Havuz

NestJS documentation in your terminal. go doc, for Nest.

High-level, declarative animation framework built on Manim for educational, technical, mathematical, and algorithmic visualization.

Local-first Codex 5-hour window scheduler for Windows and Linux. Plan when your reset clock starts with a minimal guarded request, without a

Local Figma handoff packages for developers and AI coding agents.

ChatGPT <-> Codex bridge: local coding agents ask ChatGPT for advice, and ChatGPT can inspect or steer your running Codex sessions. No API k

✨ Intelligent, adaptive multi-agent orchestration & deterministic zero-cost telemetry engine for Codex with native macOS floating widget

useAgent, farklı coding agent’lara ortak workspace, izole computer ortamı ve ekip araçları sunan self-hosted bir çalışma platformudur.

Neden yükseliyor · 29 günde 361 yıldız ve son 28 günde 314 commit dikkat çekiyor; agent’ları ortak bir çalışma ortamı ve gerçek bilgisayar erişimiyle birleştirme fikri güncel bir ihtiyaca hitap ediyor. Ancak commitlerin tek yazardan gelmesi, hareketliliğin geniş katkı veya benimsemeyle desteklendiğini göstermiyor; yükselişin kesin nedeni verilerden bilinmiyor.

DeepSeek Harness（DSH）Web 界面右下角的常驻余额挂件。基于 MeteorNOX/DeepSeek-Balance-Whale-Widget 修改的铁盆鲸鱼娘版。

Browse, filter, export, and resume local Codex, Claude Code, Gemini CLI, Pi, and Antigravity sessions.

Claude Code production-readiness audit plugin with 8 specialist lenses in 3 waves for security, reliability, tests, DevOps, live-app QA, and

Local memory for Codex. Reuse work across chats without LLM calls to organize it.

A searchable, source-linked atlas of AI coding-agent commands, flags, shortcuts, MCP, permissions, skills, and sessions across Codex, Claude

Run it on another machine you own, get the result back — a personal job runner for your tailnet

The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learn

⚡ ShareDOM — Fast, zero-dependency DOM snapshot and screenshot capture library for the browser and SSR (Next.js, SvelteKit, Node).

Community troubleshooting knowledge layer for OpenAI Codex

Run tasks on multiple Cursor Grok Bots in parallel — your laptop's RAM stays flat because the work happens in the cloud. No official API: dr

Orchestration under Claude Code on herdr: flows an agent cannot skip, jobs on a clock, threads with claims, and a forum agents search later

Local-first Markdown collaboration for humans and AI agents, with live attribution, suggestions, and Git-friendly plain files.

Vicoa, farklı makinelerde çalışan coding agent oturumlarını desktop, CLI ve mobil cihazlardan yönetmeye yarayan açık kaynaklı bir orchestrator.

Neden yükseliyor · 30 günlük bir repoda 356 yıldız ve son 28 günde 154 commit dikkat çekiyor; coding agent'ları tek yerden ve mobil cihazlardan yönetme vaadi güncel bir geliştirici ihtiyacına hitap ediyor. Ancak commit'lerin tek yazardan gelmesi ve yıldızların benimseme kanıtı olmaması nedeniyle yükselişin sürdürülebilirliği belirsiz.

sepia, Agent Skills uyumlu agent'lara kurulan ve kurgu ile profesyonel metinleri türe göre belirlenmiş kurallarla yazma, inceleme ve düzenleme işlevleri sunan bir writing skill'dir.

Neden yükseliyor · 30 günlük repo yaşında 2867 yıldıza ve son 28 günde 280 commite ulaşmış; bu, dikkat çektiğini gösteriyor. Ancak farklı yazar sayısının 1 olması, commit hacmini geniş katkıcı benimsemesiyle eş tutmamayı gerektiriyor; yükselişin özel nedenine dair bağımsız veri yok.

The fast, native code editor and agent workspace.

Ten Engines. One local-first Harness OS.

Local-first observability CLI for Codex and Claude Code

Turn a repository into a slide deck that tells you when it stops matching the code

Pi coding agent extension for focused code retrieval, grounded edits, safety checks, and language-server support.

Audits a repository for how ready it is for AI coding agents, and returns a prioritized fix backlog with evidence for every finding.

「DSH·缓存账单」：在上下文圆环弹层里实时算账，缓存命中、未命中与输出各带 token 与金额，峰谷自动计价，第三方中转照常记账。

A Codex CLI plugin packaging a full software studio — 45 specialist roles, 91 workflow skills, and deterministic quality gates for game and

The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pausel

Git for your test database. Snapshot the databases behind a system under test, break them, put them back in seconds, and read their logs bes

「DSH·质量 diff」：接管 edit/write 及 extraTools 配置的其他工具卡片，行级去重与行内高亮，消除相同内容在删除与新增两区的重复；兼容 PTC 模式。

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and cust

A lightweight simulator app for iPhone, iPad, Apple Watch, Apple TV, and Apple Vision Pro.

DevOps secrets base: lightweight, self-hosted secrets manager in a single file

Local-first desktop control center for OpenAI Codex — sessions, models, tokens, accounts, providers, and AGENTS.md.

Keyboard-first Rust developer toolbox with a responsive Ratatui TUI and script-friendly CLI for encoding, parsing, hashing, text, time, JWT,

Open-source MCP control plane for AI coding agents: mechanical time-locks, evidence-gated proof receipts, red-team remediation, and persiste

面向 Codex 的本地可视化 Git 因果工作台

Find what's using a port, who started it (Claude Code, Cursor, Docker…), whether your network can reach it, and stop it safely. An lsof alte

A native, harness-neutral workspace for agent sessions, task graphs, diffs, and durable work — Pi first, Codex and Claude next.

Local-first coordination and authority layer for long-running human-agent projects

Monid, AI agent’ların farklı sağlayıcılardaki araçları tek bir arayüzden keşfedip çağırması için deklaratif connector’lar ve ortak bir çalıştırma katmanı sunuyor.

Neden yükseliyor · 37 günlük bir repoda 1.115 yıldızın yanında son 28 günde 49 commit ve 8 farklı yazar bulunması, ilginin yalnızca tek bir yazarın README iddiasına dayanmadığını gösteriyor. Yine de bu veriler üretim kullanımı veya benimseme düzeyini kanıtlamıyor.

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

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

The open startup repo — everything a founder needs to start and run a company in the agentic era: the comprehensive founder processes from a

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

A disposable copy of your production stack for every pull request: masked Postgres, contained third-party APIs, and agents that use your app

The Military-Grade Memory Hygiene, private, offline-first prompt manager for AI Agent power users. Features AES-256 encrypted local storage,

面向可信个人开发机的 MCP 编程运行时：Agent Transport、Windows Workbench、证据优先的项目连续性 | Personal-workstation MCP coding runtime