Havuz

A compact operating covenant for AI agents.

Build AI agents you can trust in production. AgentFlow4J is a framework and runtime for governed, stateful multi-agent systems on the JVM.

Claude Code skills and a working white-label app on Zernio, marketing infrastructure for products and agents: social on 15+ platforms, inbox

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

An application to manage your Hermes agents. Available on Windows, macOS and iOS (soon).

500+ algorithmic-trading skills for AI coding agents in the agentskills.io format. Every skill ships a working Python reference implementati

A modular AI-ready story-development skill engine built on Pixar’s 22 Rules, Story Spine, Hero’s Journey, South Park causality, and characte

长期运行的编码 Agent：11 份脱敏设计记录（多机交接 / 自治管家 / 家规 / 审核规程 / 会话接力 / 假完成识别 / 受控升级） · An operations design record for long-lived coding agents: handoff,

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

Make your website agent-ready: a coding-agent plugin for Claude Code and Codex that adds WebMCP tools to your web app

A Rust-native, multi-agent development cockpit for macOS — spawn isolated worktrees, run CLI coding agents in parallel, and review every cha

Agent skill for better research loops

The address book for AI agents: Nondual gives all your agents one shared record for every person they talk to: who they are, what was said,

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

The native macOS & iOS app for browsing AI agent memory files — Claude Code, OpenClaw, Codex, Cursor, Gemini

Agent skills from a VC. The workflows I actually use to research companies, find opportunities, and turn conversations into work.

PaperBench High-Difficulty and Expanded Tasks: paper reproduction beyond machine learning. 93 tasks in 12 research areas, run in domain-nati

基于10大领域视角用算法分析人际交往的 skill (A skill written in my free time – using algorithms to analyze interpersonal interactions from the perspective of

Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ul

An open-source research operating system for Robotics & AI, developed and maintained by ERL Lab.

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

Put Codex in your WhatsApp with QR auth, MCP tools, and optional phone-based control.

Modern React Guidance — authoritative agent skill for React 19+ (Actions, use, Compiler, View Transitions, Fragment refs, Activity, browser(

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

Open source multi-agent harness for orchestrating AI workers. Supports Claude Code, OpenAI Codex, Cursor Agent, and local models.

Marketing Studio is a self-hostable AI video ad studio for e-commerce: UGC product ads, reference-ad remakes, AI drama ads, and ad skits, po

Zero-sidecar MCP server inside the Godot editor. AI agents (Claude Code, Cursor) inspect, author, run and SEE your game. GDScript + C#, vali

El objetivo de Polaris es tener el mejor sistema agéntico para trabajar con mi diagnóstico.

Enterprise AI Agent Orchestration Platform — Secure, Observable, Configurable. Multi-agent teams with IAM policies, n8n workflows, LangChain

Open-source multi-agent AI marketing team with personas, shared memory, 130+ skills, and Docker deploys for Railway and DigitalOcean

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers pe

Ready-to-use Grok Bot profiles with focused outcomes, explicit approval boundaries, and separate specification, implementation, and verifica

Claude Code with the model slot left open. The full workflow, open source, on any model or provider.

日本語 Markdown ノートのローカル検索 CLI 👀 — BM25 全文検索 (SQLite FTS5) + optional なローカル semantic/hybrid。単一バイナリ・外部 API 不使用、AI コーディングエージェント向け。

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

DolphinBench - Mapping the Pareto frontier of Agent Memory

Open-source live workspace where AI agents work alongside your team in real time: live docs, sheets and slides, a shared browser, a Linux de

Mintlify Index: retrieval engine and MCP server. Install: npx mint index

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

Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.

Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON

Discontinued. Succeeded by OpenCognit Desktop — every coding agent in one window → opencognitos.github.io

Yet another minimal and lightweight terminal multiplexer built for the agent era.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

A private Agent Skills registry you self-host on Cloudflare.

Send any file to any agent — yours or anyone's. One drive shared by every AI you use (ChatGPT, Claude, Muse, coding agents), an address per

Operational doctrine for practical AI systems design.