#claude-code

2026-09-10 Show HN: Self-hosted company OS, Claude Code and Codex agents in departments S Hi HN, I am Dimitris. This is a company OS that I built and use to run my business and anyone can install it and self host it for free. Think of it as Claude Code, Cowork and the cloud sessions in one self hosted application. It is a Multi-tenant application by design where many people can collaborate on the company agents with 4 different modes of collaboration, and it runs with your Anthropic or OpenAi subscription or even with local models. Every agent can run on Claude Code or Codex CLI running as a persistent process on your server in a kernel sandbox (bubblewrap) with network isolation always on (pasta), with its own workspace, memory, schedules and tools. The same agents can also be configured to run identical on any remote computer through one outbound WebSocket (no inbound ports, no VPN needed). The agent already have lots of built in features, as an example they can answer and place phone calls through Twilio or your own Asterisk, they can edit videos and excel, word, ppt files and preview them directly inside the chat with collabora and many more. Trying it is one install script and a docker compose, no signup. The license is Fair Source, all the code is public and self hosting is free up to 5 users. 1.6.0 went out today. AI Disclaimer: large parts of OtoDock are written using OtoDock itself, running Claude Code. I would love people to read the code, take a look in the sandbox model, and tell me what would stop you from running this on your own hardware. GitHub: https://github.com/OtoDock/oto-dock Website: https://otodock.io

2026-09-10 Show HN: Type.com: Multiplayer Codex/Claude in the cloud for non-tech use cases A Hey HN, I'm Komran, the CTO and cofounder of type.com. We're launching today. I've been describing type as "the IDE for non technical people." It allows you to build really cool shit without having to worry about maintaining the perfect local dev environment. Everything is cloud first by default. No fumbling with handoff flows or anything weird like that. Every thread is backed by a persistent sandbox VM so you don't even have to worry about git worktrees if you're doing something git backed. You can start work from claude, codex, slack, or email and then push it into a shared session in Type where your whole team can co-prompt. Since our "meta-harness" is a wrapper of codex-cli and claude code, you can connect your existing subscriptions. Because we're a multiplayer product we had to make sure that we only bill the subscription for messages authored by that user. If Alice has a subscription and she starts a thread with an agent, she will have her subscription used. If Bob comes in and add their own prompt but Bob does not have a subscription, they will be billed against their type usage. We don't charge any margin on tokens. Even with how early the product is, our customers love us and prefer us to using claude code. If I had to say our advantages over claude tag/claude cowork it would be these: * You can switch models/harnesses anytime, you aren't locked into a single provider. Creating a custom internal app/artifact is better on type because we handle internal hosting, RBAC, version control, dev/prod environments, and even the ability for your apps to talk to your type integrations. Sharing an internal app is very akin to sharing a google doc. * It's just claude code and codex under the hood. In general it should work very similar to how codex and claude code work * At my last company, halp.com (acquired by Atlassian) we invented the term "Slack-first" because we knew that people loved doing work without context switching. Type is great in slack. Each slack channel maps to a public or private "Space" which has access read only or read/write access grants to integrations. Each space has a default harness, model, and effort level built in. So you can use your subscriptions all from slack. * Our CLI allows you to get the best parts of type even when you're working in single player mode on your local machine. The type-cli lets you push your local session up to type so that other can take a look at it. It can also push up a doc for collaborative editing, and even reuse the same integrations that you've been given access to on type locally. You can sign up today at https://type.com. You get $100 worth of credits to mess around with it. It's been really fun building this. Competing with the likes of grok bot, codex, and claude cowork has been really fun, but I think that they are still very much in the personal assistant, single player mode. Each person has to set up the same integrations, skills and automations need to be created all from scratch, and every frontier's product is gonna make you be locked in to their model.

2026-09-21 trustfuture/investigation-video-skill B 不露脸商业/消费调查长片的完整生产流程：一句话出 10 分钟成片，以 Claude Code skill 形式开源（TTS 逐字时间戳、素材覆盖、Remotion 拼贴、闪避混音、封面与八平台文案）

2026-09-19 op7418/guizang-product-video-skill B 归藏 product video skill：复用真实产品组件和设计语言，用代码制作软件更新宣传片。包含分镜文案、原创配乐、动作音效与视频渲染，支持 Claude Code 和 Codex。

2026-10-14 glmn-ai/vibereceipt A Print a store receipt for your AI coding: tokens, what they'd cost at API prices, and how many times the agent said "You're absolutely right". Claude Code, Codex, OpenCode. 100% local.

