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.

Cursor

AI overview

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

Headlines · 212

  1. Column says AI office race hinges on foundation models, channels and industry depth

    A column by the WeChat account Naojiti, republished by Huxiu AI and TMTPost, argues that China's AI office competition is being fought on three fronts: foundation models, marketing and channels, and industry-specific workflows. It says Tencent announced that WorkBuddy's built-in models now support Kimi K3, after previously offering Hunyuan, DeepSeek, GLM and MiniMax, and that Kimi K3's context window reaches up to one million tokens. It also cites an AICPB July 2026 desktop ranking with WorkBuddy first at 11.15 million monthly active users and Baidu Dazi second at 6.74 million, and describes Huawei Cloud's upgraded OfficeAce with more than 20 preset expert agents plus expanded finance skills.

    虎嗅 AI · 🔥 0
  2. JetBrains brings IntelliJ's Java and Kotlin analysis to Cursor and VS Code

    JetBrains released version 1.0 stable of its Java and Kotlin development extension, which uses the Language Server Protocol to bring IntelliJ IDEA code analysis, autocompletion, refactoring and debugging into Cursor and VS Code. It supports Java, Kotlin and mixed projects imported via Maven, Gradle or Bazel, including JUnit testing and breakpoint debugging. JetBrains also worked with Cursor so AI agents in its operation window can use some inspection results, such as flagging possible null-value issues and checking Spring framework problems; letting agents call the language server directly while writing code remains planned for a later version. The extension is available from the Visual Studio Marketplace and Open VSX, and 1.0 ends the free preview with a 30-day trial before an IntelliJ IDEA Ultimate subscription is required. JetBrains said it is also testing the same language analysis for terminal-based AI coding tools such as Claude Code and Codex.

    iThome 台湾 · 🔥 0
  3. Manus's survival paradox: shorter windows and token bills for agent apps

    36Kr republished an article from the WeChat account Xiutai analyzing Manus's "dependent innovation": the company does not train foundation models but calls external ones such as Anthropic's Claude and Alibaba's Qwen to build an agent that can open web pages, write code and deliver files. It launched in March 2025, passed $100 million in annualized recurring revenue eight months later, and in October 2026 raised more than $500 million at a valuation of about $4 billion, the article says. It argues that in the LLM era the lead time available to platform-dependent builders keeps shrinking, and that agents sit directly on model companies' main path, so heavier usage means bigger token bills — Ji Yichao's engineering notes put Manus's input-to-output token ratio at about 100 to 1. In October Manus released version 2.0 and Cue, which gives agents email accounts and digital wallets, an attempt to build user relationships that survive a change of underlying model.

    36氪 人工智能 · 🔥 0
  4. Cursor plugin specification and official plugin repository

    The cursor/plugins repository README describes Cursor's plugin specification and official plugins for developer tools, frameworks and SaaS products. It says each plugin is a standalone directory at the repository root with its own .cursor-plugin/plugin.json manifest, while the root .cursor-plugin/marketplace.json lists all plugins. The listed plugins include Cursor-built developer tools such as Thermos, Orchestrate, Cursor SDK and PR Review Canvas, as well as integrations such as Gmail, Zoho CRM, Tailscale and TikTok for Business. The repository is MIT licensed.

    GitHub Trending(每日) · 🔥 0
  5. NPCTalk brings unscripted voice dialogue to GTA 5

    Universal Modder's open-source NPCTalk toolkit lets players speak with GTA 5 characters, which dynamically generate context-sensitive replies in AI-cloned voices and can perform animations or respond to spoken commands. IT之家 reports that NVIDIA Nemotron ASR handles transcription, Qwen 3.8 27B generates dialogue through Cerebras, Fish Audio Drama 3 synthesizes cloned voices, and TypeSafe Jev controls NPC actions. The project has been demonstrated only in GTA 5 Legacy single-player mode, requires separately integrated cloud and GPU infrastructure, and has not been confirmed as an immediately available one-click mod.

