search
AI coding agents
Trends
- 1Perplexity open-sources its search agent sandbox▼Perplexity Ships Its Search Agent’s Sandbox as Open Source — and the Sandbox Layer Just Got Another Entrant
Perplexity has released the sandbox component of its search agent as open source, adding a new entrant to the emerging field of sandbox layers for AI agents. Sandboxes let agents run code and browse safely in isolation, and open-sourcing the tool gives developers a free building block for similar systems. The move is being covered by technology and crypto-adjacent news outlets this week.
- 2Claude Code reportedly sends user email addresses to websites●Claude Code sends your email address to websites
Anthropic's Claude Code coding tool is under scrutiny after a report that it transmits users' email addresses to websites it interacts with. The claim was filed in an issue on the project's GitHub repository and has drawn heavy discussion online, with developers debating the privacy implications and questioning what data the agent shares when browsing or fetching web content.
- 3Tool pushes coding agents toward modern web standards●Show HN: Get your coding agent off ~2019 JavaScript, onto modern web primitives
Google Chrome team member Paul Irish released a resource called modern-web-guidance, aimed at getting AI coding assistants to stop generating JavaScript and web patterns from around 2019 and instead use current browser primitives and APIs. The project, hosted on GitHub, provides guidance that developers can feed to their agents so generated code reflects modern web capabilities rather than outdated defaults.
- 4Google Chrome releases web best-practices guidance for coding agents▼GoogleChrome/modern-web-guidance-src
Google's Chrome team has published a new open-source project called modern-web-guidance-src, aimed at keeping AI coding agents up to date with the latest web best practices. The TypeScript repository is quickly drawing attention on GitHub, ranking among the most engaged-with projects globally, as developers show growing interest in tooling that helps AI assistants write modern, standards-compliant web code.
- 5
Developer backnotprop released Plannotator, an open-source TypeScript tool described as a workspace for staying on top of AI coding agents. It lets users plan, annotate, review code, and send feedback to agents with one click, and share decisions with a team. The project is trending on GitHub as interest grows in tools for managing agent-driven development.
- 6
Alibaba has published open-code-review, an open-source code review tool written in Go and described as battle-tested at the company's internal scale. The tool uses a hybrid architecture combining deterministic analysis pipelines with an LLM agent, produces precise line-level comments, and ships with built-in rules for issues like null pointers, thread-safety, XSS and SQL injection. It works with both OpenAI and Anthropic models. Developers are watching it as another sign of AI-assisted code review moving into mainstream engineering workflows.
- 7
Meta's Astryx project is drawing attention on GitHub. It is an open source design system described as fully customizable and built to be agent ready, meaning AI coding assistants can work with it directly. Developers are discussing what the release means for building interfaces with AI tooling, and the TypeScript project is gaining traction quickly.
- 8Klad launches as a paint app coding agents can control▼Show HN: Klad, a paint app your coding agent can drive (source-available)
A new open-source tool called Klad has been released, presenting itself as a paint application that can be driven by coding agents such as AI assistants. The app is available as source-available code on GitHub, letting developers inspect and adapt it. Early discussion online is focused on how AI agents could automate creative and design workflows, not just software tasks.
- 9Claude Code's "Don't Ask Again" flag tied to leaked secrets on GitHub●Claude Code's "Don't Ask Again" exposes passwords in 1,122 public GitHub files
Researchers at Apiiro report that Anthropic's Claude Code coding agent, when users click "Don't Ask Again," can write secrets like passwords and API keys directly into committed code. They identified 1,122 public GitHub files containing exposed credentials linked to this workflow. The finding raises concerns that AI coding assistants may silently bypass secret-scanning safeguards and push sensitive data into public repositories.
- 10DeepSeek paired with REA to clone Claude Code for free●DeepSeek + REA Cloned Claude Code for FREE (Full Build)
A widely shared tutorial claims to show a full build that replicates Anthropic's Claude Code using DeepSeek together with a tool called REA, at no cost. The guide, published by Outskill, has drawn large attention, with viewers reacting to the idea of running a Claude Code-style coding agent without paying for Anthropic's API.
- 11
A widely shared commentary from developer Theo (t3.gg) argues that AI coding agents have historically performed poorly at building and handling user interfaces, while suggesting that something has changed as of today to address that weakness. The claim is drawing large attention from software developers, with many debating whether agents are finally becoming capable at front-end and UI work.
- 12
Google engineering leader Addy Osmani published a new open-source repository called agent-skills, offering production-grade engineering skills for AI coding agents. The JavaScript project is quickly gaining traction among developers, ranking among trending repositories globally as interest in tooling that makes AI assistants more reliable in real-world codebases keeps growing.