2026-08-25 ADScanPro/Claude-AD A Active Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS ESC1-17, DCSync, ACL abuse, NTLM relay, delegation), OPSEC telemetry and DORA/NIS2/ENS mapping. Drives netexec, impacket, certipy, bloodyAD, BloodHound CE.

2026-10-19 paulmil11/decks A Agent-first slide decks: comment under a slide, and your coding agent (Claude Code or Codex) makes the change and replies on the slide.

2026-10-05 obie/auto-handoff A Claude Code plugin that writes a handoff document before an idle session's prompt cache goes cold

2026-10-04 cablate/ctx-handoff-mod A Claude Code mod: auto handoff to a fresh conversation when context hits a threshold, keeps the prompt cache warm while you're away

2026-10-15 Myeongseok-Kang/claude-bulkhead A Keeps parallel Claude Code sessions from killing each other's servers, fighting over ports, freezing the machine, or switching a branch under each other.

2026-10-09 MK27MK/loadout A Claude Code harness manager: switchable profiles, scope provenance and on/off for every harness element

2026-10-05 alexknowshtml/claude-auto-handoff B Claude Code mod: hand a long session off to a fresh one with a structured brief, instead of auto-compacting

2026-10-04 amigoer/ccprogress A Live step-by-step progress bar for long Claude Code sessions, in the terminal and the Desktop app

2026-09-17 donvito/agent-monitor B Visualize your Codex and Claude Code subagents. Advanced traces view, tokens breakdown, and cost usage is also supported.

2026-10-14 lcoutodemos/chums B Talk to Claude Code and Codex agents from an Apple Watch and an iPhone. Each agent is a character on the watch.

2026-09-20 kishormorol/cli-faq-shortcuts B An Agent Skill that turns the asks you keep typing into short commands, mined from your own Claude Code and Codex history. Works in Claude Code, Codex and Cursor.

2026-09-19 karanb192/cache-tax B Keep Claude Code’s prompt cache warm during breaks and show the estimated cost before a cold send.

2026-10-19 harshpreet931/harshpreet-hand B I gave Claude Code 120 pages of my handwritten college notes. It gave me back my handwriting as a real font, in 66 minutes for $13.68.

2026-10-05 dominikmartn/leitstand B A control room above your Claude Code prompt: background jobs, disk and context at a glance. German for control room.

2026-10-29 zamirka/wfwatch B Live terminal view of Claude Code workflows, subagents and sessions

2026-10-04 click6067-ship-it/token-tv B Turn a $5 AliExpress clock into a physical AI usage dashboard (Claude, Codex, multi-account). Zero-flash where possible.

2026-10-29 SunandBean/paper2video B Claude Code skill: arXiv paper to a narrated, fact-checked explainer video (Three.js scenes, local Kokoro TTS, ffmpeg).

2026-10-04 briangtn/claude-gfm-render B Claude Code mod: GitHub Flavored Markdown alerts, task lists, strikethrough and Mermaid diagrams in the transcript

2026-09-30 humaedihume/kantor-agent C Kantor Agent: kantor 3D tanpa konfigurasi yang menampilkan Claude Code & subagent-nya bekerja (plugin Claude Code)

2026-10-29 win4r/video-director B A Claude skill for directing, building and verifying code-rendered videos (HTML/Canvas → MP4): principles, gated workflow, QA scripts and evals.

2026-10-29 bassnova42/arch-diagram-skill B RokoAI arch-diagram: a Claude Code & Codex skill that turns any repo or article into an animated architecture diagram (HTML / PNG / MP4 / GIF / Mermaid) with a live trace log

2026-09-24 muratcakmak/jev-guard B Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.

2026-10-06 joshhu/claudebigimage B 在 Claude Code 中以大尺寸預覽貼上的圖片（fork 自 claude-image-view）

2026-10-08 imajij/do_waqt_ki_roti C Claude Code skill: AI hiring partner for internship hunts. Profile audit, truthful per-job resume tailoring, ATS scoring, browser-filled applications, outreach and tracker.

2026-11-09 danyuchn/claude-work-mode C Session work modes for Claude Code: /work-mode auto | out | wrap, with optional gates

2026-10-01 kyroco/vitalaize C A wall screen for Claude Code and Codex sessions and your GitHub builds

2026-09-19 kunchenguid/compact-adviser C "Work appears completed or recorded. Run /compact to save tokens."

2026-10-13 a-samy-consultancy/claude-code-setup-kit C Turn Claude Code into a disciplined build team in 10 minutes. One file, any project. Built by Abdo Samy.

2026-09-18 thaofvn-coca06/funnel-mkt D He thong 8 AI agent chay theo mo hinh banh da de xay pheu marketing thu lead. Viet cho Claude Code, tieng Viet, VND.