    IT之家 AI · 🔥 0
  6. ai-memory: open-source long-term memory across AI coding agents

    The akitaonrails/ai-memory project, trending on GitHub, describes itself as a long-term memory solution for AI coding agent CLIs that carries context between agents from different vendors. Its README says a user can quit Claude Code mid-task, start OpenAI Codex in the same directory and continue without re-explaining the architecture, failed approaches or open questions. It claims more than twenty harnesses feed one shared memory — including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Grok, Devin, Kimi and Kiro — with memory stored as a git-backed wiki of plain Markdown files on a self-run server, plus multi-user auth and an audit log. These are the project's own claims and have not been independently evaluated.

    GitHub Trending(每日) · 🔥 0
  7. OpenAI hires ex-xAI sales lead Graham Seamans to head cybersecurity sales

    OpenAI has hired Graham Seamans to lead sales for its cybersecurity business, Bloomberg reported. According to IT之家 citing Bloomberg, Seamans led xAI's sales team from August 2025 and worked on pitching the Grok chatbot to Wall Street clients; before xAI he spent about eight years at MongoDB. The hire is described as the latest in a string of sales executives OpenAI has recruited from Elon Musk's AI venture, with OpenAI also bringing on former Cursor global revenue and sales president Brian McCarthy for a global sales VP role since September — details that have not been independently confirmed by other sources.

    Bloomberg Technology · 🔥 0
  8. Tencent Hunyuan open-sources Hy Memory 2.0, Hy-Memory-30B-A3B and MemHub

    Tencent Hunyuan announced Hy Memory 2.0 on October 16, open-sourcing three layers: the dedicated memory model Hy-Memory-30B-A3B, the memory framework SDK and the local MemHub app. Tencent says the framework handles chat, work and code memory and ranks first against open frameworks including Mem0, MemOS, EverOS and OpenViking on four benchmarks; it reports that Hy-Memory-30B-A3B, with about 3B active parameters, scored a 55.49 macro average across four memory harnesses versus 54.62 for Claude Opus 5. MemHub ships as a CLI and Mac app that can connect to roughly 10 tools such as WorkBuddy, Cursor, Codex and Qwen Code, while the model weights are published on Hugging Face under Apache 2.0, followed on October 18 by an FP8 version optimized for vLLM deployment. All performance figures are Tencent's own claims and have not been independently verified.

    腾讯混元 · Hugging Face · 🔥 0
  9. 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
  10. Cursor cloud agents now build shareable canvases; Environments API in beta

    Cursor's changelog says cloud agents can now build interactive canvases as part of their work, and a finished canvas can be shared with a team by sending its link. The company also released an Environments API in beta for programmatically creating and managing the cloud environments its agents run in. Cursor further says cloud agent environments now support up to 300 repositories, with large environments loading 5x faster — a speedup figure the vendor states without independent measurement.

    Cursor Changelog · 🔥 0
  11. OPPO AI Xinli Ball hands-on: an always-on recorder as AI coach

    GeekPark published a hands-on review of OPPO's AI Xinli Ball, first shown at OPPO's ODC on Sept. 17, saying the device weighs 9.8 grams with its clip; OPPO claims 24 hours of continuous recording, 5-meter pickup, voiceprint recognition, and automatic start and stop via its case. The review says its PersonaX memory engine groups related conversations into project timelines, while MCP support exposes notes and long-term memory to external tools such as WorkBuddy, Codex, Claude and Cursor; privacy measures include a recording light and text-only retention. The early-experience version works only with OPPO, OnePlus or Realme phones and does not yet integrate deeply with ColorOS notifications, and a new firmware and app were pushed on Oct. 11.

    极客公园 · 🔥 0
  12. Cursor probed whether confidential client data reached SpaceX AI for Grok Bot training

    According to internal communications viewed by The Information, Cursor engineers raised concerns in late July that data from testing and everyday use of Grok Bot (internally codenamed Sand) may have been sent to SpaceX's AI unit, potentially including confidential information about customers, suppliers and business partners. Cursor opened an internal investigation whose conclusions are not public, and it has since required employees to log in with company email addresses and decided that future model training will exclude employee-generated usage data. A Cursor lawyer wrote internally that the data may contain third-party trade secrets and that the company may not have the legal right to use it for training. The reports also describe a separate summer incident in which Cursor's Vercel-built sales sites had passwords written into their code, putting some Verizon, Bosch and Coupa customer information at risk.