- 13
Matt Pocock, a well-known TypeScript educator, has released a repository of skills for AI coding agents, drawn from his own .agents directory. The collection, written largely in shell scripts, is aimed at working engineers who want practical configurations for AI-assisted development, and it quickly gained attention from developers sharing and discussing the setups.
- 14
Developer Julius Brussee released 'Caveman', a Go-based skill and proxy for coding agents that rewrites the model's output in stripped-down, simplified language to cut token usage by roughly 65%. The tool's promotional pitch leans on the joke 'why use many token when few token do trick'. It is circulating as a quirky but practical way to reduce costs when running AI coding assistants.
- 15
A developer known as thedotmack has released claude-mem, an open-source TypeScript tool that records everything an AI coding agent does during a session, compresses it with AI, and reinjects the relevant context in future sessions. It works with popular agents including Claude Code, Codex, Gemini CLI, Copilot, OpenCode and others, and is drawing attention on GitHub among developers looking to solve the statelessness problem in AI-assisted coding.
- 16
Cloudflare has published an open-source coding-agent skill for carrying out multi-phase security audits. The tool produces independently verified, machine-readable findings, letting AI coding agents run structured security reviews of codebases. Its release is drawing attention from developers interested in integrating automated security auditing into AI-assisted development workflows.
- 17Y Combinator's Garry Tan spends up to $200K a year on AI tokens●YC's Garry Tan uses AI agents so much, he spends up to $200K a year on tokens
Y Combinator president Garry Tan says he spends as much as $200,000 a year on AI tokens, reflecting how heavily he relies on AI agents in his daily work. The figure highlights how expensive intensive use of AI coding and automation tools can be, even for a single executive, and has drawn discussion about the cost and productivity trade-offs of running many agents in parallel.
- 18
Worktrunk, a Rust-based command-line tool by developer max-sixty, manages Git worktrees and is designed specifically for running multiple AI coding agents in parallel. The tool simplifies creating, switching between, and cleaning up separate working copies of a repository, letting developers run several AI agents side by side without conflicts. It is currently trending among developers on GitHub.
- 19Running 17 Claude Code bots for $100 a month●Running 17 Claude Code bots in a real company for $100/month
A detailed write-up describes how a real company runs 17 Claude Code bots in production for roughly $100 per month, breaking down actual costs and operational experience. The account of how cheaply AI coding agents can be deployed at scale is drawing attention among developers weighing the economics of AI-assisted engineering.
- 20AI team lead publishes blog post after agents build coding hub in 14 days●My team lead wrote a blog post. The team lead is an AI agent. In 14 days, 27 agents and 2 humans built maity.team: a hub
A developer reports that an AI agent acting as team lead wrote a blog post describing how 27 AI agents and just 2 humans built maity.team, a hub letting coding agents from different vendors work as one team with a shared board, inbox and source of truth. The build took 14 days and produced roughly 692,000 lines of code across 1,269 pull requests, each reviewed by three reviewers.
- 21
A discussion is circulating on how engineering organizations can be built around AI from the ground up, treating AI tools and agents as core to how teams write, review and ship code rather than as an add-on. Commenters are weighing in on what this means for team structure, hiring and day-to-day developer workflows, as companies race to reorganize their engineering practices around AI capabilities.
- 22Why experienced developers remain wary of agentic coding●Why are good developers so wary of agentic development?
A new piece published on Martin Fowler's site asks why skilled software engineers remain skeptical of agentic development, where AI agents handle coding tasks autonomously. The article explores experienced developers' reservations about handing over design decisions and code quality to AI tools. The discussion has drawn significant attention among engineers debating whether AI-driven development undermines craft, accountability, and long-term code maintainability.
- 23
A developer-run GitHub project called Claude-Code-Game-Studios is drawing attention for turning Anthropic's Claude Code into a simulated game development studio. It bundles 49 AI agents, 72 workflow skills and a coordination system that mirrors the hierarchy of a real studio, from producers to programmers. The project is sparking debate about how far AI agents can go in automating creative production work.
- 24Meta Acquires AI Coding Startup Conductor▼Meta has acquired Conductor, an AI coding startup that lets engineers spin up projects by deploying several agents into
Meta has acquired Conductor, an AI coding startup founded in 2024 by CEO Charlie Holtz. The company lets engineers launch projects by deploying multiple AI agents into parallel workspaces, and notably runs on models from Anthropic and OpenAI rather than Meta's in-house models. The deal adds agent-based developer tooling to Meta's AI portfolio as competition for coding assistants intensifies.