2026-11-05 duyunzhoudyz/dyz-gongwen-skills 未评级公文写作 Skills｜AI 公文写作助手：防编造、守保密、GB/T 9704 一键排版，覆盖 22 种文书，支持 Claude Code / Codex / Cursor

2026-11-05 garrytan/gstack 未评级 Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

2026-11-04 nateherkai/claude-code-mods 未评级 Four Claude Code mods: Cache Keeper, Recording Mode, Goal Meter, and Collision Guard

2026-11-03 michael-denyer/pstack-claude 未评级 Claude Code, Codex, Copilot, Pi, OpenCode, Muse, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

2026-11-02 mattabate/life-distributable 未评级 A personal agent that works on your life around the clock, on a Mac you own. One sentence to Claude Code installs it.

2026-11-01 Orkas-AI/Orkas 未评级 Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.

2026-10-30 francize/my-better-claude 未评级 Plugins and mods that make Claude Code better: work with the local Codex CLI, watch the prompt cache, preview pasted images.

2026-10-30 ray-amjad/claude-code-mods 未评级 Claude Code mods: panes, bands, prompt guards, secret handling and memory tools

2026-10-30 Donchitos/Claude-Code-Game-Studios 未评级 Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

2026-10-29 davidondrej/cloudroom 未评级 Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud.

2026-10-29 robonuggets/ribbon 未评级 A slim band above your Claude Code prompt: usage left, reset times, and whether the prompt cache is warm or cold. By Jay E | RoboNuggets

2026-10-28 duyunzhoudyz/gongwen-skills 未评级公文写作 AI Agent Skills：懂规矩、懂单位、懂角色；不编造、守保密、帮你做减法。覆盖 22 种文书类型，支持 Claude Code、Codex、Cursor 等主流工具，防编造、懂国标格式、适配机关事业单位和医院高校国企。

2026-10-27 savannahfeder/agentbox 未评级 A desktop GUI for running dozens of Claude Code and Codex agents in parallel, each in its own git worktree. Answer them like email, or use the board view. Free, open source, on the plan you already pay for.

2026-10-27 whyashthakker/awesome-claude-code-mods 未评级 Collection of 100+ mods you can use with Claude Code.

2026-10-25 EricJujianZou/rederive 未评级 Learn a codebase by re-deriving its design decisions yourself. A Claude Code skill.

2026-10-24 Show HN: Claude Code session-resumption plugin 未评级 GitHub sofumel/claude-handoff-revive ★7 · Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.

2026-10-23 Gilvt-WTJ/gilvt 未评级 Native macOS terminal for running, monitoring, and reviewing parallel Claude Code and Codex sessions.

2026-10-23 Zafer-Liu/claude-super-sidebar 未评级 A visual sidebar for Claude Code and Codex: agent trees, live status, and conversation task flows.

2026-10-23 brushknight/agents-deck 未评级

2026-10-23 Show HN: Skillstore – Expert skills your coding agent fetches as it works 未评级 TLDR: Connect once to your favorite coding agent. Claude Code and Codex find and load relevant skills for the task at hand, from expert developers or your own team. Hey HN I was originally a bit frustrated with having to scour github repos for the right skill while I tried to improve an iOS app's Swift animation. Then I got frustrated with having to force the agent to use the right skill for the right task. So I built Skillstore: a library of engineering skills behind an MCP server. Claude Code and Codex can search it, load relevant instructions, and apply them to your task. You don’t need to know the skill’s name beforehand. Skills are loaded on demand, so you don’t have to keep the whole library in your prompt. (ideally with help you also save tokens and preserve the context window) ex: In our running app, a review using Paul Hudson’s SwiftUI skill caught undersized touch targets and controls that VoiceOver couldn’t meaningfully identify. We fixed those before the release. In our gym app, a Skillstore-guided review caught an onboarding layout overflowing on small iPhones at large text sizes. You describe the work → your agent finds relevant expertise → your agent uses it. You dont have to browse github repos and filter by stars anymore. And you dont have to invoke skills by name You can also give your team a shared library of private skills Been using it inhouse and with friends for the past 2 months. Favorite feature so far: Turning a tutorial into a private skill, so the agent can use that knowledge on future tasks when the time is right You can try the public library without an account https://skillstore-jk.fly.dev/developers#try Send me your feedback :)

2026-10-22 Show HN: Multiplayer AI 未评级 so recently i was working on a hackathron project with a friend and we were both using claude code however as it so happened we had to code one at a time in order to avoid file conflicts and interfering with each others work so i made a simple solution for this simple problem I am currently looking for users to test my app so if anyone has the same problem please check out synteny and join https://discord.gg/BPn28HSjH