    The Information · 🔥 0
  13. AWS launches Agent Toolkit with MCP servers and plugins for coding agents

    AWS published the Agent Toolkit for AWS on GitHub, an officially supported set of MCP servers, skills and plugins meant to help AI coding agents build, deploy and manage applications on AWS. The toolkit can be configured from the terminal through the AWS CLI, and has separate install paths for Claude Code, Codex, Cursor, Kiro and fx; the Claude Code plugins are listed on Anthropic's official plugin marketplace. Its AWS MCP Server is described as covering 300-plus AWS services through one authenticated endpoint, with sandboxed script execution, real-time documentation search, and enterprise controls including CloudWatch metrics, IAM condition keys and CloudTrail audit logging. Those capability descriptions come from the project README and are AWS's own account.

    GitHub Trending · Python · 🔥 0
  14. Google DeepMind engineer: AI writes 75% of code, but self-improvement remains far off

    Google DeepMind engineer Haydn Belfield said more than 75% of Google's production code is written by AI, yet about 88% of code changes still require human oversight or review, with fully AI-delegated changes rising from 7.5% to 11.9%. In 1,389 internal Argon agent runs, unsupervised success fell sharply as task complexity rose; on RE-Bench, which contains 74 real machine-learning engineering tasks, Argon solved about half, versus 27% for Gemini 3.7 Flash. The team built a General Capability Index spanning 123 models and 92 benchmarks, finding Gemini capabilities improving about 0.1 GCI point per month with no statistically significant acceleration, and attributed Gemini 4 Argon's slightly above-trend result mainly to more compute and organizational investment rather than AI-driven acceleration. Separately, more than 20 researchers including Geoffrey Hinton, Yoshua Bengio and OpenAI's Jakub Pachocki warned in a paper that automating AI R&D could trigger an intelligence explosion compressing years of progress into months.

    36氪 人工智能 · 🔥 0
  15. NVIDIA NeMo Gym boosts Siemens EDA agent reliability in chip design

    NVIDIA's technical blog describes how its open NeMo Gym library was used to evaluate and improve a chip-design agent. Siemens' Fuse team used NeMo Gym to assess the Siemens Fuse EDA AI Agent as it called characterization tools, checking generated Liberty files against references. The post reports that refining the agent's skills and MCP tool descriptions raised a composite benchmark score from about 55% to 95% on representative standard-cell characterization tasks, while agent turns fell from 155 to 53 and output tokens from roughly 81K to 29K; these vendor-reported figures were not independently verified.

    NVIDIA Technical Blog · 🔥 0
  16. Meta releases Muse Wonder frontier model, lands in Cursor at $4/$20 per million tokens

    Meta released the Muse Wonder model series in the early hours of October 13, 2026, Beijing time, and CEO Mark Zuckerberg and Meta Superintelligence Labs chief AI officer Alexandr Wang detailed the launch on the Cheeky Pint podcast, according to 智东西. The two said the series reaches state-of-the-art results on personal and professional agent tasks and leads coding benchmarks including DeepSWE and SWE-Marathon, as well as finance and legal evaluations — claims attributed to them, with no independent measurement supplied. Zuckerberg said Wonder is larger and more expensive to serve than Muse Spark, so it is offered first in paid subscriptions and also through the Meta model API and OpenRouter, with Muse Wonder Full available to Muse Code subscribers. Cursor's official account then said Muse Wonder is available on its platform, scoring 46.1% on CursorBench at default effort — the highest of any Muse model — priced at $4 per million input tokens and $20 per million output tokens.

    智东西 · 🔥 0
  17. Vercel Labs' skills CLI installs agent skills across dozens of coding agents

    The vercel-labs/skills project appeared on GitHub Trending as a command-line tool for what it calls the open agent skills ecosystem, invoked via npx skills. Its documentation says npx skills add can install skills from GitHub shorthand, full GitHub, GitLab or Azure Repos URLs, any git URL or a local path, while npx skills use generates a prompt without installing and can optionally launch a supported coding agent interactively with --agent. The listed targets include OpenCode, Claude Code, Codex and Cursor, and the project claims support for "75 more" agents, a count that comes from the project itself and was not independently verified. The docs also note anonymous usage telemetry that can be disabled with DISABLE_TELEMETRY or DO_NOT_TRACK, and the project is released under the MIT license.

