Havuz

观澜 / Guanlan：AI Agent 的中文互联网研究、阅读与信源路由工具。

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

Candid reviews of Claude Code skills. File:line citations. Ranked actions. No filler.

One command to turn any codebase into an MCP server

The One Dashboard every Voice Agent needs

Rucio P2P file sharing

多智能体小说写作框架 | Multi-agent novel-writing framework — 每个角色都有自己的脑子,每一章都有质量门禁

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

Free SEO keyword research toolkit for indie builders. Zero dependencies, pure Python.

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

Architecture-aware code search, dependency graphs, and impact analysis for Python, TypeScript, Rust, C#, Java, Go, Ruby, Rails, Free Pascal,

Capture Kubernetes cluster state to a portable archive and replay it through a mock API server — use kubectl against a customer's environmen

Multi-agent Claude Code skill for building apps and stuff

One free AI endpoint, every free tier behind it. Local OpenAI-compatible gateway routing across OpenRouter, Groq, NVIDIA NIM, Cloudflare Wor

A native macOS menu bar app that shows your Claude.ai usage at a glance — colour-coded icon, live counter, reset timer. No API key needed.

Find memory leaks in your single-page web app in minutes rather than hours, with Playwright.

零框架零依赖的个人博客系统 — 双击 index.html 即用，支持 Cloudflare Workers + D1 云端部署

Self-hosted GPT Image 2 / Image-2 workbench for teams: text-to-image, image-to-image, templates, quotas, history and admin dashboard.

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

Manage GitHub PR Stacks natively with `jj`

CodexMeter：本地运行的 Codex 用量监控桌面工具，支持 5 小时 / 7 天额度、重置时间、小组件和本地安全存储。

Turn scattered, duplicated AI-agent Skills into per-Agent Rosters—with evidence, receipts, and exact undo.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

A team of AI agents that runs your job search — self-hosted, on your own LLM subscription. MIT.

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

SYNCLE keeps multiple databases in sync, live, without kafka.

Guarded, recoverable web ChatGPT automation for local Codex projects on Windows and macOS

File leasing for AI agent teams. One MCP server. Any IDE. Zero merge conflicts.

PPP pricing for App Store apps — bulk-update IAP & subscription prices in 175+ countries by purchasing power. Free CLI, agent-friendly (Clau

Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before pow

Convierte informes de brokers extranjeros en declaraciones fiscales españolas: Modelo 100 (Renta), Modelo 720, Modelo 721 (cripto) y D-6. 10

Agent PI - Agent Development Environment (ADE)

pick any past Claude Code session via fzf, then resume it from the right cwd

The fastest way to setup and manage Git Profiles. A terminal UI + CLI to switch git identities, SSH keys, GPG signing, and GitHub profiles i

Free, open-source macOS storage and cache cleaner built for developers. Scans Docker, Xcode, Node.js, Ollama, JetBrains, Homebrew, and more.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows,

Advanced AI platform

Kraivor is an AI-powered system that analyzes real-world codebases and simulates how they behave under production stress, failures, and scal

Review your working changes like a pull request — in the terminal. Block-scoped live diffs, GitHub/GitLab PR review, and send-to-AI-agent.

OpenCode Garbage Collector. Analyze and reclaim storage used by OpenCode sessions, diffs, and snapshots

Turn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more chat apps. A judge revi

Terminal-native AI assistant built specifically for Termux and Android development.

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance

Generative rocket greeting for a bash, zsh, fish, and PowerShell — every new terminal spawns a unique, deterministic artwork

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI,

A statistical code analyzer built from your repository's history.

"Linux? Nah. WinUX!" Windows auto-patcher for vibe coders.

External-agent-first orchestration for AI coding workflows: dispatch to Antigravity CLI, Grok CLI, Claude Code, and Codex CLI with structure

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

Open-source benchmark of 5 intentionally vulnerable web apps with 100 baseline vulnerabilities for evaluating AI penetration testing agents.