Havuz

Loop Engineering, kodlama agent’larını bir repository’deki bakım ve geliştirme işleri için planlayıp denetlemeye yarayan pattern’ler, starter’lar ve CLI araçları sunar.

Neden yükseliyor · 110 günde 11.318 yıldız ve son 28 günde 68 commit ile 8 farklı yazar, belirgin ilgi ve yakın dönem geliştirme aktivitesi gösteriyor. Bu veriler benimsemenin veya etkinliğin başarısını tek başına kanıtlamaz; ilginin ne kadarının gerçek kullanıma dönüştüğü verilen bilgilerden bilinmiyor.

Replay your coding agent sessions as a map and a timeline

AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools

clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves

pilot: AI That Ships Your Tickets for Automated Development

#1 Product of The Day @ Product Hunt. The GTM co-founder you don't have. Open-source GTM Agent Skills for developer tools and AI products, f

Wireshark for MCP. A transparent proxy between your AI client and MCP server. Watch every call live in your terminal, fail CI on what it fin

Profile-based coding runtime for Claude Code and Codex. Lean core; opt-in quality, context, memory, orchestration and dashboard.

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, a

Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.

Claude in Chrome, reverse-engineered and open-source. No domain blocklist. Any Chromium browser. Same 18 MCP tools, same performance.

Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in

htop for your Claude Code sessions — real-time cost, cache efficiency, model comparison, and smart alerts

🚀 Automated scraper & injector for 100+ free AI coding models into 9router combos. Live pre-tested, ranked by coding benchmarks & zero-conf

One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, and deploy across all major AI

A polished terminal UI (TUI) for the pi AI coding agent — real-time chat, multi-provider LLMs, tools and sessions. Built with Go and Bubble

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into

See your codebase as a living architecture map — then edit the map and let Claude build the code

⌘-click an element in your running app, say what to change, and Claude, Codex, Cursor or another AI agent opens with the exact file and line

Stop babysitting Claude Code. A free, open source terminal workspace: run every session side by side, and answer Claude's prompts from your

Point at any part of your running app, describe the change, and Lasso edits the real source file — not the DOM. Works with Vite and Next.js.

What your AI coding agents actually cost — by task, branch, model and file. Runs locally, dashboard on 127.0.0.1:4976, no telemetry.

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat

MCPSafari: Native Safari MCP Server for AI Agents

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

Comprehensive multi-agent code review for Claude Code

Write your repo rules in Markdown. AI enforces them — triages issues, reviews PRs, fixes bugs, merges code, cuts releases.

⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel,

Turn Claude Code into an autonomous software development team — 16 specialized agents, documentation-first pipeline, TDD slices in parallel

An AI desktop app that runs on your own keys. Chat with any model, let always-on Workers take jobs off your plate, and run every coding agen

Browser automation for AI agents in your real, logged-in Chrome. You watch every action and can veto any tab. Chrome extension + zero-depend

Hand a live Claude Code, Codex, or opencode session to anyone with three spoken words - encrypted, no account. Or carry your whole Claude Co

One interview writes AGENTS.md and agent skills for your project, plus git and agent hooks that enforce them. Works with Claude Code, Cursor

🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8

AI-powered code review agent for GitHub pull requests. Self-hosted GitHub App using PI.

Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by

Give AI coding agents product, spec, task, QA, and release workflows in one command.

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-

A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

Claude/Grokbot plugin and scripts: long-running controller pattern to chunk and delegate code work to cli-agents, with embedded adversarial

Remove Claude/AI attribution from a GitHub repo in one command clean commit history, force-push, and refresh the Contributors graph so @clau

Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI wo

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approv

Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and befo

Spine — governed, provenance-grounded autonomous software delivery (installs as agent-orchestrator).

Local-first tool to visualize and analyze Claude Code, Cursor, Pi & OpenCode sessions — context tokens, LLM insights, governance artifacts.

Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.

Turn your Claude Code / Codex subscription into a Feishu agent your whole team can @