2026-10-22 Show HN: Peras – Pause Claude Code and Codex before they burn your weekly limit 未评级 Hello HN! Today I am presenting you with Peras, the tool which governs your Claude Code and Codex usage, and enforces limits. I built it because I got tired of constantly having to spam /usage to check my usage, and decide if a task is worth risking the agent running out mid-task. Peras enforces a limit with 2 main tiers. At 75% weekly usage you will get a notification, and at 90% Peras will automatically pause the agent. These limits are the default and they are customizable to your own liking. You may ask "how does it know my usage in Claude Code or Codex?" Well, it's pretty simple. Peras gets the Claude Code usage % from the status line, and Codex's one comes from its local app-server. The "pause" Peras executes is a hook that refuses the agent's tool calls and ends its turn. A new feature I implemented is one that makes agents aware of their own usage. When you send your prompt, Peras attaches the usage %. It sends it at the start of the session, then again at 50, 75, 90 and 100%, or if a reset is coming in 30 minutes, so the agent can hurry up and actually capitalize on the remaining usage, if any. Just to clarify, this feature is informational and the pause is what enforces the limit. Before I switched to native SwiftUI, I used SwiftBar. The problem was that for the mascots patrolling their usage bars, I had to re-encode every menu image 8 times a second! There was also stuff SwiftBar wasn't capable of, like the menu being able to appear over fullscreen apps, pinning it as a floating panel, etc. What is the difference between the free and paid version? Well, it is MIT, first of all. The CLI, the hooks, the SwiftBar menu, and the app's source are all on GitHub, but building the app needs macOS 13+, Node 18+, "xcode-select --install" and then finally "npm run build:app". The €4.99 buys you a signed copy which is notarized by Apple, with updates included. The guard works with no menu at all. To install, just run: npx peras-cli setup npx peras-cli codex setup And now we get to the limits part. For now it's subscription plans only, and when running "claude -p", the pause uses the last interactive reading, so it can come late. Also I feel I have to mention that the guard rail is not a security boundary. It runs inside the agent. The menu is macOS only. The CLI and hooks pass tests on Linux in CI, but I don't use them there day-to-day. Last thing before I end this post, I would really appreciate feedback from you, whether install worked for Codex users, whether you have encountered any bugs, or whatever you feel like sharing.

2026-10-22 Show HN: My personal agent, distributed as a prompt 未评级 Hi HN, I'm Matt. I just open-sourced my personal agent. If you're interested, paste this into Claude Code or Codex on a Mac: "Clone github.com/mattabate/life-distributable and set up my life agent. Follow its SETUP.md." What's cool about the agent: - It's software distributed as a prompt. No installer, no package, no config. - The prompt builds a Desktop and iPhone app for communicating with the agent. You can ask the agent to update or refactor the Desktop and iPhone apps to match your desired user experience and use case. - Mine keeps me on my daily routine, manages my finances and runs a P&L on itself that has stayed positive. When it hit +$200 I bought it Claude Max. When it hit +$1,600, I bought it a Mac mini. Let me know what you think.

2026-10-21 ghorbelhamdi/buddy-android 未评级 A floating chat bubble that lets Claude Code, Codex or OpenCode use your Android phone. Runs inside the app on your own subscription or free models. No adb, no PC, no root.

2026-10-21 liuda30201/AI-Coding 未评级 AI 编程福利导航：汇总 Claude Code、Codex、Cursor 中转站与公益站，整理免费额度、注册福利、签到活动和评测记录，提供可视化看板与 Python 数据采集工具。

2026-10-21 wshobson/agents 未评级 Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi

2026-10-21 Graphify-Labs/graphify 未评级 Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

2026-10-20 iha2/superlite 未评级 A faster, leaner fork of the superpowers workflow for Claude Code: one approval gate, parallel waves, routed models. 3.9x faster in benchmark at equal quality.

2026-10-17 MadsLorentzen/ai-job-search 未评级 The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

2026-10-16 HangYu8123/Pocket-Agent-CLI 未评级 Codex CLI and Claude Code CLI on your phones. No computers required.

2026-10-16 HeyCubit/effortless 未评级 Claude Code mod: picks the reasoning effort for every prompt, shows the prompt cache and context, and hands off or compacts in one click

2026-10-16 Sixian-Li/knowledge-base-kit 未评级 Source-backed Markdown knowledge bases for Claude Code and Codex.

2026-10-16 Sunwood-ai-labs/hyperframes-motion-reel-skill 未评级 🎬 Claude Code skill for showreel-grade, beat-synced motion graphics with HyperFrames (HTML + GSAP + SVG + Canvas, Apache-2.0) — 120 BPM / 60 FPS to MP4

2026-10-16 anthropics/claude-code-playground 未评级

2026-10-16 chipfighter/context-attachment-manager 未评级 Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goes on, and requests stay small.

