Project Directory

Browse all indie developer projects and co-creation requests

Active: ShowcaseDeveloper Tools
Showcase
Online
Developer Toolsclaude-code

vibe-learn

A Claude Code skill that teaches you core concepts while the AI codes — with quizzes and spaced repetition.

vibe-learn is a Claude Code skill that flips the usual AI-coding dynamic: while the AI writes your code, it also explains the core concepts behind it. Non-blocking mini-quizzes check your understanding without breaking your flow, and cross-session progress memory keeps track of what you have learned. A spaced-repetition review system brings concepts back at the right time, and you can export everything as Anki, CSV or Markdown flashcards. The author writes in the README footer: "Built with Claude Code." The repo holds 3 stars and was last pushed on October 4, 2026.

Showcase
Online
Developer Tools

OpenNavo

为 macOS 打造的 Homebrew 图形化应用商店:一键安装更新 5,008 款应用,全程由 AI Agent 辅助开发。

OpenNavo 是为 macOS 打造的 Homebrew 图形化应用商店:网页端展示完整的应用目录、分类与排行榜,macOS 客户端提供一键安装、更新与卸载流程。底层依然走 Homebrew 安装,但整个过程全程可见,再也不用记命令行。 vibe-coded 证据来自作者本人在 V2EX 的首发帖(t/1248977,2026-10-15)原话:"从功能开发、Bug 修复到日常维护和版本迭代,我都在尝试交给 AI Agent 完成。" 核心功能:5,008 款应用的完整目录(带描述与更新日志)、按 Homebrew 官方安装统计生成的实时排行榜(支持 30 天 / 90 天 / 365 天维度)、分类浏览、精选合集、最近更新追踪,以及应用详情页的一键 Get 安装按钮。 技术架构:网站用 Nuxt 4 + Vue 3,macOS 客户端用 Tauri 2 + Rust,后端是 Go + PostgreSQL + Redis,还预留了 FastMCP 作为 AI Agent 接口。以上均为作者在原帖中明确声明的技术栈。 现状:GitHub 仓库 opennavo/OpenNavo 开源(Apache-2.0),已有 15 个 star,2026-10-15 当天仍有代码推送,网站数据每日同步。

Showcase
Online
Developer Toolspi

Phi — Pi AI Agent for VS Code

An AI agent extension for VS Code powered by Pi - itself vibe-coded, and iterating fast.

Phi (φ) is an AI agent extension for VS Code, and the author's own description leaves no ambiguity about how it was built: "Phi is a vibe-coded project - built with AI agents (using Pi), iteratively refined, and open to everyone." That statement appears verbatim both in the README and on its Open VSX extension page. The extension is real and installable: Phi is listed on Open VSX as gnassro/phi-agent at version 0.9.1, powered by the Pi coding agent SDK (@earendil-works/pi-coding-agent@1.0.4). Per the README, it is "built with TypeScript + vanilla JS", and the repository (gnassro/phi) was last pushed on 2026-10-11 - days before this writing - so the project is being actively iterated, matching the author's "iteratively refined" claim. A nice meta touch: a coding-agent extension that was itself built by coding agents. If you work in VS Code and want an Open VSX-native AI assistant, Phi is worth a look.

Showcase
Online
Developer Toolsclaude-code

Orthonym

Free IUPAC name generator for chemical structures — paste SMILES, upload a file, or draw the molecule.

Orthonym turns chemical structures into verified IUPAC systematic names. Paste SMILES (one per line), upload a structure file, or draw the molecule right in the browser — every name is parsed back by OPSIN and checked against your structure, and unnameable molecules get a second, broader pass. The README documents the build process in a dedicated "How Orthonym was built" chapter: "Orthonym was built with Claude Code, under a fixed set of working rules." A rare documented case of an AI agent shipping a deterministic scientific-computing engine — with companion orthonym-skills for agent workflows. From the Steinbeck-Lab team; 8 GitHub stars, updated the day before this listing.