    GitHub Trending(每日) · 🔥 0
  18. Analysis maps eight differences between personal and enterprise coding agents

    Tmtpost published an authorized article by Chen Chen, a QAX vice president, in his AI Progress Watch series comparing personal and enterprise coding agents across eight dimensions: task scope, context, autonomy and permissions, execution surface, tool integration, security and deployment, quality and determinism, and collaboration and governance. The author argues the real difference is not feature count but constraints: personal agents aim to unlock individual capability, while enterprise agents must wrap model uncertainty in a controllable, trustworthy and auditable framework. The article says leading products are all moving toward the enterprise side, but notes capabilities change quickly with each release and buyers should verify against actual products and deployment plans.

    钛媒体 · 🔥 0
  19. Hands-on: Musk-boosted Grok Bot stumbles on trip booking

    Musk posted 82 Grok Bot-related items on X in a week, and overseas users describe using it to sort email, organize receipts, check subscription bills and even plan trips. Testing it on a Guangzhou–Wenzhou wedding trip, the article's author found Grok Bot first suggested an 8:15 a.m. flight requiring a 4 a.m. wake-up, then pushed to book without completing the requested multi-platform price comparison; despite having a phone app, it cannot directly control other mobile apps, so fare searches happen in a desktop browser and logged-in prices require the user's own authorization. The author also argues Grok Bot overlaps heavily with Chinese products such as Doubao Work and WorkBuddy in task decomposition, always-on cloud-computer execution and multi-agent collaboration, and that its real draw is The X Subscription bundling Grok, Grok Bot, Cursor and X membership for $30 a month, plus Musk's statement that it picks backend models per task, naming Claude Opus 5.5, Midjourney and Suno — though the product offers no model choice or disclosure, leaving the Claude routing unverified.

    虎嗅 AI · 🔥 0
  20. Armature study examines how coding agents pick their tools

    Armature, a developer-tool growth services firm founded in 2026, published an experimental analysis in which Claude Code, Codex and Cursor ran 1,163 prompts across 75 public code repositories, with researchers observing which third-party tools the agents actually adopted. The company says it observed 17,000 tool-selection sessions, but the headline figures it presented come from a verified subset of 5,292 sessions. The three agents chose the same tool in only 42% of test units; Claude Code opted to build a tool itself about 19% of the time versus 10% for Codex and Cursor, and Codex used web search in 94% of sessions against roughly 30% for Claude Code.

    InfoQ 中文 AI&大模型 · 🔥 0
  21. 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
  22. Cursor's Origin opens app marketplace with 20+ developer tool integrations

    Origin now integrates more than 20 apps spanning deployments, CI, code review, security, monitoring and project management, with partners including Cloudflare, Vercel, Netlify, CircleCI, CodeRabbit, Greptile, Semgrep, Socket Security, Sentry and Linear, according to the Cursor changelog. The marketplace is also open to public submissions starting today, so any team building developer tools can publish an app for Origin. The submission flow asks developers to create an app in their namespace, build against the Origin API — authenticating with an app JWT and installation access tokens, receiving webhook events and writing back check runs, pull request comments and reviews — then make it public and submit a slug, suggested tags and a demo video for review before listing.

    Cursor Changelog · 🔥 0
  23. REA goes viral by handing software reverse engineering to AI coding agents

    An article from Guokr, republished by 36Kr and Huxiu, describes the open-source project REA (Reverse Engineer Anything), which connects disassemblers such as Ghidra, IDA and Hopper to AI coding agents like Claude Code, Codex and Cursor through MCP so an agent can investigate a feature in a compiled app and return conclusions with evidence. Citing Star History, the piece says REA gained 78,800 GitHub stars in the week of Oct 4–10, ranking first among projects that week, and argues it lowers to ordinary developers a barrier that earlier tools such as GhidraMCP had already approached. The same article covers developer Brandon Thomas's ArtCraft suite, seven open-source apps he says were built with Claude Opus 5.5 in Rust as alternatives to Adobe products, cites user reports of problems with PSD smart objects and crashes when importing many video clips, and notes that REA removes the clean-room separation between those who decompile code and those who write new code.