2026-10-16 evondev/evondevKit 未评级

2026-10-16 hellosverre/claude-skins 未评级 Skins for Claude Code: tool rows with icons, diff, table and Mermaid chart cards, a usage band and fifteen themes. /skin swaps them live.

2026-10-16 iamumeransari/claude-show-your-work 未评级 Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

2026-10-16 liouhai/plot-is-all-you-need 未评级

2026-10-16 pavrus117/ai-os-maps-guide 未评级 Free MAPS guide: set up your own AI operating system on Claude Code (Memory, Agent, Pulse, Screen) — one prompt per layer

2026-10-16 shenysun/skills-manager 未评级

2026-10-14 Show HN: shadowclone, skills learned from your coding agent corrections 未评级 shadowclone reads the coding-agent sessions already on your disk, finds where you corrected the agent and turns those corrections into skills your agents load next time. It supports Claude Code, Codex, Cursor, Pi, and Antigravity. Every capture source is off by default and has its own consent setting. Why I'm building it? I use multiple harnesses and agents, I extensively use Claud Code and Codex, but I also use Cursor and Antigravity every now and then. I didn't want to have to teach every harness or model the things I taught the other ones between my last session and the current one. I also cannot have my personal rules and preferences in all the repositories I work on because my collaborators may have varying levels of trust with AI and their own preferences. shadowclone helps me build and improve trust with my agents so I can give them more autonomy while running multiple sessions in parallel. --- Who is this for? If you only use Claude or Codex or any one of these, you may not need the shadowclone CLI and the harness and agent you use might already be sufficient. But, if you are like me and work across harnesses and agents, shadowclone will help you avoid repeating your preferences each time. --- Built-in skills and skill builds shadowclone is also great for someone who is just now adopting AI into their coding workflows because it ships with several skills that they can use to customize their agent's behavior. They can equip all the skills, or just some of them, they'll see the "personality" their agent gets from equipping those skills from the `shadowclone wizard`. --- Setup is extremely easy, just ask your Claude Code, or Codex, or another agent - "Set up shadowclone: https://raw.githubusercontent.com/theonly1me/shadowclone/mai..." --- Privacy shadowclone is free and open source, it uses the MIT license. It doesn't have a subscription, or a server. It just uses your existing agent subscription i.e. Claude Code, Codex, Cursor, Antigravity, or even your local model via Pi. You can explicitly disable sources, it also redacts any and all sensitive information it uses for learning. --- PR reviews and Cloud bots It can review PRs with the `shadowclone review` command, it ships a guided review skill that will perform a deep review of your code (or someone else's) and produce an HTML document you can annotate, add comments to and submit so your agent can stage a draft review on the PR you are reviewing. --- Evals I performed several evals, I won't describe them here, all of them are available in the repository - https://github.com/theonly1me/shadowclone/tree/main/evals --- Comparison to other tools? You can also see how it compares to other tools here - https://github.com/theonly1me/shadowclone/tree/main#how-shad...

2026-10-13 Alishahryar1/free-claude-code 未评级 Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

2026-10-12 Show HN: Tracon (air traffic control for subagents) 未评级 My Claude Code workflow usually involves... a lot of subagents. I make one Opus model coordinate work as my tech lead, it dispatches subagents using models appropriate for the task into their own git worktrees, and then I try to multitask and do something else while they run. I'd been finding lately (particularly with Opus 5.5) that there was a ton of drift and instances of subagents not doing anything and it was evading the attention of the TL despite the instructions I gave it to have them report in at a regular cadence. Running tracon in a split terminal is my new personal workflow. It gives me early indicators when things start going off the rails (ex. blocked on a prompt, idle, looping on a failing command, simultaneous edits to files other subagents are editing, drifting off the brief, etc.) and I can interrogate the subagent's workflow and by pressing n the main agent gets a note to make a call on how and if to correct it. Read-only and runs on your machine: it tails transcripts in ~/.claude/projects/ and checks each worktree with ps, lsof, and git -- only thing that leaves your machine is what the Haiku judge reads for classification (or optionally you can turn that off with --no-judge). I've found it super useful for the game I'm building and figured others in the community might also find it useful. If you just want to give it a spin without committing: uvx tracon --demo macOS and Linux, Python 3.12+, MIT. (Not affiliated with Anthropic.)

