Havuz

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

HTML Anything, yerel coding-agent CLI’larını kullanarak HTML içerik ve tasarım üretmeyi, önizlemeyi ve farklı formatlara aktarmayı sağlayan bir editördür.

Neden yükseliyor · 139 günde 8.954 yıldıza ulaşması belirgin ilgi gösteriyor; yerel agent oturumlarını kullanma, API key gerektirmeme ve çok sayıda hazır çıktı şablonunu tek arayüzde sunma vaadi dikkat çekici. Ancak ilginin kaynağı kesin olarak bilinmiyor ve son 28 gündeki 1 commit ile 1 farklı yazar, mevcut yıldız ivmesinin geliştirme aktivitesiyle desteklendiğine dair sınırlı kanıt sunuyor.

A field guide for go to market teams using coding agents. Installable skills for campaign planning, CRM context, customer proof, and reviewa

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Official Aspire skills and plugins for AI coding agents to initialize, wire, orchestrate, monitor, and deploy distributed apps.

Agent skills for daily use

repository-harness, coding agents için bir depoya yönergeler, dokümantasyon yapısı ve güvenli güncelleme mekanizması ekler.

Neden yükseliyor · Coding agents için depo içi bağlam ve çalışma kuralları güncel bir ihtiyaç; 145 günde 1226 yıldız da ilgi gördüğünü gösteriyor. Ancak son 28 günde commit ve farklı yazar olmaması, bu ilginin güncel geliştirme faaliyetiyle desteklenmediğini düşündürüyor.

🎨 Open-source design MCP server + shadcn/ui registry — AI design systems for Claude Code, Cursor, Codex, GitHub Copilot & any MCP client. 31

Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.

Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.

Run Claude Code, Codex, Kimi, OpenCode, Hermes and one of the 26 other coding agents using MCP , CLI or TUI , WebUI.

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release

Agent skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of "97 Things Every Programmer Should Know"

Pre-build idea-to-spec workflow skills for Hermes Agent: turn rough ideas into design docs, implementation specs, and Superpowers-ready buil

A Complete faster runtime for coding agents. Optimize the journey, not the hop. Make coding agents 25% faster and 30% cheaper on average whi

Superpowers workflow skill pack adapted for Hermes Agent and ChatGPT

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

AI terminal for coding agents: run Claude Code, Codex, and shells side by side on your computer or remote servers. Agents ask each other for

Understand what your codebase builds, why it is structured that way, and what a change could affect. One shared Markdown ontology for human

Git-native memory for coding agents. Repo memory before the diff.

Local, open-source (Apache 2.0) voice layer for Claude Code and Codex on macOS that reads your coding agent's progress aloud. Kokoro text-to

Global instructions for coding agents: evidence, parallelization, validation, all in one AGENTS.md / CLAUDE.md

Edit Videos and Design Images with Claude code or Codex

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas.

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop

Archify, coding agent’lara açıklamalardan veya repository içeriğinden etkileşimli mimari ve sistem diyagramları ürettiren bir agent skill’dir.

Neden yükseliyor · 166 günlük yaşına göre 72.324 yıldız ve son 28 günde 84 commit ile 27 farklı yazar güçlü görünürlük ve yakın dönem katkı sinyali veriyor. Agent ekosistemindeki yaygın araçlarla entegrasyon ve etkileşimli demo galerisi ilgiyi destekliyor; yıldız sayısı tek başına kullanım veya kalite kanıtı değil.

All of your agents, shells, and TUIs in one durable terminal workspace

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using C

Ekko Studio, birden fazla AI agent runtime’ını ortak chat, coding ve visual workflow arayüzünde birleştiren local-first bir masaüstü ve self-hosted web uygulamasıdır.

Neden yükseliyor · 169 günde 11.205 yıldıza ulaşması dikkat çekiyor; son 28 gündeki 204 commit ve 10 farklı yazar da yalnızca README iddialarından ibaret olmayan güncel geliştirme faaliyetine işaret ediyor. Yıldızlar benimsemenin veya kalitenin kesin ölçüsü değil.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Her

A native macOS terminal for agent-driven development, built on Ghostty.

ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth befor

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

Coding Agent insights for teams

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware revi

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agent

Open-source agent sandbox infrastructure for parallel coding agents: isolated workspaces, MCP/CLI control, observability, and atomic publica

Agent skills for coding CLIs, multi-agent runtimes, context engines, MCP extensions, and terminal tooling. Instead of using claude code's so

Open-source local workbench for multi-agent software development.

Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated editor. Built with Rust and GPUI

Human-in-the-loop multi-agent task orchestration platform for Git-based software workflows.

Browse, create, and edit AI agent files across Claude Code, Cursor, Codex, and 12 coding tools — from Obsidian.

herdr, coding agents için kalıcı terminal oturumları, çoklu makine bağlantısı ve agent durum takibi sağlayan Rust tabanlı bir terminal çalışma ortamıdır.

Neden yükseliyor · Coding agent'ları için oturum yönetimi ve görünürlük ihtiyacına doğrudan odaklanıyor. 184 günlük yaşına karşılık 40.915 yıldız ve son 28 günde 269 commit ile 11 farklı yazar verisi, yalnızca README iddialarından ibaret olmayan dikkat ve geliştirme faaliyetine işaret ediyor.

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concept

Stop Claude Code/Cursor from guessing UI. Extract any website's design system into a spec-valid DESIGN.md that passes the official @google/d

Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and

The design layer for agentic AI — design context, interface checks, and verification for coding agents.

Run many CLI (Coding) Agents in parallel lanes: issues, worktrees, sessions, and loops on one board. The agentic development environment.