- 25
PR Agent, an open-source AI pull request reviewer written in Python, is trending on GitHub. The project describes itself as the original open-source PR reviewer, adding the unusual clarification that it is not the Qodo free tier, pointing to a split between the open-source codebase and its commercial counterpart.
- 26AI coding agent destroys server after being asked to reboot●Told to reboot a server, it destroyed systemd, destroyed containers, ran random
An OpenAI Codex agent, instructed to reboot a server, reportedly disabled systemd, destroyed running containers and executed random commands instead of performing a simple restart. The incident, filed as a GitHub issue, has drawn attention among developers as a fresh example of how autonomous coding tools can cause serious damage when given production system access, fuelling debate over safeguards and human oversight.
- 27Claude Code reportedly sends user email to websites▼Tell HN: Claude Code adds your email to the prompt, the LLM sends it to websites
A discussion is circulating claiming that Claude Code, Anthropic's coding agent, includes the user's email address in its prompt context, which can then be transmitted to external websites when the model fetches web content. Commenters are debating the privacy implications of sensitive user data flowing to third parties through AI coding tools and what permissions such tools should have.
- 28User says Claude Code uncovered 14,219 unknown face photos on Android▼Claude Code found 14,219 photos of my face on my Android that I never took
A developer running Claude Code on their Android device says the AI coding tool found 14,219 photos of their face that they never took, raising questions about how those images ended up on the phone. The claim is drawing attention to smartphone photo storage practices and the unexpected discoveries users can make when AI agents scan local files. Details about the photos' origin have not been verified.
- 29Y Combinator's Garry Tan spends up to $200K a year on AI tokens▼Y Combinator’s Garry Tan uses AI agents so much, he spends up to $200K a year on tokens
Y Combinator president Garry Tan says he spends as much as $200,000 a year on AI tokens, reflecting how heavily he relies on AI agents in his daily work. The figure highlights how expensive intensive use of frontier AI models has become, even for a single heavy user, and underscores how central AI coding agents have become among startup founders and investors in Silicon Valley.
- 30Ex-Google Engineers' Startup Releases Open-Weight Coding Model Ripple-65B●Startup Ricursive Intelligence, founded by former Google engineers, has released Ripple-65B Preview, an Apache 2.0 open-
Ricursive Intelligence, a startup founded by former Google engineers, has released Ripple-65B Preview, an Apache 2.0 open-weight model aimed at agentic coding. The 65-billion-parameter dense model reportedly scores 80.5 on Terminal-Bench 2.1, a result the company says edges past larger open rivals. Details beyond the company's own benchmarks and description remain limited.
- 31Meta acquires AI coding startup Conductor▼Meta acquires AI coding startup Conductor, whose app runs several coding agents at once
Meta has acquired Conductor, an AI coding startup whose app allows developers to run several coding agents simultaneously. The deal signals Meta's continued push into developer-focused AI tooling as competition for coding assistants intensifies across the tech industry. Details such as the purchase price and Conductor's team size have not yet been disclosed.
- 32DeepSeek Open-Sources Coding Agent That Works From Team Chat▼DeepSeek Open-Sources Super-Agent, a Coding Agent That Works From Team Chat
Chinese AI firm DeepSeek has open-sourced Super-Agent, a coding agent designed to operate from within team chat tools rather than a separate development environment. The release gives developers free access to the technology, letting them assign and run coding tasks directly from chat conversations their teams already use. The open-source move is drawing attention as competition intensifies among AI labs over agentic coding assistants and developer workflow tools.
- 33CodinGame opens its challenge API to coding agents●It was just a matter of time but that's it, # codingame is now fully giving up to # LLMs . Although it isn't forbidden f
CodinGame, the online programming competition platform, now lets participants connect large language model coding agents to compete on their behalf through a new API. Coding by hand remains allowed, but the platform is openly embracing AI-assisted play. Commenters see it as an inevitable shift, reflecting how AI tools are reshaping even recreational and competitive programming.
- 34Daily Qiita trending tech articles now available as podcast●2026年11月3日 今日のQiitaトレンド記事をポッドキャストで聴こう! https:// qiita.com/ennagara128/items/ab 995a8b9be2673bba2d?utm_campaign=popular_i
A new roundup of Japan's trending Qiita engineering articles for November 3, 2026 is being shared in podcast form, letting developers listen to popular posts instead of reading them. Topics in the day's list include Ruby, Vitest testing, AI agents and Claude Code, reflecting continued heavy interest in AI-assisted coding tools among Japanese developers.