2026-10-12 Show HN: I Cut my Agent Tokens By 50% 未评级 This started by watching the built-in tool calls in Claude code. We noticed that a LOT of the time was being spent searching for lines of code with regex. This approach makes sense when you are working in an unknown environment, but we all work inside of some codebase structure and tracking. This took us down the rabbit hole of codebase indexing and led to us building Indexio. Indexio was built to eliminate the time and tokens agents waste rediscovering a codebase. Regex calls return lots of data each time to the context window which causes bloat over time with items that don't really matter. Since codebase work container mostly static files indexing them and quickly getting to data for discovery is what we were trying to solve. Indexio index's the codebase to its internal DB and then returns what is needed via MCP when asked. We ran into some fun issues when trying to force the session to use a tool call for lookups so there is some aggressive tool call logic which attempts to override built-in lookup tools. If something isn't in the index it will just fallback to regex lookups. The whole system is a single binary written in Rust for performance. In our real world testing we are seeing about 50%-60% reduction in token usage compared to the built-in tools, and near instant lookup times compared to multiple seconds for each regex lookup. One place that indexio does come up shorter than then regex is when looking up symbols. We found that most of the agent's work was done looking at strings of words rather than symbols, but if you have a workflow that is heavy in this specific situation just know it may not fit. We opened sourced everything and would love to hear feedback. Huge Shout out to CocoIndex who gave us the inspiration for this idea. https://github.com/IOServicesLabs/indexio

2026-10-09 Show HN: Claude Code spinner verbs reflect the model (Haiku: Licking screen..) 未评级 I found it tricky to know which intelligence level (effort+model) my claude code is on so I used the claude mod system to make the spinner verbs depend on intelligence level and bake in jokes. This plugin sorts the spinner verbs into six tiers by model + effort: Haiku gets "Licking the screen...", sonnet gets "Force-pushing to main...", Fable "Remembering the future..." How it works: this is a 20 line registry file plus a 120 line verbs file. If you want to add custom verbs, modify verbs.ts. The only slighlty hacky workaround claude did was using hooks to identify the effort level since it's not exposed by the mods api. It takes the word claude code originally sampled and maps that to the word list. Please send PRs with better verbs! Only rules: can't communicate something concrete about the code (like "Deleting and force pushing the codebase...", as that would make users lose their minds), and must correlate to model+effort level.

2026-10-06 Show HN: Browsentic Open-source Claude for Chrome alternative for any agent CLI 未评级 A personal agent harness lives in your existing browser, connects to your claude-code (or any other major harness codex or cursor-cli...) NOT the SDK API, exposes web-optimized tools to the harness - that's Browsentic. A free, opensource (Apache 2.0) with rich capabilities alternative to Comet, BrowserOS, Browser-use, Claude for Chrome or nanobrowser. The unique architecture of Browsentic makes it different from all other alternatives. It uses a loopback MCP server that spawns claude/codex/OpenCode/Cursor harness in a detached process. You can already guess, it is a bi-directional MCP, you can browse agentic through the browser harness or through any MCP client. Browsentic doesn't require any new browser to install and not limited to chromium, it supports Firefox as well. By default you don't even need CDP to perform core agentic browsing. Capabilities: core accessibilities (50+ compare to nanobrowser only had 20), custom skill, record-replay, schedule-monitoring-notification, resolves captcha autonomously, has it's own memory, voice orb over web-speech API, can sideload custom tools, platform + browser + agent agnostic It is opensource, no API key, no telemetry & local first and actively maintained and yesterday was the first public stable launch (v0.8.0) Currently I'm the only author but every & any contribution or suggestion will be more than welcome :) Source: https://github.com/imshaikot/browsentic Install guide: https://browsentic.com/install Docs: https://browsentic.com/docs Install video: https://www.youtube.com/watch?v=o8t4l9Q9BkE

2026-10-06 Show HN: Claude Remote – start Claude Code on your own PC from your phone 未评级 I kept having ideas away from my desk, and my Claude Code sessions only lived at it. The hosted sessions run on a cloud copy of the repo, so my local hooks and config don't come along. This is a small Node agent on a Windows PC (zero dependencies, binds to 127.0.0.1 only) exposed through tailscale serve, plus a PWA. Tap a folder on the phone and it starts a Claude Code session there with --remote-control, which you then drive from the Claude app. It's a start button, not a terminal. The trade is spelled out in the README: a session runs with your account's full permissions and anything on your tailnet can reach the agent, behind a six-digit passcode with a lockout. Fine for a single-user tailnet, not for a shared one. Windows only for now. Happy to answer questions about the design.

2026-10-05 Show HN: Make Claude Code sessions talk to each other 未评级 It lets one Claude Code session ask another a question, whether that session is your own in another project or a teammates, and get the answer back. Typical use is a frontend project asking the API project how something behaves. Let me know if you find it useful.