Showcase
Online
Developer Toolsclaude-code

GHDash

Native macOS/iOS/terminal dashboard for your GitHub PRs, review requests and pending Actions runs — 100% vibe-coded with Claude Code.

GHDash is a small native dashboard for your GitHub work across the repositories you choose. It ships as three apps sharing one data layer: a native macOS app, an iPhone/iPad app, and a terminal TUI (ghdash). The whole point is to show everything that's waiting for you, at a glance. What it shows: My open pull requests – with draft, review, approval, check, conflict and unresolved-thread status; Awaiting your review – PRs where your review is requested, plus Dependabot PRs nobody was asked to review; My pull requests waiting on reviewers – your PRs with nothing left for you to do; Pending actions – GitHub Actions runs not yet finished, including deployments awaiting approval. Every row opens the PR or workflow run on GitHub (the app itself is read-only). A sidebar scopes the dashboard to one repository with per-repo item counts; the Dock badge counts the things waiting on you; data refreshes every three minutes. The Mac app signs in through the GitHub CLI (gh auth token, storing no credentials itself), the iOS app uses a personal access token kept in the device Keychain, and a demo mode with made-up data lets you try everything without signing in. Vibe-coded evidence, verbatim from the author (README of https://github.com/markuspalme/gh-dash): "This project is 100% vibe-coded: all of the code was written by Claude Code from conversational prompts." The repository was created on 2026-10-02 and was still being pushed to on 2026-10-06 (17 commits). Tech stack (as stated by the author): SwiftUI views shared by the macOS and iOS apps; the terminal app built with TermKit. AI tool: Claude Code. Open source on GitHub (2 stars).

Showcase
Online
Developer Toolscodex

Finder Actions

macOS Finder 原生右键扩展:右键一键在 Alacritty / VS Code 打开目录,支持自定义脚本,运维纯口述让 Codex 半天搓出。

Finder Actions 是一款 macOS Finder 原生右键扩展。在任意文件/文件夹上右键,即可一键在 Alacritty 或 VS Code 中打开当前目录;还支持自定义 shell 脚本动作(路径以 $1 传入)、拖动排序、生效目录控制、中英文切换。 作者 qvgz 本人是运维,不懂 Swift。他的原话:「试一试让 Codex 写,纯口述需求没看一行代码,半天做得有模有样。」项目用 Swift + SwiftUI 实现(作者 GitHub topics 标注 swift/swiftui/developer-tools),MIT 开源,Release 页可直接下载安装。 诚实注记:安装需 Ad-hoc 签名去隔离并在系统设置中启用 Finder 扩展,README 有完整说明;3 stars 的新工具,仍在持续迭代。

Showcase
Online
Developer Toolsibm-bob-20claude-code

Neuro Symbolic Game Level Designer

Describe a level in one sentence: agents plan, algorithms build, validators check — a playable Flame level in about a minute.

Neuro Symbolic Game Level Designer is a hybrid AI level-design tool built for an IBM Bob 2.0 hackathon. You describe a level in one sentence; a pipeline of agents plans it while classical algorithms build and verify it. The output is a complete, playable 2D isometric Flame game level — a Tiled map plus a typed Dart loader — with a six-check validation report covering spawn reachability, item placement and pathfinding. The author, raf-xtgt, describes the build on dev.to: "One orchestrator session wrote the architecture and a precise prompt for each task. A coding agent implemented each task, and I reviewed it with tests and browser checks. IBM Bob built the first five tasks… After my Bob credits ran out, I continued with Claude Code using the same workflow." Stack: Flutter web / Flame 1.38 frontend, Python + FastAPI + LangGraph backend, Gemini agents on Vertex AI, backend on Cloud Run. Honest note: it's a research-style hackathon project — the levels look charming, but game feel is still generator-grade.

Showcase
Online
Developer Toolsclaude-code

mazkir

One shared memory for all your AIs, built mostly by Claude Code: tell one agent once and ChatGPT, Claude and Claude Code all remember.

