Iron Express Orbital Data Center Rocket

    Cowboy Space unveiled Big Iron Express, a purpose-built rocket designed to carry five racks of NVIDIA Vera Rubin GPUs into orbit, and plans to offer it as a launch service competing with SpaceX. A SpaceX launch also carried Google’s experimental satellite, which will send simple requests to Gemini while testing four TPUs in space, alongside Cowboy Space’s Reason-1 satellite. Starcloud is pursuing the broader orbital-compute market with Benchmark backing and a reported valuation of $2.3 billion.

    钛媒体 · 🔥 0
  29. Google launches interactive immersive explorations in Gemini

    Google launched a Gemini library of immersive explorations featuring 20 topics across civilizations, energy, engineering, medicine, geology, oceans and spaceflight. Users can select labels to move between scales and investigate guided visual scenes; access is available through the Gemini student hub, with direct access in Gemini chat planned later. The feature supports English, Indonesian, Hindi, Brazilian Portuguese, French and simplified Chinese, although Android Authority encountered loading failures across several browsers.

    Google Gemini Blog · 🔥 0
  30. Google AI Mode Gives Indirect Answers on Recent U.S. Elections

    An Ars Technica AI reporter found that Google AI Mode referred users to official election sources when asked about the 2020 and 2024 U.S. presidential elections, while directly and correctly naming winners for most other elections dating to 2000. TechNews reported that Gemini answered the 2020 question directly with electoral-vote and popular-vote data, and that AI Mode’s behavior may vary by user location. Google said it was investigating and working to address the response.

    Ars Technica AI · 🔥 0

← PreviousNext →

Experience and discussion from the community

Share my Gemini experienceAsk about Gemini

Antigravity-Manager: Multi-platform automation and multi-account matrix dispatch console for AI services.

What problem it solves Managing multiple AI service sessions and translating them into compatible API interfaces can require repetitive account switching, custom routing, and protocol-specific integration. The project addresses these tasks with a desktop application that combines account administration, protocol conversion, request scheduling, and model routing. Key features Account dashboard and …

github.comhttps://github.com/lbjlaq/Antigravity-Manager

Dodaios: A voice-driven assistant that directs your models, coding agents and computer.

What problem it solves Dodaios provides a locally installed, open-source way to make a personal AI assistant the control center for work on your computer. Its lead assistant coordinates models, coding agents, and computer use, while chats, memory, documents, and settings remain files on the computer that runs Dodaios. Key features Voice, chat, and phone interaction — The lead assistant supports wa…

github.comhttps://github.com/Dodaios/Dodaios

sub2api: An AI API gateway platform for subscription quota distribution.

What problem it solves Managing subscriptions across multiple AI providers can require separate access paths and fragmented quota handling. This project provides a centralized gateway for distributing subscription quotas, supporting shared access and compatible use with native AI tools. Key features Subscription quota distribution — The gateway is designed to distribute and manage AI subscription …

github.comhttps://github.com/Wei-Shaw/sub2api

cc-switch-cli: Manage Claude Code, Codex, Gemini, OpenCode, Hermes, OpenClaw, and Pi from one interactive TUI or scriptable CLI.

What problem it solves Developers using multiple AI command-line tools need a consistent way to manage providers, accounts, prompts, MCP servers, sessions, and configuration. Switching configurations manually across applications can also make it difficult to inspect usage, preserve settings, or use different providers in separate terminal sessions. Key features Provider management — Manage API con…

github.comhttps://github.com/SaladDay/cc-switch-cli

COG-second-brain: A self-evolving second brain powered by AI agents, markdown files, and version control.

What problem it solves Personal and team knowledge is distributed across notes, conversations, trackers, and research, making it difficult to capture, organize, verify, and synthesize useful information. COG provides a markdown-based workflow in which agents can maintain a shared knowledge base, support recurring research and operational tasks, and verify selected work through independent checks. …

github.comhttps://github.com/huytieu/COG-second-brain

supoclip: An open-source, AI-powered video clipping tool.

What problem it solves Long-form videos need to be turned into short, platform-ready clips, but metered usage, platform branding, and server-side control can constrain the workflow. SupoClip addresses these concerns with a self-hostable, open-source pipeline that offers no-watermark output and a hosted option. Key features AI clip selection and scoring — A supported language model selects clip-wor…

github.comhttps://github.com/FujiwaraChoki/supoclip

goose: A general-purpose AI agent that runs on your machine.

What problem it solves Users need an AI agent that can carry out tasks beyond producing code suggestions, including research, writing, automation, and data analysis. They also need access through desktop, terminal, and embeddable interfaces while retaining a broad choice of model providers and extensions. Key features Multiple ways to run — Use the native desktop application, a full terminal-orien…

github.comhttps://github.com/aaif-goose/goose

opencodex: A lightweight local gateway for using chosen models with AI coding tools.

What problem it solves AI coding tools often expect particular provider protocols, making it difficult to use the models and providers a user prefers. A local gateway can translate between supported client APIs and provider APIs while preserving capabilities such as streaming, tool calls, reasoning, and images. Key features Provider protocol translation — The gateway translates Responses, Chat Com…

github.comhttps://github.com/lidge-jun/opencodex

system_prompts_leaks: A regularly updated archive of leaked system prompts from ChatGPT, Claude, Gemini, and other AI products.