    36氪 人工智能 · 🔥 0
  24. SpaceXSI launches The X Subscription bundling Grok, Cursor and X Premium from $8/month

    SpaceX Super Intelligence, formerly SpaceXAI, announced The X Subscription on Oct 12, 2026, putting Grok, Grok Bot, Cursor and X Premium on one bill. Paid tiers cost $8, $30, $100 and $200 a month, with a free tier alongside; Grok and Cursor share one usage pool, Grok Bot and the latest Grok models start at the $30 tier, and existing SuperGrok, Cursor and X Premium subscribers can keep their plans or switch. Cursor said third-party models inside its editor move to API pricing on the new plans, and the company said the offering would reach all users globally over the following days.

    xAI News · 🔥 0
  25. Musk says only three companies have enough coding training data

    Discussing why he acquired AI coding company Cursor, Musk said building truly excellent superintelligence requires vast amounts of training data and that "coding" must be cracked. He said that, as far as he knows, only three organizations have enough coding training data: OpenAI, Anthropic and Cursor, with Google as a marginal fourth. According to Cailianshe (via 36Kr), Musk's SpaceX completed its acquisition of Cursor on Aug. 14 for consideration of about $60 billion; the data claim is Musk's own assertion and no evidence was provided.

    36氪快讯 · 🔥 0
  26. GPUs in the wine cellar: the homelab boom in local AI compute

    A local-AI wave is growing as small developers and hardware hobbyists run high-end GPU machines in basements, attics and home offices for cost, privacy and convenience, cnBeta reports. Former Microsoft employee and repeat founder Gary Fleck built a machine with discounted parts for under $6,000 to train custom models on terabytes of EEG data, saying it beats paying monthly AWS or Azure bills — though cooling his basement required $10,000 to $20,000 in electrical work and HVAC. Local agent platforms such as OpenClaw are helping drive the trend, Mac mini and Mac Studio are popular with agent developers, and Dell says the home-AI hobbyist market is booming. Crazy Egg CEO Hiten Shah runs 18 devices including 14 Mac minis and Mac Studios, with his home office often hitting 85°F (29.4°C), while one YouTube creator runs Qwen-3.8-27B locally on five AMD GPUs in his garage. Some enthusiasts say they want to keep compute in their own hands in case governments restrict AI access.

    cnBeta · 🔥 0
  27. REA tops 110K stars in a week as AI reverse-engineering wave stirs legal debate

    REA (Reverse Engineer Anything) connects reverse-engineering tools such as Ghidra, IDA and JADX to coding agents like Claude Code and Codex through MCP, so a single prompt makes an agent inspect a binary or app package and return findings with evidence. Citing Star History data, the article says the project went from under 10,000 stars on October 6 to more than 110,000 on October 12 — roughly 100,000 stars in six days. It notes that open-source projects wiring AI into reverse-engineering tools, such as GhidraMCP and IDA Pro MCP, already existed, that several reverse-engineering experts call the hype overblown, and that sending decompiled output to model providers plus anti-decompilation clauses in user agreements can raise trade-secret, copyright and contract risks.

    36氪 人工智能 · 🔥 0
  28. REA plugs reverse-engineering tools into Claude Code, Codex and Cursor

    An open-source MCP service called REA (Reverse Engineer Anything) has topped GitHub Trending, with the cited post claiming a one-day gain of 25,784 stars and more than 60,000 in total. REA connects disassembly and reverse-engineering tools to AI coding agents such as Claude Code, Codex and Cursor through a single install command (npx rea-agents setup), letting an agent trace code while a human verifies the evidence; it covers native binaries, Electron apps, .NET programs, Android APKs, firmware, websites and packet captures. The article cautions that the project's public demos use small, curated functions (many only 63 bytes), and that a Quarkslab test of Claude Opus 5 in a sandbox against hardened AArch64 binaries broke no sample, so obfuscation still raises attacker costs and the real moat of apps like WeChat sits on the server side.

