Havuz

Terminal pixel-art office for AI coding agents

Self-hosted personal finance OS — cash flow, net worth, budgets, and every income stream you own. Free for personal use.

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, C

Universal Retro Gaming Toolkit — convert, patch, compress and manage ROMs. PS1, PS2, Xbox, GameCube, Wii, Saturn, Sega CD and more. Window

tsk, a Linear alternative that stays in the terminal: a shared task board for you and your agents. TUI for you, CLI for them.

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

#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

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

TUI note-taking app in Rust — Yazi-style navigation, notebooks as independent git repos, real per-note version history, themes, and fast fuz

One simple SDK for transactional email across 23 adapters

An opinionated personal dashboard for your terminal — world clocks, calendar and agenda, weather, tasks, notes, markets and live system metr

Open-source SEO monitoring. GSC + Site Crawler + Core Web Vitals in one dashboard.

Dewarr, Goodreads ve Hardcover listelerini audiobook kütüphanesi ve indirme akışlarıyla birleştiren self-hosted bir uygulamadır.

Neden yükseliyor · Yedi günlük yaşına karşın 92 yıldız ve 246 commit dikkat çekici başlangıç ilgisi ve yoğun geliştirme gösteriyor. Ancak son 28 gündeki farklı yazar sayısının 2 olması, geliştirme faaliyetinin dar bir ekibe bağlı olduğunu gösteriyor; ilginin neden yükseldiğini bu verilerden tek başına belirlemek mümkün değil.

The open-source email platform — self-host on your own AWS SES, or use the cloud. Resend-compatible API.

first-pass, Claude Code ve diğer coding agent’lara değişiklik öncesi inceleme, bağımsız code review ve kanıt temelli tamamlanma kuralları ekleyen bir plugin’dir.

Neden yükseliyor · 5 günde 131 yıldız alması hızlı ilgiye işaret ediyor; coding agent’ların değişiklik çevresindeki riskleri kaçırması ve doğrulanmamış işi tamamlanmış göstermesi güncel bir sorun. İlginin özel nedenini veya kullanım yaygınlığını mevcut verilerle doğrulamak mümkün değil; son 28 günlük commit ve farklı yazar verileri de ölçülmemiş.

Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Harness for all major AI coding agents baked in.

A lightweight, all-in-one connection manager — SSH, Serial, SFTP, Telnet, FTP, WebDAV and S3 in a single TUI 🔥

AI pair programming in your terminal — one static binary, sub-ms startup, any model

Localhost, anywhere. One command gives your dev server a public HTTPS URL, with WebSockets and hot reload. Free, no account, runs on Cloudfl

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub A

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives

Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.

Local-first threat hunting for the logs you already have: Zeek, Pi-hole, syslog or the systemd journal, CloudTrail. Every run names the tech

A REST Client where the Repository is the Workspace

Privacy-aware trajectory viewer for local Codex task logs

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless re

ParseBench - A Document Parsing Benchmark for AI Agents

Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status l

~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

Real-time OSINT command center for the Iran/Israel and Russia/Ukraine theaters — 50+ live open-source intelligence sources (news, Telegram,

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

Autonomous, headless Android debugger designed for AI coding agents. Inspect runtime memory, set breakpoints, and debug live apps.

Your private network, wherever you work. Peer-to-peer first, end-to-end encrypted access to your own LANs — no port forwarding, no public UR

Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team proto

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

An Apple Reminders CLI for power users and AI agents. RemCTL supports all the latest Reminders features such as sections, subtasks, tags, ri

Self-hosted photo intelligence, enrichment, curation, and automation for your Immich library. Pictaria Server helps you explore and understa

Local-first AI e-commerce image suite generator for individual sellers. Pi Agent storyboards, 25 templates + reusable suites, product-truth

Open-source research workspace: search academic papers, upload PDFs, inline citations with on-PDF highlights, reader-mode Q&A, and get citat

Custom skins (visual themes) for the Hermes CLI agent

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

OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus.

Native macOS menu bar app & CLI to see what is listening on localhost, identify projects & processes, and gently close them. The safer alter

Open-source agentic ops platform for cloud, SRE, DevOps, support and FinOps teams. AI agents investigate incidents, cut cloud and Kubernetes

55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP

SkillRanker, agent oturumunun bağlamına göre kullanılabilecek skills öğelerini sıralayan ve sonucu CLI, JSON veya hook üzerinden sunan bir Rust aracıdır.

Neden yükseliyor · 10 günlük bir repoda 121 yıldız ve 962 commit dikkat çekiyor; agent skills seçimi güncel bir geliştirici aracı ihtiyacına hitap ediyor. Ancak commitlerin tamamının tek yazardan gelmesi, bu hareketliliğin bağımsız katkı veya benimsenme kanıtı olmadığını gösteriyor; yükselişin kesin nedeni mevcut verilerden anlaşılamıyor.