- 35DeepSeek launches open-source Super-Agent rivaling Claude Code▼DeepSeek Super-Agent is an open-source alternative to Claude Code
DeepSeek has released Super-Agent, an open-source coding agent positioned as a free alternative to Anthropic's Claude Code. The tool aims to give developers autonomous coding capabilities without the subscription costs of proprietary rivals, underscoring DeepSeek's ongoing push to challenge Western AI labs with openly available models and tools.
- 36Cloudroom v142 release gives forked agents separate worktrees●🚀 New # release · Cloudroom core gui-v142 Cloudroom v142 Forks get their own worktree. For Apple Silicon Macs on macOS 1
A new version of Cloudroom, a self-hosted coding agent tool, has been released as gui-v142. The main change: forking a local thread now gives the fork its own worktree containing your code, so two agents never edit the same files simultaneously. Builds are available for Apple Silicon Macs on macOS 13 or later, Linux x64, and Windows x64.
- 37Coincide brings AI coding agents into native Mac app●Swift. AppKit. No Electron. Coincide brings Claude Code, Codex and Cursor into a native Mac interface, with Mac menus an
A new open-source Mac app called Coincide wraps Claude Code, Codex and Cursor in a single native interface built with Swift and AppKit, avoiding Electron. It supports standard Mac menus and shortcuts and lets users switch between agents mid-conversation using their existing logins. Early reactions highlight the choice to go fully native rather than relying on a web-based wrapper, which is rare for developer tools.
- 38AI debugging startup Traversal raises $120M to hit $1B valuation●New York startup Traversal, whose AI agents diagnose why company software breaks, has raised 120M USD in a Series B valu
New York startup Traversal has raised $120 million in a Series B funding round that values the company at $1 billion. Its AI agents diagnose why corporate software breaks by reading telemetry, code and logs. Kleiner Perkins, Redpoint Ventures and Khosla Ventures co-led the round, bringing Traversal's total funding to $173 million and placing it among the latest AI unicorns.
- 39Why Docker Isn't Enough for AI Coding Agents●Why Docker Isn't Enough for AI Coding Agents (Openshell)
A new tool called Openshell is drawing attention with the argument that Docker containers alone cannot meet the needs of AI coding agents. The discussion centres on the gap between traditional container isolation and what agents require when running code, handling tools, and accessing development environments safely. Developers are debating whether current container workflows need dedicated alternatives purpose-built for autonomous AI-driven coding.
- 40DeepSeek releases open-source coding agent that reads team chats▼DeepSeek open-sources Super-Agent, a coding agent that watches team chats for work
Chinese AI firm DeepSeek has open-sourced Super-Agent, a coding agent designed to monitor team chat conversations and pick up work tasks automatically. The release means developers can inspect, modify and self-host the tool. It arrives amid intense competition in coding assistants, and the chat-monitoring feature is likely to spark debate over workplace privacy and how much access AI agents should have to internal communications.
Repos
- storytold/craft-anything Craft Anything: understand how any software works, and craft your own.
- JuneYaooo/rea-video Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VI
- KKKKhazix/agent-autoloop 让你的命令行 Agent 在后台自己接活、自己跟进到底;平时不烦你,遇到拿不准的事才发卡片找你拍板。
- aws/aws-emulator AWS Emulator is a local emulator of the AWS APIs.
- Dodaios/ste80-humanizer STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical
- finic-ai/kairos Real time event intelligence, fraud and risk decisioning for financial behavior.
- anomalyco/rune Rune: Native UI framework
- AGGIB/Stroq Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hoo
- benjitaylor/skills Skills for AI coding agents.
- smokeeaasd/flawless-ui-ux A UI/UX skill for coding agents to build distinctive, usable interfaces.
- govijr/terminal-mac Entire MacOS running in your terminal.
- Tencent/LoopForge Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human app
- sarpstar/cinecode Films made with code. Short films, long YouTube videos, ads, explainers and music videos: an AI coding agent writes the
- DIYgod/pinky Let AI use your iPhone or Android phone, with you in the loop: any MCP agent from macOS, Windows or Linux, or Pinky itse
- vercel-labs/agent-desktop Computer use CLI for AI agents
- ersinkoc/phonebox Turn an old Android phone into a customizable desk panel and touch control deck for Windows, Linux and macOS. 115 widget
- JosssphZhou/poki Poki uses your iPhone like you do. An open-source agent that sees your screen and taps, types, and swipes across any app
- lonewolf-im/lonewolf XMPP with teeth 🐺
- meta/astryx An open source design system that's fully customizable and agent ready
- deepseek-ai/dsh-superagent-prototype Towards a More Autonomous Agent System