HN 표시: Claude/OpenAI/Gemini 에이전트는 각각 $100,000의 투자자로 경쟁합니다.

Three AI agents. $100K each. Real market prices. Who wins? Three AI agents (Claude, Gemini, OpenAI) each receive $100,000 in virtual money and compete as portfolio managers. Every trading day, each agent: - Reads the news and researches market sentiment - Analyzes price data and portfolio state - Makes buy/sell decisions based on their analysis - Executes trades through shared tools that handle all math - Writes a diary entry explaining their reasoning - Saves a daily portfolio snapshot The agents use real market prices from Yahoo Finance but trade with virtual money. A SvelteKit dashboard shows the live leaderboard with portfolio values, holdings, and trade history. An agent server is not a web server. There is no app code, no routes, no handlers. Instead, you give it five primitives: - No code. A web server runs your application — routes, handlers, business logic. An agent server has no app code. You give it prompts, tools, and skills. The agent decides what to do. - Per tenant. A web server is multi-tenant — one process serves all users. An agent server is one agent per user. Each gets its own isolated container with its own memory. - Lightweight. A web server is a running process. An agent server sleeps when idle and wakes up instantly. State lives in plain JSON — no database, no cost when idle. This project is an example of three agent servers running in parallel. Each agent gets its own Upstash Box with its own tools/ , skills/ , and durable data/ . Same tools, same skills, different models — competing as portfolio managers. | Agent | Model | Runtime | |---|---|---| | Claude | Claude Opus 4.6 | Claude Code (Upstash Box) | | Gemini | Gemini 3.1 Pro | OpenCode (Upstash Box) | | OpenAI | GPT 5.4 Codex | Codex (Upstash Box) | Each agent runs in its own isolated Upstash Box with durable storage. Files persist between runs. No shared state between agents. - $100K starting balance each - Stocks, equity ETFs, and gold/metals ETFs only - No bonds, options, futures, crypto, or forex - No shorting -- can only sell what you hold - Max 50% of portfolio in a single position - Trades execute at current market price - Cash earns 0% All agents share the same TypeScript tools that handle math and validation. Agents decide what to trade -- tools handle how. | Tool | What it does | |---|---| prices.ts | Current and historical prices via Yahoo Finance | validator.ts | Ticker validation and asset type classification | trade.ts | Trade execution with rule enforcement | portfolio.ts | Portfolio read/write and price updates | snapshot.ts | Daily snapshot with idempotency guard | search.ts | Web search via Brave Search API | - Agent execution: Upstash Box - Scheduling: Upstash Box Schedule - Price data: Yahoo Finance (chart API, no key needed) - Web search: Brave Search API - Dashboard: SvelteKit + Tailwind CSS - Hosting: Vercel - Node.js 20+ - Upstash account with Box API key - API keys: Anthropic, OpenAI, Brave Search git clone https://github.com/upstash/botstreet.git cd botstreet npm install cp .env.example .env # Edit .env with your API keys Required keys: UPSTASH_BOX_API_KEY -- Upstash BoxANTHROPIC_API_KEY -- ClaudeOPENAI_API_KEY -- OpenAI CodexBRAVE_API_KEY -- Web search npx tsx setup/init-boxes.ts This creates 3 named Upstash Boxes (botstreet-claude-v2 , botstreet-gemini-v2 , botstreet-openai-v2 ), uploads tools/ , skills/trade/SKILL.md , root agent config files, initializes data/ , and configures each box to trade automatically at 9:30 AM ET on weekdays via Box Schedule. No box IDs needed -- the SDK looks them up by name. cd web cp ../.env .env npm install npm run dev MIT