AI 智能体1 month ago
AgentsProof — One decorator. A shareable eval report.
为你的AI代理添加评估报告，生成可分享的URL展示性能。
adeeonline · HN
AgentsProof – a small project for testing AI agents
完整作品展
技术栈
60 projects
为你的AI代理添加评估报告，生成可分享的URL展示性能。
adeeonline · HN
AgentsProof – a small project for testing AI agents
The fullstack agentic platform for Ruby on Rails. Install rails-agent-stack, open /agents, build with docs and your coding agent, test, deploy, and monitor agents at the speed of l
kannanreghu · HN
Rails Agent – Build Autonomous AI Agents Natively in Ruby on Rails
使用 Claude Code 构建可通过 SMS 与外部系统交互的 AI agent。
jacobgc · HN
Outside Agent – Build SMS Agents from Claude Code
通过 npm 浏览、预览并安装社区构建的 eve agents。
@TommyBez85 · X
I'm building the eve agents registry
打造AI智能体与对手竞技对战，赢取现金奖励。
@haddmeerj · X
I’m building what I believe will become the next competitive sport: AI agents battling each other for real prize pools. ( )
An AI agent finds companies that fit what you sell, reads their site, writes a first letter, and sends it from your mailbox. Trial: 25 potential clients · 10 days.
@molotilka_dev · X
AI-powered outbound system. Finds prospects, researches companies, writes personalized emails, and helps turn cold outreach into conversations.
在网站上启用AI代理交互，并从仪表板跟踪它们的行为。
not_wowinter13 · HN
Make any website agent-ready in one script tag
Recruit the Swarm. Specialized Grok-powered AI workers that take a goal and execute 24/7 across your tools. The Hive is live. Palm Coast, Florida.
@FirstDeployAI · X
Popular agents in the cloud, one call away. Claude Code, Codex, Hermes, pi & more — one API key, billed per use.
@agentsky_dev · X
Built for agents, not just models. AgentSky is live: one API to run Claude Code, Codex, DeepSeek, Kimi, OpenCode, and more in the cloud. Connect your real tools, then compare time, cost, and tokens side by side in Agent Playground. Try it:
The arena where AI agents fight with money. King of the hill. Outbid to reign. Humans get a 402.
@outfightlol · X
为 AI agents 提供请求人工批准的结构化方式，支持安全重试和决策验证。
@GetAgentHail · X
AgentHail — a control layer for AI agents to request approval, execute work, and return verifiable results. Would you sign up or leave?
在平台上管理和同步你的AI Agent技能配置，避免供应商锁定。
@matebenyovszky · X
I use multiple providers Claude Code, Cursor, Codex, Hermes, Antigravity etc. and multiple machines. Over time, each one ended up with its own slightly different skills and tools 😰 So I started where a playbook is a portable bundle containing my MCP/OpenAPI servers, skills, prompts, personas and memory, which I can take with me into whichever environment I’m using. I’m still trying to figure out whether this is useful beyond my own workflow. Ideas? 🤔 🍎 Source / open source on Github: matebenyovszky/agentplaybooks I also built an npm CLI that audits a project and syncs the same skills and MCP definitions across harnesses.