Havuz

Every coding agent you run, in one window: a free, open-source app for macOS and Linux for Claude Code, Codex, OpenCode, Antigravity and Cur

Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.

Separate services, ports, and Postgres databases for every git worktree. Run parallel coding agents on one machine.

CleanMyMac CLI, macOS geliştiricilerinin önbellek ve oluşturulmuş dosyaları inceleyip temizlemesine ve disk kullanımını analiz etmesine yarayan bir komut satırı aracıdır.

Neden yükseliyor · 94 günlük yaşına rağmen 1009 yıldız, Mac geliştiricilerinin yaygın disk temizliği ihtiyacına ve bilinen CleanMyMac markasına ilgiyi gösteriyor. Ancak son 28 günde commit ve farklı yazar verisi sıfır; mevcut ilgi, sürdürülen geliştirme veya benimseme kanıtı olarak tek başına yeterli değil.

Tusk, macOS için birden fazla veritabanına bağlanan, SQL düzenleme ve veri yönetimi sunan yerel bir veritabanı istemcisidir.

Neden yükseliyor · Repo yalnızca 1 günlük ve 35 yıldız almış; bu erken ilgiye işaret ediyor, ancak yükselişin nedenini veya kullanıcı benimsemesini gösteren commit ve yazar verisi ölçülmemiş. README'de öne çıkarılan macOS'a özel yerel arayüz, çoklu veritabanı desteği ve AI agent entegrasyonu ilgiyi açıklayabilir; bunların sahadaki karşılığı henüz belirsiz.

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

Open source software factory infrastructure for advanced AI coding workflows

Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows ·

Rotate Claude and GPT subscriptions and API keys seamlessly inside the Claude Code CLI — switch on usage limits without interrupting your se

Learn from your vibe coding instead of just clicking Accept. AhaDiff turns each AI diff into a code-verified lesson, quiz, and review. · 别再无

A native macOS GUI for Jujutsu (jj) — DAG graph, side-by-side diffs, interdiff, conflict resolution. Built with Rust + SwiftUI.

Run AI Agent CLIs in your browser

jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones

Codex-native engineering workflows derived from pstack, with 45 explicit skills and 23 Poteto Mode playbooks.

A live, local-first dashboard for Claude Code sessions: project graph of agents, tokens, tool feed, replay, alerts. Plugin + terminal UI + M

Free ADB GUI and Android Emulator control panel for macOS. One click for dark mode, font scale, RTL and pseudo-locales, TalkBack, layout bou

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Include

This project is inspired by CMP40HX-Unlock. If you find it useful, please consider giving a star to both the original author and this reposi

Help your agents find the smoking gun they're looking for. Optimization evidence for agents: find complexity hotspots.

Simulator-free, headless SwiftUI checks for AI coding agents: render screens as accessibility trees and hot-reload views in ~2 s, without th

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature

Control the hinge angle of iPhone Duo Simulator from the CLI or AI agents

Cortex Terminal: run real Ubuntu 24.04 LTS (glibc 2.39, apt) natively on Android. No root, no PRoot, no containers, no VM. A fast Termux alt

Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT v

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

Open-source AI coding assistant with read-only Stellar/Soroban developer tooling: Soroban XDR & transaction decoding, RPC/Horizon inspection

An operating harness for repositories maintained by AI coding agents. Memory hierarchy, verification ladder and reusable workflows.

A phone-friendly web interface for Herdr: monitor agents, receive notifications, open real terminals, and send files.

Reverify, AI agent’larının reverse engineering ve kod doğrulama iddialarını deterministik araçlarla sınayan, CLI ve MCP server sunan bir Python aracıdır.

Neden yükseliyor · Repo yalnızca 28 günlük olmasına rağmen 1.245 yıldıza ve son 28 günde 83 commit’e ulaşmış; AI agent’ları için doğrulanabilir çıktı ihtiyacıyla MCP entegrasyonu dikkat çekmiş olabilir. Dört farklı yazarın katkısı aktiviteyi destekliyor, ancak yıldızlar tek başına benimseme veya kalite kanıtı değil.

MemoraX Code, coding agent’ların önceki oturumlardan mühendislik bilgisini, repository kurallarını ve çalışma tercihlerini sonraki görevlere taşımasını sağlayan bir memory katmanıdır.

Neden yükseliyor · 58 günlük yaşına karşı 1693 yıldız ve son 28 günde 230 commit dikkat çekici ivmeye işaret ediyor. Coding agent’larda oturumlar arası bağlam kaybı yaygın bir sorun; ancak yükselişin özel nedenini veya gerçek kullanım düzeyini verilen verilerden doğrulamak mümkün değil. Commit yoğunluğuna karşın farklı yazar sayısının 3 olması ekip genişliği konusunda temkin gerektiriyor.

Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that al

Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sess

Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%

🛍️ The TUI app store: browse, search & one-key-install hundreds of terminal apps.

A tiny macOS app that turns Caps Lock into a physical keep-awake switch for closed-lid MacBook work.

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

A REST Client where the Repository is the Workspace

A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, Gemini...) in real time, and grows as you

Image2 UI by ONDesign — open-source UI generation toolkit for OpenAI Codex. Turn screenshots and ideas into editable frontend code.｜基于 OpenA

htop for your ports. Inspect processes, Docker & systemd, detect port drift, audit Compose, and manage it all from TUI, Web or Cockpit.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Open-source TypeScript framework for building operational software used by humans and AI agents.

Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts,

Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys,

Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md