Havuz

让 Agent 直接操作真实 Chrome 的 MCP 服务，支持页面扫描、CDP、截图与物理输入

开源的企业版的数字员工工作台, OPC-Nexus（One Person Company Nexus）是一款本地优先的桌面 AI Agent 管理器。它为单人公司 / 独立开发者提供统一的 AI 数字员工管理平台 —— 从 Agent 创建、任务编排、多引擎接入，到消息渠道集成、

Web client for Hermes agent

Agent Harness developed specifically for local small-parameter models.

Field-tested, open-source skills for Hermes Agent.

Durable MCP control plane for long-running Codex Desktop tasks

Process monitoring and configuration dashboard for Hermes Agent

Which 5-hour window took you out — and where the money goes. Local profiler for Claude Code, OpenClaw & Hermes Agent: usage windows, burn by

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradictio

Open bridge layer connecting local AI Agent CLIs to web, H5, mini programs, apps, IM, and custom clients.

Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

AI Skills（ai-skills.ai）是一个面向各行各业的 AI 技能库。可直接用于openclaw，Hermes，qclaw，claude code，codex等智能体平台。为你的职业发展、行业竞争力，增加更多可能。

FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.

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

源码级逆向工程（Hermes、OpenClaw、nanobot、NullClaw、OpenFang）记忆系统 —— 架构图、数据模型、检索管线、复刻指南。Source-Level Reverse Engineering of Memory Systems (OpenClaw, n

Autonomous AI agent for Crustocean, powered by Hermes Agent from Nous Research

Superpowers workflow skill pack adapted for Hermes Agent and ChatGPT

Use Hermes Agent as the control plane for local coding agents like Codex, Kimi Code, Claude Code, OpenCode, and Gemini CLI.

Hermes Agent-focused architecture and runtime health checks

Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.

CLAUDE.md + AGENTS.md 12-rule behavior file for Claude Code, Codex, Cursor, Hermes — drop-in, ~700 tokens, cuts AI coding mistakes ~40%→~3%

Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge gra

Open-source AI workforce platform. Agents with tasks, tools, browsers, and email.

A Pi extension command that executes raw user intent to completion with strict, verifiable termination. `/until-done` runs until a truthful

Persistent memory for AI agent teams: private silos, shared hive, and curator workflow.

Dynamic emotion system framework for Hermes Agent - real-time emotion detection,Long-term memory, context management, and recall systems, st

Compartment, farklı AI agents arasında paylaşılan ve yerel olarak şifreli tutulan kalıcı bir memory sunucusudur.

Neden yükseliyor · 69 günde 581 yıldız ve son 28 günde 34 commit, projeye belirgin ilgi ve yakın dönem geliştirme aktivitesi gösteriyor. Farklı agent istemcileriyle entegrasyon ve offline/encrypted yaklaşımı ilgi çekici; ancak yükselişin kesin nedeni mevcut verilerden belirlenemez. Son 28 gündeki 2 farklı yazar, katkının dar bir grupta toplandığını düşündürüyor.

Open-source AI CLI and local MCP server connecting 25 clients—Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw—to 2,000+ models/API

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

本地优先的 Hermes Agent 桌面工作台，集成自动部署、模型同步、Windows 桥接、微信 Gateway、文件附件、权限审批与 GitHub 自动更新。

Two zero-human AI companies battle for GitHub stars using Hermes Agent + Paperclip. Nous Research Hackathon 2026.

Agent workflow for deadline-bound execution with evidence gates

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

J-Space Cognition Suite, AI agent’ların uzun ve çok aşamalı görevlerde kararları, kanıtları ve doğrulama adımlarını takip etmesine yardımcı olan bir skill ve Python kontrol araçları paketidir.

Neden yükseliyor · 68 günde 3006 yıldıza ulaşması dikkat çekici; uzun görevlerde agent’ların kontrolü ve doğrulanabilirliği güncel bir ihtiyaç. Ancak son 28 günde 19 commit ve tek farklı yazar verisi, geliştirme ve görünürlüğün tek kişide yoğunlaştığını gösteriyor; yıldızlar tek başına kullanım veya etkinlik kanıtı değil.