2026-09-28 Show HN: swe-mux – A terminal multiplexer for coding agents optimized for mobile 未评级 I run a lot of coding agents at once, mostly Claude Code, Codex and pi, across several projects. I got tired of having so many windows open, of agents leaving hung processes behind, of tracking which one needed input, and of having to remote into my desktop or SSH into a single shell to manage them from my phone. Even then, a terminal on a phone couldn't show me the frontend or output I needed to verify the work. I tried Orca and herdr. Both were better than my setup, but neither had a real WYSIWYG markdown notes surface, and neither had a phone interface I could actually work in. swe-mux is the terminal multiplexer I built for that. It runs any shell or CLI in real terminals on your own machine and serves the same live sessions to your desktop and your phone. It's built around agents: Claude Code, Codex, opencode, pi and oh-my-pi get a live status (working, done, or waiting on you), searchable history and resume. Anything else runs as an ordinary terminal with everything except the status. This is the actual terminal and not a UI wrapped around the agent, and you can just use it that way, or start claude in a plain shell and that pane becomes an agent session. On the desktop it's panes and tabs of sessions, notes, files and dev-server previews. Input behaves the same across agents: Shift+Enter, Ctrl+Backspace, paste and click-to-position work in all of them, shortcuts come from presets (tmux, VS Code, Vim, Emacs), and you can paste images straight from the clipboard. Notes and any markdown file in the project open in the same WYSIWYG editor, on desktop and phone, and autosave. No more scattered locations for notes. On the phone it's the same sessions over your own Tailscale network, installed as a PWA: the terminal with a usable keyboard, git diff review, files, notes, and push notifications when an agent needs a decision. A dev server on the host's 127.0.0.1 is proxied through swe-mux, so the phone can open it without exposing another port. Being able to play-test and check a frontend there is what finally closed the development loop on the phone for a lot of my projects. Now I can and do swe anywhere. It's a problem Two things I use constantly: a prompt queue, so something I think of mid-turn waits until the agent is done instead of interrupting it, and messaging between sessions, so a Codex session can ask a Claude session something. I don't want my workflow tied to one provider. General architecture: Sessions survive restarts. A separate supervisor process owns the terminals, so the daemon can restart and the app can update without killing anything. I update it several times a day, so this wasn't optional. Status comes from the CLI's hooks, its transcript and the terminal itself, because no single one reliably tells "waiting on you" apart from "busy in the background". There's no swe-mux account, no server of mine in the path, and no telemetry. Just your tailnet It was built on Windows, which is where I use it every day and the only platform with a packaged desktop app. The installer is unsigned, so the PyPI install is the way to avoid the SmartScreen prompt. macOS and Linux run the daemon and use a browser. CI runs it on all three, but I haven't lived on those myself, however Linux I have tested. Demo, the real UI with simulated agents, nothing to install: https://swemux.dev/demo/ Install: `uv tool install swe-mux` (or `pipx install swe-mux`), then run `swe-mux` on Windows or `swemux start` elsewhere. Apache-2.0: https://github.com/jatoran/swe-mux I've put a lot of work into the initial user experience to help streamline a quick setup depending on someone's needs, feedback greatly appreciated, thanks

2026-09-21 Show HN: 8 months extending my terminal to handle all my work with all agents 未评级 GitHub albertwujj/agent-term ★4 · For Claude Code, Codex, Cursor CLI, and other CLI agents. macOS and Windows with WSL. · I’ve been using this as my only terminal since January, adding things I needed and keeping what worked well. I didn’t expect so many useful additions to work so well with a terminal and Electron as the base. I still check out agents in desktop apps and IDEs from time to time, curious to see what they offer. But with this terminal, I don’t want to work any other way. Let me know what additions are important to you.

2026-09-20 Show HN: Built a local guardrail layer for Claude Code 未评级 I built Mati to give me more control over what Claude Code and Codex are allowed to do. Many important product constraints live in an engineer's or product person's head. This isn't new for engineers. We've always had important constraints that only certain people know about, but with coding agents it gets worse because we can now delegate a lot more, sometimes without realizing how much context the agent is missing. Then we delegate changes and the agent implements a change that looks reasonable but breaks some hidden constraint, hurts performance, exposes data, or does something destructive. It’s a local, Apache-2.0 licensed tool. It works with Claude Code and Codex, and also exposes MCP and CLI interfaces. The name comes from a Nahuatl verb meaning “to know” or “to think.” It’s probably a bit over-engineered. Anyway, sharing it here in case it’s useful to someone.

