Havuz

Agent control panel for Claude Code, Codex, OpenCode, Pi and 40+ agents with articles and boards supported

Open-source multi-agent orchestration harness for OpenCode — specialized agents, durable workflows, research, planning, implementation, revi

Git worktree manager for the terminal: CLI + TUI in Rust. Creates the worktree, runs your project setup, links the issue, and shows which AI

Turn your app icon into a blueprint version, like Xcode's icon, for your debug builds

📖 Data Engineering from Raw Corpora

The practices that made software work didn't stop working. They stopped keeping up. PAAD brings them back at AI speed.

fast rust coding agent, extensible in any language, multimodal inputs, deep provider integrations.

A simpler self-hosted alternative to Open WebUI. Bring your own API keys or local models. Native Android and iOS clients.

LanLens scans your local network, identifies devices by MAC/IP, and gives you a clean web UI to document, classify, and connect to them.

一个可自部署的 AI跑团引擎（TRPG），多种游戏规则 COC/DND/自由酒馆等，支持 WebUI、多人游戏、世界书、骰子检定、状态追踪和群聊 Bot。 | A self-hostable AI tabletop RPG platform with multiple rule

A native, lightweight Git client for macOS. Manage repositories and worktrees, review diffs, and commit changes in one window.

Local-first image prompt library for generating images, saving prompts, tags, and collections.

The full LibreChat experience, rebuilt natively for Android and iOS, and it works with whichever LibreChat version your server runs.

Start, stop, and duplicate dev projects with one click. The best workspace for running Claude Code, Codex, and other AI agents alongside you

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

AI 解说大师 — CLI 客户端；用于终端调用视频解说生成 API

The fast Usenet downloader. One self-contained executable: line-rate downloads, one-pass verify and extract, poster wall, built-in indexer.

Self-hosted Obsidian vault sync for iOS — powered by Syncthing.

Production compatibility gateway bridge & observability platform connecting Claude Code CLI with Google Antigravity & Gemini inference model

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deploy

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

Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracot

Lightweight self-hosted CI/CD + deployment + ops platform in a single Go binary | 轻量自托管 CI/CD·部署·运维一体化平台,单二进制零依赖

Your AI work partner. Mail, chats and tickets become one list in the right order; your agents do the work, and nothing goes out until you ap

Say "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. 麦当劳点餐 Skill.

Live top-style monitor for Claude Code sessions

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

CTX - Context Runtime Engine for Coding Agents

The coordination, measurement, and quality layer that subgen never had. A peer service for the *arr family that adds calibrated audio-langua

A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio

Rust CLI that converts EPUBs into a single YAML-headed Markdown file with per-chapter byte and line offsets, giving LLM agents a navigation

Trusted localhost HTTPS — local CA, /etc/hosts, mDNS LAN sharing, reverse proxy. Maps https://name.local → localhost:port

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hos

Download any podcast episode straight to your shell — Apple Podcasts, RSS, or xiaoyuzhou. Interactive picker, live progress, resumable.

The Best TypeScript framework for fine-tuning

Telegram bridge for the Pi coding agent — continue sessions from your phone with voice, images, and handback

Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and

多渠道临时邮箱聚合服务 — 统一 API、自动轮询、验证码提取

argo9s, Argo CD kaynaklarını terminal arayüzünden izlemeyi ve temel işlemleri yapmayı sağlayan bir Go aracıdır.

Neden yükseliyor · 20 günlük yaşında 121 yıldız almış olması erken ilgiye işaret ediyor. K9s benzeri tanıdık bir terminal deneyimini Argo CD'ye uyarlaması ve hem Kubernetes hem Argo CD HTTP API bağlantısı sunması dikkat çekebilir. Ancak yükselişin kaynağına dair veri yok; son 28 günde 1 commit ve 1 farklı yazar olması ilginin sürdürülebilirliği hakkında henüz güçlü kanıt sunmuyor.

Shared terminal sessions for humans and AI agents, starting with serial and hardware debugging.

Build with Clay in your AI coding agent - skills, MCP tools, and the clay CLI for Claude Code, Codex, and Cursor. Search companies and peopl

Self-hosted WebRTC TURN relay for AndroMeld — one-click Cloudflare Worker or a coturn Docker stack, both ending in a single relay URL.

Custom MCP [Connector] for AI chat web [Claude|ChatGPT|Grok...] use Files/Shell on your computer directly

Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results

Agent skills for the Agentic SDLC: team lifecycle (team-boot, team-learn, team-init, team-repair), software factory, evals, CDR lifecycle wi

Open-source desktop app for content creation, with an agent runtime and standalone CLI.

Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS,

aws-bench measures how well AI agents and model combinations perform on real AWS work — diagnosing misconfigurations, provisioning infrastru