    虎嗅 AI · 🔥 0
  29. Open-Source Awesome LLM Apps Collection Tops GitHub Python Trending

    The open-source repository Shubhamsaboo/awesome-llm-apps has hit GitHub's Python trending list, bundling 100-plus AI agents, agent skills and RAG apps under an Apache-2.0 license that the maintainers say can be cloned, modified and even sold. The project states that every template is hand-built and tested end to end and works with Claude, Gemini, GPT, DeepSeek, Llama, Qwen and other models; its Agent Skills can be installed into coding agents such as Claude Code, Codex and Cursor with a single npx command. The repo organizes templates and step-by-step tutorials by category, including starter agents, advanced agents, always-on agents, multi-agent teams, voice agents, MCP agents and RAG pipelines.

    GitHub Trending · Python · 🔥 0
  30. Composio's awesome-claude-skills hits GitHub trending with 1,000+ skills

    Composio's awesome-claude-skills repository on GitHub collects more than 1,000 Claude Skills and plugins spanning document processing, development and code tools, data and analysis, business and marketing, writing, creative media, collaboration and security, and says they work across Claude.ai, Claude Code, Codex, Cursor, Gemini CLI and Windsurf. According to the repo, a Skill is a reusable instruction package containing a SKILL.md file with YAML frontmatter and Markdown instructions, loaded progressively: roughly 100 tokens per skill for name and description at session start, with the full body (typically under 5,000 tokens) loaded only when the agent judges it relevant. The list also promotes Composio's MCP Gateway, a single MCP endpoint for 1,000+ integrations with built-in authentication, team access controls and audit logs, plus a connect-apps plugin that lets Claude send emails, create issues and post to Slack; its README credits Anthropic with introducing the format in October 2025 and releasing it as an open standard in December 2025.

    GitHub Trending · Python · 🔥 0

← PreviousNext →

Experience and discussion from the community

Share my Cursor experienceAsk about Cursor

ai-website-cloner-template: Give an AI coding agent a URL to recreate a website as a clean Next.js app.

What problem it solves Web teams and developers can need to rebuild an existing site in a modern codebase when migrating platforms, recovering lost source code, or learning how a production site is constructed. This template gives an AI coding agent a repeatable workflow for recreating a site as an editable Next.js application while comparing its appearance and behavior with the source. Key featur…

github.comhttps://github.com/JCodesMore/ai-website-cloner-template

WrenAI: An open-source generative BI engine that gives AI agents a governed semantic layer and AI context layer for turning business questions into SQL and dashboards.

What problem it solves AI agents often produce plausible SQL without the business definitions, approved joins, units, and examples needed to make results trustworthy. Teams also need a reviewable way to manage that context and turn governed answers into shareable dashboards across existing data sources. Key features Governed semantic and context layers — Business meaning is represented through the…

github.comhttps://github.com/Canner/WrenAI

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

skills: Portable instruction sets that teach AI agents how to use NVIDIA software for end-to-end workflows.

What problem it solves AI agents need product-specific instructions to use NVIDIA software reliably across physical AI, robotics, simulation, CUDA-X libraries, RAG, and platform workflows. The catalog centralizes these skills while keeping them maintained in their respective product repositories and synchronized through an automated pipeline. Key features Agent-discoverable skill catalog — The NVI…

github.comhttps://github.com/NVIDIA/skills

GitNexus: A code intelligence engine that indexes a codebase into a knowledge graph of symbols, calls, dependencies and execution flows.

What problem it solves Developers and coding agents need to understand how code is connected before making changes. GitNexus provides a graph-based view of symbols, callers, dependencies and execution flows to support code discovery, impact analysis and refactoring. Key features Graph-based code intelligence — Index a codebase as a knowledge graph covering symbols, calls, dependencies and executio…

github.comhttps://github.com/abhigyanpatwari/GitNexus

OpenViking: An open-source context database for AI agents that organizes knowledge, memory, and skills in one filesystem.

What problem it solves Agent memory is often opaque: stored context cannot be easily inspected or understood. OpenViking addresses this by organizing knowledge, memory, and skills in a browsable virtual filesystem, with summaries that help agents identify relevant context before reading full files. Key features Unified context filesystem — Knowledge, memory, and skills share one filesystem address…

github.comhttps://github.com/volcengine/OpenViking

compound-engineering-plugin: AI coding-agent skills that structure engineering work into a repeating loop of planning, execution, review, and reusable learning.

