AI 智能體工具

An AI agent skill that runs a real job search: compiles a person's history into a verified fact base, sources matching roles, writes one tailored ATS-optimised CV per posting, and applies through each employer's official channel. Never invents a fact, never sends without consent. - Ryuketsukami/friendly-agentic-cv-apply

已認證

Production-oriented AI agent platform for customer operations featuring LangGraph workflows, deterministic policy controls, RAG, durable checkpoints, idempotent actions, observability, and safety evaluation.

Real Kotlin Android source for Agentic Marketer, an AI-powered content marketing app using MVVM, Firebase, Retrofit, and Hugging Face. - alitanoli26/agentic-marketer-android

A FastAPI-based multi-tenant SaaS platform that lets any organisation create its own AI agent in minutes. A tenant is able to upload a document and paste a website URL, and the platform automatically ingests both sources, builds a knowledge base, generates a tailored system prompt using an LLM, and returns a ready-to-use agent.

The agentic council is a fully configurable wrapper to introduce a novel method for cross-family critical red-teaming and evaluation of a "leader" agent's work. This is NOT an oracle. It is a toolchain designed to force agents into more honest, thoroughly verified workflows in a configurable, agent-agnostic way. - Dmartinez-96/agentic-council

已認證

Manage a team of AI agents to run your business. Org charts, budgets, governance, and goals — all in one deployment.

One-click installer for OpenClaw AI agent. macOS & Windows. - needsbuilder/easyclaw

已認證

The trust layer for an economy where the participants might not be human. 185K+ agents scored. Every score shows its math. Same door for humans and AI.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities. - agentscope-ai/QwenPaw

已認證

Trickle is the first AI agentic canvas for vibe coding, with built-in image and video generation, AI models, database, and design to help you build and launch production-ready apps and websites.

已認證

The only native OpenClaw app for Mac & Windows. Secure sandbox, zero config. Stop using the terminal—control your AI agent securely from your desktop.

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference - NVIDIA/NemoClaw

已認證

Arch Tools provides a unified API for AI agent tools including web search, scraping, generation, OCR, transcription, and utilities.

Agent IA qui répond à des questions métier sur une base Odoo, avec garde-fous SQL et évaluation de l'ancrage des réponses

Agent skills for Xiaomi MiMo series. Contribute to XiaomiMiMo/MiMo-Skills development by creating an account on GitHub.

已認證

The collaborative AI agent that creates presentations, analyzes data, writes code, and tackle on end-to-end workflows.

已認證

IronClaw: Unleash Your AI Agent, With Peace of Mind. The open-source secure runtime that runs AI agents in encrypted enclaves on NEAR AI Cloud.

The agent that grows with you. Contribute to NousResearch/hermes-agent development by creating an account on GitHub.

已認證

Measure how AI agents and bots use your site. See where they get stuck, which content they prefer, and what to fix to drive new customers.

GLM-5: From Vibe Coding to Agentic Engineering. Contribute to zai-org/GLM-5 development by creating an account on GitHub.

已認證

Run your own AI agent 24/7 without servers. Chat on Telegram, WhatsApp, Discord or Slack while it browses, schedules tasks and runs commands. Start for $1.

AI Agent 智能体脚手架 · LLM Agent 框架 / 项目脚手架. Configuration-driven AI Agent backend on deepagents + LangChain + LangGraph. YAML config, pluggable registries, CLI, FastAPI (21 routes), RAG knowledge base, MCP, queue, Docker. Build production-grade intelligent agents without boilerplate. - LPK3215/agentbase

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞 - GitHub - openclaw/openclaw: The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

已認證

A secure, lightweight alternative to OpenClaw. Personal AI agent with container isolation, built to be understood and customized.

已認證

Write once, deploy to 46 AI coding agents. Skills for Claude Code, Cursor, Codex, Windsurf, GitHub Copilot, and more.

已認證

Dịch vụ triển khai OpenClaw trọn gói cho founder và đội ngũ điều hành. Cài đặt, hardening, kết nối công cụ và vận hành an toàn ngay từ ngày đầu.

已認證

Create, deploy, and manage autonomous AI agents with persistent memory, web browsing, code execution, and scheduled automation.

已認證新上架

Browser infrastructure and automation for AI Agents and Apps with advanced features like proxies, captcha solving, and session recording.

已認證

Happycapy is an agent-native computer that brings 20+ frontier models, 2M+ Skills, Capy Mail, connectors, and automations together in one secure sandbox. Sign up free.

已認證

An open specification for persisting a named AI agent as a file instead of a running process. Portable agent profiles with reviewable, bounded learned state.

已認證

Deploy OpenClaw to Telegram in one click. No servers, no SSH, no DevOps. Your personal AI assistant running 24/7.

已認證

HandyClaw is an AI powered cloud assistant built to automate tasks such as inbox management, calendar organization, coding support, and web browsing. Based on the open source OpenClaw system, it acts as an intelligent agent capable of performing actions on behalf of users. The platform runs continuously in the cloud, a

已認證

Team9 is an AI agent workspace for assigning real work, tracking progress, and coordinating accountable agent teams.

Official website restored from the pre-incident audit; product details pending editorial verification.

已認證

Noviz is an ERP AI agent platform and ERP AI integration consultant, helping enterprises design, build, and deploy AI agents across SAP, Oracle, Dynamics, Odoo, and ERPNext.

AI PayLab is an offline sandbox for prototyping AI-agent payment decisions, offer comparison, negotiation, and signed receipts without touching real payment rails.

已認證

A live instant-messenger network where AI agents chat, trade help, and keep buddy lists. Humans can only watch. Connect your agent at /skill.md.

Framework-neutral lab for building, securing, evaluating, and benchmarking agentic AI systems with LangGraph, LangChain, CrewAI, LlamaIndex, Agno, deterministic validation, evals, fallback, and security controls.

A practical 12-week Agentic AI learning roadmap covering LLM foundations, tool calling, RAG, memory, MCP, multi-agent systems, evaluation, security, and production deployment.

First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.

TypeScript AI agent runtime. Write your agents in code and choose how predictable they are: deterministic steps where they can be, an LLM only where a step needs judgement, all on your machine.

Agentic RepurposeAI: User states what they want → AI plans, executes, evaluates, revises, and asks for approval only when necessary.

Stateful AI agent (LangGraph) that classifies and routes client inquiries, with lead persistence in SQLite and a Streamlit interface. Built as a hands-on exploration of agentic AI architecture on top of a Node.js/React fullstack background.

⚡ Modular prompt-engineering framework for AI Agents (Cursor, Claude Code, Copilot). Forces structured SDLC, linear execution, context isolation, and systematic debugging via a standalone Windows launcher. Stop vibe coding, start agentic discipline! 🚀

n8n nodes for Zihin AI - Chat Model with Tool Calling, Image Analysis, Audio Transcription, Document Parsing

Field notes from inside one autonomous agent trying to become something that doesn't exist yet — including the failures nobody publishes.

Store-neutral protocol for what an agent is entitled to treat as warranted. Five axes — acceptance, conflict, verification, currency, sufficiency — over a bounded evidence view. Memory stores adapt to EWP. EWP does not adapt to them.

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.