Every AI you talk to starts from zero. mazkir is a shared memory layer that fixes that: tell one AI something once, and it shows up in your next chat — in Claude, Claude Code, and ChatGPT. It's a remote MCP server; your memory is plain Markdown notes you can read, edit, export, and delete, with per-project permissions. The feature list is practical rather than flashy: 20 MCP tools, OAuth login, a 30-day trash bin in case an agent deletes something, dark mode. Free during early access. The author's showcase post is disarmingly honest about how it was made: "claude code built most of it for me." Launch week brought ~160 visitors and exactly one sign-up — the author's friend. The numbers are real; so is the product.

Showcase
Online
Developer Toolsclaude-code

My Claude

A private local dashboard for everything Claude Code keeps on your machine — skills, token spend, session history and costs, all in one readable place.

Every Claude Code session leaves traces on your machine — skills you installed, MCP connectors you wired up, tokens you burned, conversations you had. My Claude puts all of it on one private dashboard that runs entirely on your local machine. One command installs it: the script sets up an isolated Python environment and opens the dashboard on localhost. The Overview page shows your skills, conversations, 30-day token usage with API-price cost estimates, and disk use at a glance. Drill into Usage for live plan limits, Skills to see which ones you never touch (and push them to GitHub with one click), MCP & Plugins with a one-click health check, and History with full-text search across every session — including transcripts Claude Code has already rotated away. Nothing leaves your machine: it binds to 127.0.0.1, computes everything from files already on your disk, and secrets in MCP configs are auto-redacted before they're shown. The README ends with three words that explain how it was built: "Built with Claude Code."

Showcase
Online
Developer Tools

Reachy Mini Vibe Coding Apps

A conversational agent that helps you vibe-code tiny browser apps for your Reachy Mini robot

Reachy Mini Vibe Coding Apps is a conversational agent: describe what you want, and it helps you vibe-code tiny static browser apps for Reachy Mini robots, then publishes them as Hugging Face Spaces in one click. Updated 2026-10-10, running on Hugging Face Spaces. From the author's README: "A conversational agent that helps you vibe-code tiny static Reachy Mini apps for Reachy Mini robots, then publishes them as Hugging Face Spaces in one click." Built on the @pollen-robotics/reachy-mini-sdk as a 3-file static Space (author-stated).

Showcase
Online
Developer Toolsclaudeclaude-fable-5

BootLoops

Open-source LLM harness for exact quantitative science across 22 fields — code written by Claude, supervised by a Harvard physicist.

BootLoops is an open-source (MIT) harness that helps large language models do exact, interdisciplinary quantitative science: 49 tool packages spanning 22 quantitative science domains, written in Python 3.12 and Julia. In about three months the project produced 36 manuscripts and solved 15 previously unsolved elliptic Feynman integrals. The vibe-coding credential is in the repository LICENSE itself: "Created by Matthew D. Schwartz; code written by Claude (Anthropic) under his supervision." Schwartz, a Harvard physicist, wrote up the project as a guest post on the Anthropic Science Blog (October 1, 2026), describing how his experiments doing research computation with Claude crystallized into this software and its protocols. Version 1.0 shipped October 1, 2026 and is actively maintained. 中文导读:哈佛物理学家 Matthew Schwartz 发布的老牌开源 LLM 科学计算 harness——22 个定量科学领域精确计算,三个月产出 36 篇手稿;仓库 LICENSE 明言代码由 Claude 在作者监督下编写。

Showcase
Online
Developer Toolsclaude-code

piermux

A Tauri GUI for managing tmux sessions across multiple SSH hosts, with a cross-host tree view and line-buffered typing.