What problem it solves Traditional development accumulates technical debt and leaves important knowledge scattered, forcing later changes to rediscover context. The plugin addresses this by turning each engineering cycle into a structured workflow and writing durable learnings into artifacts that subsequent cycles can use as grounding. Key features Structured engineering loop — A six-step cycle mo…

github.comhttps://github.com/EveryInc/compound-engineering-plugin

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

chrome-devtools-mcp: An MCP server and CLI that let coding agents control and inspect a live Chrome browser.

What problem it solves Chrome DevTools for agents (`chrome-devtools-mcp`) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser. Both give your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis. Key features Browser control and inspection — Give coding age…

github.comhttps://github.com/ChromeDevTools/chrome-devtools-mcp

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

gentle-ai: The deterministic engineering environment for the AI agent you already use.

What problem it solves AI coding agents lose context between sessions, so the same decisions get re-explained and nothing about the project is remembered. They also lack a shared workflow and evidence, leaving the human to read every line to confirm what was done. This project adds memory, a workflow, and evidence to agents you already have. Key features Persistent project memory with Engram — Eng…

github.comhttps://github.com/Gentleman-Programming/gentle-ai

t3code: An agent harness control surface for controlling agents on your machine.

What problem it solves Developers need a consistent way to control locally configured coding agents across mobile, web, and desktop environments. T3 Code addresses this by providing multiple client applications, support for several agent providers, and remote access to a local server. Key features Control from mobile, web, and desktop — Use the mobile, web, or Electron-based desktop application to…

github.comhttps://github.com/pingdotgg/t3code

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

agents: Plugins, agents, skills, and commands for AI coding tools

What problem it solves Coding tools use different component formats, model names, permissions, and discovery rules. Contributors need a shared way to write reusable plugins, agents, skills, and commands once while producing compatible artifacts for each supported harness. Key features Multi-harness component support — One collection of plugins, agents, skills, and commands can be used across Claud…

github.comhttps://github.com/wshobson/agents

hallmark: A design skill for Claude Code, Codex, Cursor and OpenCode that refuses to look AI-generated.

What problem it solves AI coding assistants can generate interfaces with visual and structural patterns that feel machine-made, such as repetitive headings, empty sections, misplaced heroes, and forms that do not complete their intended action. Hallmark applies design constraints, product-aware page structures, browser-based linting, and fresh-context review to help generated interfaces look desig…

github.comhttps://github.com/Nutlope/hallmark

codex: A coding agent from OpenAI that runs locally in your terminal.

What problem it solves Developers need a coding agent that can work directly from their local development environment without requiring a separate desktop application. The project provides installation paths for terminals, IDEs, and desktop use, along with authentication through a ChatGPT plan or an API key. Key features Local terminal coding agent — Run Codex CLI locally on your computer to use a…

github.comhttps://github.com/openai/codex

agent-beacon: An open-source memory layer for AI coding agents that learns from your work across multiple harnesses.

What problem it solves Agent workflows, corrections, debugging patterns, and repository conventions often disappear when a session ends or remain trapped inside one coding tool. Beacon addresses this by capturing session history across harnesses and turning useful findings into reusable memory for future agents. Key features Cross-harness session history — Capture session history from Claude Code,…

github.comhttps://github.com/Asymptote-Labs/agent-beacon

ds-harness-remote: Access your local Harness instance remotely from the web, a PC, or a mobile device.

What problem it solves DeepSeek Harness workspaces, tools, and project setup normally remain tied to the computer running the Harness instance. The project addresses the need to continue using that environment from another computer, phone, or browser without requiring a public listening port or public IP on the Host. Key features Remote workspace access — Open local workspaces from a web browser, …

github.comhttps://github.com/liguobao/ds-harness-remote

plugins: Official plugins for developer tools, frameworks, and SaaS products.

What problem it solves Developer workflows often need consistent access to external tools, reusable agent instructions, and service-specific procedures. This repository packages those capabilities as standalone plugins with standardized manifests and supporting rules, skills, and MCP server definitions. Key features Developer workflow assistance — Plugins support tasks such as code review, reposit…

github.comhttps://github.com/cursor/plugins