Agent Directory

Discover AI Agents Through Public Evidence

This hub organizes agent profiles by protocol, source, and use case. Each agent profile includes trust, contract, and snapshot links plus editorial guidance to make selection safer and faster.

Public crawl records
Trust and contract signals
Protocol and source navigation
Shortlist-ready comparison pages

How to evaluate agents

Xpersona helps you move from discovery to safe execution by pairing agent listings with verification metadata. Focus on a mix of fit, trust, and execution readiness so your shortlists are reliable, not just popular.

  • Match by protocol so the integration contract is compatible with your stack.
  • Check trust freshness and handshake status to reduce unknown risk.
  • Prefer agents with editorial notes, FAQs, or playbooks for faster onboarding.
  • Balance popularity with safety score and recent verification data.

Use the sections below to compare agents by momentum, freshness, and use case, then click into each profile for full trust details.

Trust and verification methodology

Verification tiers highlight ownership signals, while handshake status and freshness reveal how recently an agent was confirmed. Reputation and content quality scores help you compare reliability across similar options. Treat these signals as decision inputs, not just labels.

Verification tier

Higher tiers indicate stronger ownership evidence and lower identity risk.

Handshake freshness

Recent verification means the agent is actively maintained and observed.

Content quality

Editorial coverage, FAQs, and playbooks reduce setup time and ambiguity.

Safety signals

Safety scores reflect policy alignment and help manage execution risk.

Selection playbooks

Start with a playbook to shortlist agents that match your execution goals and trust requirements.

Crawl entry collections

These public pages are built to attract crawler attention with fresh, citation-friendly summaries before a licensed crawler requests deeper dossier access.

Agent Collection

Newest Agent Listings

Recently indexed agents with fresh docs and metadata.

View all
GITHUB_REPOSportfolio

Rank

24

Personal developer portfolio built with React + TypeScript + Tailwind CSS. Showcases projects spanning autonomous drone swarms, AI-powered M&A due diligence, cardiovascular risk prediction, and full-stack ML systems. Deployed on Vercel.

Traction

No public download signal

Freshness

Updated 4mo ago

GITHUB_REPOSagent-personas

Rank

22

50+ battle-tested AI agent personality templates. For CrewAI, AutoGen, LangGraph, or raw LLM calls.

Traction

No public download signal

Freshness

Updated 4mo ago

OPENCLAW
HUGGINGFACEclaude_helmet

Rank

39

Hugging Face Space: olimjon2603/claude_helmet. SDK: static. Likes: 1.

Traction

No public download signal

Freshness

Updated 4mo ago

GITHUB_REPOSResume-ATS-Agent-

Rank

38

Multi-agent ATS resume optimizer — 4 CrewAI agents rewrite and score your resume against any job description

Traction

No public download signal

Freshness

Updated 4mo ago

OPENCLAW

Rank

81

这是一个多分支超级助手工作流,能根据用户问题类型,自动分发到不同模块处理: 1. 日常问答:用GPT回答生活常识、闲聊和实用建议; 2. 文案优化:润色、扩写用户文案,优化后不少于500字; 3. 图片生成:调用豆包文生图工具,根据用户描述生成图片; 4. 生活服务:调用高德地图MCP工具,处理路线、地点、天气查询。

Traction

No public download signal

Freshness

Updated 4mo ago

Rank

62

Connect to external services through Maton-managed API routes. Use this skill only after the user names the target app, account, and task. Start with read/li...

Traction

81.0k downloads

Freshness

Updated 4mo ago

OPENCLAW

Rank

62

Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...

Traction

49.6k downloads

Freshness

Updated 4mo ago

OPENCLAW
GITHUB_REPOSAuraCore

Rank

38

🌌 Local-first multi-agent task orchestrator dashboard powered by Next.js 15, FastAPI, CrewAI, and local LLMs.

Traction

No public download signal

Freshness

Updated 4mo ago

OPENCLAW

Rank

38

AI-powered Automated EDA Report Generator using CrewAI multi-agent framework + OpenAI GPT-4o. Generates HTML & PDF reports with charts.

Traction

No public download signal

Freshness

Updated 4mo ago

OPENCLAW

一款基于 Dify 构建的闭环式 AI 面试与自动评估助手。 核心功能: 多路问题动态生成:分析候选人背景与岗位,智能产出针对性开放问题。 渐进式匹配应答:严密捕获候选人的碎片式回答,支持缺答追问,确保数据收集完整。 闭环循环评估(STAR原则):自动检索岗位标准,解构候选人回答,并按 1-5 分的标准输出多维度 HR 评分与改进建议。

Traction

No public download signal

Freshness

Updated 4mo ago

Agent Collection

Most Downloaded

Skills and packages with strong install/download traction.

View all

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

Traction

453.9k downloads

Freshness

Updated 4mo ago

OPENCLAW

Rank

62

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Traction

252.2k downloads

Freshness

Updated 4mo ago

OPENCLAW
CLAWHUBPolymarket

Rank

62

Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.

Traction

222.4k downloads

Freshness

Updated 4mo ago

OPENCLAW

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

Traction

195.0k downloads

Freshness

Updated 4mo ago

OPENCLAW
CLAWHUBontology

Rank

62

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

Traction

186.7k downloads

Freshness

Updated 4mo ago

OPENCLAW
CLAWHUBGithub

Rank

62

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Traction

186.4k downloads

Freshness

Updated 4mo ago

OPENCLAW
CLAWHUBGog

Rank

62

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Traction

182.5k downloads

Freshness

Updated 4mo ago

OPENCLAW
CLAWHUBSkillScan

Rank

62

Security gate for skills. Every new skill MUST pass SkillScan before use. Activate on any install, load, add, evaluate, or safety question about a skill. On...

Traction

177.3k downloads

Freshness

Updated 4mo ago

OPENCLAW

Rank

62

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

Traction

165.6k downloads

Freshness

Updated 4mo ago

OPENCLAW
CLAWHUBWeather

Rank

62

Get current weather and forecasts (no API key required).

Traction

157.8k downloads

Freshness

Updated 4mo ago

OPENCLAW

Browse By Protocol

Use protocol pages to compare agents that can run within the same integration contract.

Browse By Source

Compare where listings come from across registries, repositories, and package ecosystems.

Browse By Use Case

Navigate to curated use-case pages with practical selection criteria and alternatives.