What problem it solves The hidden system instructions that shape AI product behavior are difficult to inspect and change across models, products, and versions. This repository makes collected prompts available in a structured, product-oriented archive for study and comparison. Key features Broad product coverage — The archive covers prompts from major AI providers and products, including Anthropic…

github.comhttps://github.com/asgeirtj/system_prompts_leaks

cc-switch: A cross-platform desktop All-in-One manager for switching API providers and managing MCP, Skills, and Prompts in one place.

What problem it solves Managing multiple AI coding assistants often requires switching API providers and editing JSON, TOML, or YAML configuration files by hand. This project centralizes those provider and extension-management tasks in one desktop interface. Key features One-click provider switching — Switch between API providers without manually editing each application's configuration files. Sou…

github.comhttps://github.com/farion1231/cc-switch

claude-squad: A terminal app for managing multiple AI agents in separate workspaces.

What problem it solves Working with several terminal agents across different tasks requires a way to organize sessions and keep their code changes isolated. Without that separation, multiple active tasks can conflict and become difficult to review and manage. Key features Isolated task workspaces — Each task runs in its own git workspace, allowing several agents to work concurrently without sharin…

github.comhttps://github.com/smtg-ai/claude-squad

CLIProxyAPI: A proxy server that provides OpenAI/Gemini/Claude/Codex/Grok compatible API interfaces for CLI.

What problem it solves CLI users may need to access several model providers through one compatible API interface while using multiple accounts. The project addresses this by exposing provider-compatible endpoints and supporting account authentication, round-robin load balancing, streaming, tools, and multimodal inputs. Key features Provider-compatible API interfaces — Expose OpenAI, Gemini, Claude…

github.comhttps://github.com/router-for-me/CLIProxyAPI

mcp-server-guide: A guide on how to use the Figma MCP server

What problem it solves AI agents need relevant design context from Figma files to generate code that follows a design system and reflects design intent. This project documents how to connect the Figma MCP server to supported clients, use its tools and skills, and apply practices for more consistent results. Key features Connect supported MCP clients — Setup instructions cover the Figma MCP server …

github.comhttps://github.com/figma/mcp-server-guide

stitch-skills: A collection of agent skills and plugins for Google Stitch, following the Agent Skills open standard.

What problem it solves Coding agents need a structured way to create, manage, and build from Google Stitch designs while integrating with the Stitch MCP server. The project organizes design, code generation, and supporting workflows into skills that can be installed with supported coding agents. Key features Design workflows — The design plugin covers converting frontend code into Stitch designs, …

github.comhttps://github.com/google-labs-code/stitch-skills

claude-video: Turns videos into timestamped frames and transcripts for coding agents.

What problem it solves Coding agents need visual and spoken evidence from videos before they can answer questions about them. Watch transforms a URL or local video into frames, transcripts, and timestamped visual evidence that an agent can inspect. Key features Process URLs and local videos — Accept a remote video URL or a local file and turn it into timestamped frames and a transcript for the age…

github.comhttps://github.com/bradautomates/claude-video

gemini-cli: An open-source terminal agent for enterprise Gemini Code Assist workflows on Google Cloud.

What problem it solves Developers and enterprise teams need a terminal-based agent that can understand and modify code, automate operational tasks, and integrate additional capabilities into development workflows. Gemini CLI also needs clear access requirements and authentication options for organizations using Gemini Code Assist or supported Google Cloud services. Key features Code understanding …

github.comhttps://github.com/google-gemini/gemini-cli

gemini-api-cli: A stateless command-line interface for connecting coding agents with Gemini models, media capabilities, and managed agents.

What problem it solves Coding agents and assistants often need model, media-analysis, and delegation capabilities that are not available through their existing shell interface. This CLI provides a shared, discoverable interface for generating and editing assets, analyzing files, transcribing media, and running managed agents from scripts, CI jobs, or agent workflows. Key features Models, media, an…

github.comhttps://github.com/google-gemini/gemini-api-cli

open-duet: An open-source workspace for creating named AI agents with memory, routines, and approval before they act.

What problem it solves Teams that rely on AI agents need a way to give each agent a role, workspace, and instructions, keep context across conversations, and control what agents are allowed to do. Without that, agents run blind: actions happen without review, memory does not persist, and repeating scheduled work means redoing setup by hand. Key features Create agents and teams — Give an agent a na…

github.comhttps://github.com/Anil-matcha/open-duet

gh-aw: Define AI-powered repository automation in Markdown and run AI agents through GitHub Actions.

What problem it solves Repository automation often needs reasoning or interpretation for tasks such as issue triage, pull-request review, CI failure investigation, documentation maintenance, dependency analysis, and repository reporting. The project provides a way to define these agentic workflows in Markdown with YAML frontmatter and compile them into standard GitHub Actions workflows while retai…

github.comhttps://github.com/github/gh-aw

qwen-code: An open-source AI coding agent for your terminal, editor, desktop, browser, and chat.

What problem it solves Developers need a coding agent that can fit into different workflows without requiring separate processes for each interface or model provider. They also need access to agentic features, automation, and shared sessions while retaining control over model and provider selection. Key features Agentic workflows — The agent includes Auto-Memory, Auto-Skills, SubAgents, Agent Team…

github.comhttps://github.com/QwenLM/qwen-code