piermux is a desktop (and Android) GUI for managing tmux sessions across multiple SSH hosts: a cross-host session tree on the left, an attached tmux session on the right, and line-buffered typing explicitly designed for feeding prompts to AI agents. MIT-licensed, 25 releases deep since its 2026-04-28 debut. The README says it outright: "This is a vibe-coded side project — 'small things decide yourself, big things ask first'. Built with Claude Code as collaborator," with CLAUDE.md and NOTES.md keeping the whole collaboration public. Declared stack: Tauri 2 (Rust + WebView), russh, xterm.js, React 19, TanStack Query, Tailwind 4, SQLite, keyring 3. 中文导读:跨多台 SSH 主机管理 tmux 会话的图形工具,为 AI Agent 提示词输入优化的行缓冲打字。

Showcase
Online
Developer Toolscodexclaude-code

boxes.dev

Cloud computers for Claude Code and Codex: give every agent its own machine, start it from Slack.

boxes.dev gives every AI agent its own cloud computer: bring your Codex or Claude subscription, start agents from Slack and Linear, and manage them from your desktop, phone, or terminal. The pitch is one line — "Close your laptop again." The makers, Nick & Drew, built it the way they dogfood it. Their Product Hunt maker comment (2026-10-06 launch): "We spent the last year coding almost exclusively with Codex / Claude Code" and "we've been building boxes.dev with boxes.dev for months" — the product that hosts coding agents was itself coded by coding agents, running on its own infrastructure. A neat meta-loop for the vibe-coding era: the tooling that lets agents work while you close your laptop was made by people who barely opened theirs. curated by the VibeFix editors

Showcase
Online
Developer Tools

minecraft-modding-mcp

An MCP server for AI-assisted Minecraft modding: 41 tools, 9 resources

minecraft-modding-mcp is an MCP server for AI-assisted Minecraft modding: 41 tools and 9 resources that let a coding agent inspect decompiled source, resolve Mojang/Yarn/Intermediary mappings, diff versions, analyze Fabric/Forge/NeoForge mod JARs, and validate Mixin and Access Widener files. Published on npm as @adhisang/minecraft-modding-mcp. The README states it plainly: "Note: This project is entirely vibe-coded — built with AI-assisted development without formal specs." 8 stars, 520 commits, last push 2026-09-25, MIT — a meta-vibe project: AI-built tooling that helps AI build Minecraft mods.

Showcase
Online
Developer Toolsclaude-code

OtoDock

Self-hosted 'company OS' — multi-tenant AI agent platform running Claude Code / Codex on your own servers

OtoDock 是自托管的"公司操作系统":多租户 AI Agent 平台,让 Claude Code / Codex 以部门制协作运行在自己的服务器上,支持电话拨打、文档编辑、定时任务和沙箱隔离。 作者 Dimitris 在 Show HN 首发帖写了个罕见的声明:"AI Disclaimer: large parts of OtoDock are written using OtoDock itself, running Claude Code." 用自己做的 Agent 平台写自己,递归式 dogfooding。GitHub 仓库 190 star、15 releases,最近 commit 是 2026-10-07(v1.7.1),技术栈 Python (FastAPI)、React + TypeScript、Docker、PostgreSQL,外加 bubblewrap + pasta 沙箱隔离。

Showcase
Online
Developer Toolsclaude-opus-55

pwasm

纯 Python 实现的 WebAssembly 引擎:零依赖,安全沙箱跑不可信代码

pwasm 是 Simon Willison 的纯 Python WebAssembly 引擎:零外部依赖,可在沙箱里运行不可信代码,内置 MicroPython / QuickJS / Micro QuickJS 访客解释器,顺手带了 WASI 支持。作者自己管这叫 folly project——玩票项目。 作者在 2026-10-01 的博客原文写道:"pwasm is one of my folly projects - an entirely vibe-coded pure Python WebAssembly engine that I built in January during my first bout of AI mania." 一月份 AI 狂热期起了个头,9 月底又把 Claude Opus 5.5 放进来冲刺了一轮(两天 42 个 commit),直接打到 Release 0.2a0,"几乎覆盖全部 WASM 规范"。仓库 10 star、Apache-2.0。

