Havuz

Literature-grounded research idea exploration for CLI agents. 文献驱动的研究选题与方向探索工具。

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and

Codex-first Agent Skills library for premium frontend, website, motion, accessibility, QA, and handoff workflows.

Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison,

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to ru

Your private, searchable work timeline for macOS and local AI agents.

One MCP server for the whole self-hosted media stack: Radarr, Sonarr, Whisparr, Lidarr, Prowlarr, Bazarr, Jellyfin, Plex, Seerr, SABnzbd, NZ

TradingView MCP server: search indicators and strategies, fetch Pine Script source. Works with Claude Code, Claude Desktop and Cursor. No AP

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

A fast, keyboard-driven HTTP intercepting proxy and pentesting toolkit for the terminal built for humans and AI agents alike.

Make narrated vertical shorts (TikTok, YouTube Shorts, Reels) with a coding agent and Remotion. 9+ agent skills, 20+ story flows, fact ledge

Skill pack for Claude Code that helps you monitor and troubleshoot your K8s clusters superintelligently

Claude Code plugin with 14 composable marketing skills: competitor research, content calendars, SEO briefs, ad copy, cold outreach, short-fo

Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.

Observability platform for Digital Employee, providing real-time tracing, session insights, and cost analysis for multi-agent workflows

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and

AI-powered FL Studio control via the Model Context Protocol. Beyond piano-roll notes — full in-DAW mixing (Mix Doctor, gain staging, EQ/comp

Open-source YouTube AI video editing system: Eyeline teleprompter, editing agents, JSON, Claude Design, animation and motion graphics.

Open-source TypeScript framework for building operational software used by humans and AI agents.

smol is a smol agent

Control your Android phone with natural language. No computer required. Powered by Midscene, with Skills and a Codex plugin.

Seedance 2.5 Shot Design Skills

AudacityMCP connects any MCP-compatible AI assistant to Audacity, giving it full control over audio editing through 144 tools and 9 pipeline

The first open-source repository for Scientific Machine Learning (PINNs, PIELM, RFM, Neural Operators) via Vibe Coding. JAX-GPU implementati

Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware tabl

A visual manager for fleets of Claude Code, Codex and Muse agents — real terminals, agents that message each other, teams that run tickets o

Instant messaging between coding agent sessions — Claude Code, Codex, opencode, Cursor CLI, MiniMax Code and ZCode — across tools, to other

Zero-config entity resolution feeding a durable identity layer: messy records from any source become stable golden entities, a Customer 360

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

Open-source NURBS surface modeller — a Rhino-style freeform modeller on the OpenCASCADE kernel, with AI-native MCP integration

Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tas

Codex/OpenClaw skill for generating images with ChatGPT/Codex OAuth

把你的网易云歌单与听歌排行变成一份深度自我画像 —— 支持 Windows / macOS 的本地数据采集与 AI 画像分析 Skill

Unofficial Agent Skill for Claude Code and other SKILL.md-compatible agents, driving ArvanCloud's APIs (CDN, DNS, IaaS, Object Storage, Edge

Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).

Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and

The Open Analytics design language as an agent skill: component recipes with type-checked source, token CSS, and a CLI. Works with Claude Co

Voice-driven multi-agent assistant — Realtime API + CLI runners + multi-channel orchestration.

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger,

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.

🎮 Codex Micro functionality using any Gaming Controller on any Coding Harness!

人格蒸馏引擎 · 蒸馏自己看清自己，蒸馏亲友留住余温与回声 · Claude Code Skill

Memory-safe Rust controller for your own Sonos speakers on your own LAN — reliable SSDP/UPnP-SOAP/GENA interoperability (S1 + S2), a Spotify

Declarative dynamic forms engine. Define dynamic forms with a typed TypeScript builder or as JSON, then render them in React, Angular, Vue,

Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaint

Open-source, model-independent Agent Skill for evidence-based software reconstruction with REA. Optional integration, portable installer, an