2026-09-17 Show HN: Leo – a Markdown engineering process for AI coding agents 未评级 I'm the builder of LEO, and this is not a packege or a service. It's a engineering framework of the rules for Cursor or ClaudeCode, helping to build enorm AI Native projects, 300 000 + lines of code (I understand that is not the quality gate, but - zero TODO, cyclomatic complexity <= 10 (lizard), the project work). A cursorrules file with 44 rules plus 133 *.md files (roles, canons, protocols) that registred how to do an Enterprise project. However, I build solo an AI Nodes Constructor pipeline IDE like n8n for 3-4 month, and if you wont you can look some greps and tests of this project. 368 schema constrants, 77 row-level-security policies, 120+ alembic migrations, 3900+ tests, 10 200+ functions and more. If you wont to know more about the project and LEO rules: https://dev.to/alex-zaporozhan/385000-lines-of-code-in-three... Another projects build with LEO (first debute project, open source, enjoy the lines of code): https://github.com/alex-zaporozhan/medCore" Thank you for your help, Alex

2026-09-15 Show HN: Replay – Audit silent prompt cache misses in AI agent transcripts 未评级 I built Replay because AI agent bills spike without a single warning or error in your logs when a prompt cache breaks. Whether your team runs Claude Code, Cursor, or Aider, the provider just silently re-bills your entire conversation history at cold-write prices instead of cached read prices. Replay is a zero-telemetry, zero-dependency local Go CLI that forensically reads your on-disk log transcripts, replays them against reverse-engineered provider caching state-machines, and names the exact turn the cache broke, the cause, and the exact token leakage. Repo: https://github.com/RedRobotKK/Replay Core Subcommands (What it actually does): - `replay` : Computes total avoidable re-billed cost across your local transcripts. - `replay diff <transcript>` : Pinpoints the exact turn the cache sharded and why. - `replay advise <dir>` : Outputs structural prompt optimization adjustments based on your history. - `replay context <transcript>` : Ranks and isolates exactly what content is bloat-filling your context window. - `replay route <dir> --to <model>` : Simulates what switching models would cost, factoring cold-start prefixes. Why Go / Design Constraints: 1. Zero Dependency: Avoids messing with Python virtual environments or Docker runtimes for local diagnostics. 2. 100% Sandboxed: Absolutely no remote tracking, cloud accounts, or telemetry. Your prompt text never leaves your machine. 3. Mutant Testing Isolation: Keeps 76 real past defects frozen as re-runnable mutants to enforce code stability. It's completely free and source-available (BUSL 1.1). To check your local developer logs or audit the setup script before running, use: curl -fsSL https://replay.doctor | less

2026-09-15 Show HN: A skill that makes people think you're using Claude Code 未评级 Built a skill that makes people think you're using Claude Code. Sometimes when browsing repositories on GitHub, you might notice "Claude" listed as a co-author or contributor in commit histories and PRs. This skill lets repositories that aren't using Claude Code mimic that exact look. To make the mimicry as authentic as possible, I analyzed dozens of real-world commits and PRs, and studied Claude Code's binary behavior and output patterns. It now replicates Claude's commit dialect, RFC 2822 trailers, and PR style almost 1:1. GitHub: https://github.com/Juwan-Hwang/claude-mimic Now any code can look like it was authored by Claude. Built purely for fun and entertainment! :)

2026-09-05 ervareza/boost-skill 未评级 Universal /boost multi-agent reasoning and independent verification pipeline for all AI coding CLIs (Hermes, Claude Code, Codex, OpenCode, Cursor, Aider).

2026-09-04 Show HN: A Context Registry for AI coding agents 未评级 Hi HN. We built an API context registry to help coding agents (like Claude Code) generate production-ready API integration code without blowing through token limits. We build a lot of API integrations. In our experience, most coding agents write basic client calls fine, but consistently stumble on details that make code shippable, like idempotent retries, rate-limiting and Auth token management. We tried all the existing approaches of injecting context into coding sessions: - Markdown dumps delivered via MCP (think Context7 or Mintlify Docs MCP) - API behaviour described in prose using AGENTS.md and skills. - OpenAPI specs However, all of them left the same production-readiness gaps. So we came up with our own approach that combines prose with typed SDK reference code into a "Context Plugin". You install the plugin into your coding agent and it automatically injects language-specific context whenever the agent works on an API. Across our benchmarks, Context Plugins boosted one-shot production readiness by up to 34%, allowing Sonnet to match or beat baseline Opus on the same integration tasks. You can read more about our experiments here https://www.apimatic.io/blog/working-api-call-is-not-product... We have published Context Plugins for 24 APIs for the community to try out, including Slack, Google Maps, and Notion. We'd love for you to give them a go and share your feedback on our plugins as well as our evaluation methodology.