Showcase
Online
Developer Toolsclaude-code

getrequest

API 可靠性层:流量中继、请求留存、失败一键重放,再不丢任何 API 请求

getrequest 是挡在后端前面的 API 可靠性层:流量中继、全量请求留存、失败请求一键重放。首页只写了一句话——"Never lose an API request." 流量高峰、宕机、失败的发布都不再意味着请求丢失。 作者 santoshbaggam 在 2026-10-09 的 Show HN 首发帖标题里写明:"I claude-coded in a few weeks what I wanted to build since 2023"——从 2023 年就想做的东西,用 Claude Code 几周做成了第一版,正在找处理过这类问题的开发者试错。免费版永久免费、无需信用卡。

Showcase
Online
Developer Toolsqclawclaude-code+1

AI Animation Skills

12 个 AI Agent 动效 Skill:一句话生成 PPT 翻页、流程图、架构图、视频分镜等炫酷 HTML 动画

AI Animation Skills 是一套「让 AI 做动画」的 Agent Skills:装好之后,对 AI 说一句话,就能生成带炫酷动效的完整 HTML 页面。12 个 Skill 覆盖 PPT 翻页、流程图、网络协议可视化、动态架构图、学霸笔记、卡片剧场、手机 UI 演示、视频分镜、Win11 仿真、瑞士风图表等场景——需求到成品之间,只剩一句话的距离。 仓库 README 明示,这是「基于 WorkBuddy / Claude Code / Cursor 等 AI Agent 的动效 Skill 集合」;其中的 dynamic-archify 更是作者用 AI 编程 Agent QClaw 魔改开源项目 archify 而来:静态图表变成带流动粒子动画、明/暗双主题切换、一键导出 PNG/GIF/WebM 的动态架构图。项目 4 月创建、10 月 5 日仍在加新 Skill,已收获 1466 star。对 AI 视频与科普创作者而言,这就是一条现成的动画生产线。

Showcase
Online
Developer Tools

LDRAW Nova

Agent tooling that generates buildable LEGO models — vibe-coded with GPT-6 Astra and Claude Opus 5.5

LDRAW Nova is agent tooling for generative LEGO model building — and its author says the idea only became buildable when the models caught up: generating LEGO models that are actually valid "proved really hard to get right, even if vibe coding it... until GPT-6 Astra and Claude Opus 5.5 arrived," at which point the project itself was vibe-coded. The output is Python code that produces mathematically valid models, exportable as Blender-editable glTF — the showcase render is a Sakura Garden pagoda scene assembled from real parts. The repo includes agent instructions, model-checking scripts and worked examples, treating the AI agent as a first-class collaborator rather than a code autocomplete. It's a neat inversion of the usual story: here the vibe-coded artifact isn't an app but a toolchain that lets agents do physical-world-valid design. 309 stars and commits this month suggest the LEGO-builder niche is very much alive.

Showcase
Online
Developer Toolsclaude-code

CoIsland

Your whole engineering stack, centralized in the Mac notch — 35+ connectors, one click hands any alert to your coding agent.

CoIsland lives in your MacBook notch and watches your engineering stack: 35+ connectors for GitHub, Vercel, Snowflake, Jira, Linear, Sentry, PagerDuty, email and calendars. Each monitor runs on its own schedule, and when something fires — a failed deploy, a red CI run, a failed payment — the notch shows the alert with what was found. One click hands it to Claude Code, Codex or Cortex Code, which opens in a terminal right under the alert with the full context; the agent does what is safe, asks you for the rest, and never closes an alert — you do. It is a native Swift/SwiftUI app for Apple Silicon, deliberately serverless: tokens live in the macOS Keychain and the app talks to your tools directly. Two monitors run free forever; a license is a one-time $29.99 early-bird purchase. The maker has run his own days from the notch since July 2026. The author's own disclosure: CoIsland was built with Claude Code (Opus 5.5). curated by the VibeFix editors