{"id":"38b68942-ae39-4dbb-8ef5-02e940d9fb0b","entityType":"agent","slug":"crewai-spycoder01-multi-agent-stock-trading-system","name":"Multi-Agent-Stock-Trading-System","canonicalUrl":"https://www.xpersona.co/agent/crewai-spycoder01-multi-agent-stock-trading-system","canonicalPath":"/agent/crewai-spycoder01-multi-agent-stock-trading-system","generatedAt":"2026-10-09T17:10:54.969Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T11:16:31.537Z","emptyReason":null},"description":"LLM-powered multi-agent stock trading system using CrewAI, Gemini, and Yahoo Finance to analyze market data and generate BUY, SELL, or HOLD recommendations. Multi-AI Agent Trader An LLM-powered multi-agent system for stock market analysis and trading recommendations using **CrewAI, Google Gemini, and Yahoo Finance**. The V1 system uses two specialized AI agents: a **Financial Analyst Agent** that retrieves and analyzes live market information, and a **Trader Agent** that evaluates the analysis and generates a **BUY, SELL, or HOLD** recommendation. --- Architecture --- Ho","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/spycoder01/Multi-Agent-Stock-Trading-System","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/spycoder01/Multi-Agent-Stock-Trading-System","kind":"source"}],"safetyScore":66,"overallRank":37.6,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"LLM-powered multi-agent stock trading system using CrewAI, Gemini, and Yahoo Finance to analyze market data and generate BUY, SELL, or HOLD recommendations. Mul"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T11:16:31.537Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T11:16:31.537Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T11:16:31.532Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T11:16:31.537Z","lastCrawledAt":"2026-10-09T11:16:31.532Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T11:16:31.532Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-09T17:10:54.968Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-spycoder01-multi-agent-stock-trading-system/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T11:16:31.537Z","emptyReason":null},"readme":"# Multi-AI Agent Trader\n\nAn LLM-powered multi-agent system for stock market analysis and trading recommendations using **CrewAI, Google Gemini, and Yahoo Finance**.\n\nThe V1 system uses two specialized AI agents: a **Financial Analyst Agent** that retrieves and analyzes live market information, and a **Trader Agent** that evaluates the analysis and generates a **BUY, SELL, or HOLD** recommendation.\n\n---\n\n## Architecture\n\n```text\n                         User\n                           │\n                           │ Stock Symbol\n                           ▼\n                  ┌─────────────────┐\n                  │  Analyst Agent  │\n                  │                 │\n                  │   Gemini LLM    │\n                  └────────┬────────┘\n                           │\n                           │ Uses Tool\n                           ▼\n                  ┌─────────────────┐\n                  │ Stock Research  │\n                  │      Tool       │\n                  └────────┬────────┘\n                           │\n                           ▼\n                    Yahoo Finance\n                           │\n                           ▼\n                     Market Data\n                           │\n                           ▼\n                  Analyst's Report\n                           │\n                           ▼\n                  ┌─────────────────┐\n                  │   Trader Agent  │\n                  │                 │\n                  │   Gemini LLM    │\n                  └────────┬────────┘\n                           │\n                           ▼\n                    BUY / SELL / HOLD\n```\n\n---\n\n## How It Works\n\nThe system follows a sequential multi-agent workflow:\n\n### 1. User Input\n\nThe user provides a stock ticker such as:\n\n```text\nAAPL\n```\n\nor an Indian stock:\n\n```text\nRELIANCE.NS\n```\n\n### 2. Analyst Agent\n\nThe Financial Analyst Agent uses a custom Yahoo Finance tool to retrieve available market information, including:\n\n* Current price\n* Previous closing price\n* Daily price change\n* Trading volume\n* Market capitalization\n* 52-week high\n* 52-week low\n\nGemini then analyzes the retrieved information and produces a concise market assessment.\n\n### 3. Trader Agent\n\nThe Trader Agent receives the Analyst Agent's output and evaluates:\n\n* Current market condition\n* Price movement\n* Market trend\n* Positive signals\n* Potential risks\n* Potential opportunities\n\nIt then generates a final:\n\n```text\nBUY\nSELL\nor\nHOLD\n```\n\nrecommendation with supporting reasoning.\n\n---\n\n## Key Features\n\n* **Multi-Agent Architecture** — Separates market analysis and trading decision-making into specialized agents.\n* **Real-Time Market Data** — Retrieves stock information through Yahoo Finance.\n* **LLM-Powered Analysis** — Uses Google Gemini for financial reasoning and interpretation.\n* **Sequential Agent Workflow** — Analyst output is passed to the Trader Agent for final evaluation.\n* **Multiple Market Support** — Supports ticker formats available through Yahoo Finance, including US and Indian stocks.\n* **Tool-Enabled Agent** — The Analyst Agent can interact with an external data source through a custom CrewAI tool.\n\n---\n\n## Tech Stack\n\n| Technology        | Purpose                         |\n| ----------------- | ------------------------------- |\n| **Python 3.12**   | Core programming language       |\n| **CrewAI**        | Multi-agent orchestration       |\n| **Google Gemini** | Large Language Model            |\n| **yfinance**      | Stock market data               |\n| **python-dotenv** | Environment variable management |\n| **Git & GitHub**  | Version control                 |\n\n---\n\n## Project Structure\n\n```text\nMulti-AI-Agent-Trader/\n│\n├── agents/\n│   ├── analyst_agent.py\n│   └── trader_agent.py\n│\n├── tasks/\n│   ├── analysis_task.py\n│   └── trading_task.py\n│\n├── tools/\n│   └── stock_tool.py\n│\n├── crew.py\n├── main.py\n├── requirements.txt\n├── .env\n└── .gitignore\n```\n\n### `agents/`\n\nContains the specialized AI agents.\n\n* `analyst_agent.py` — Defines the Financial Market Analyst.\n* `trader_agent.py` — Defines the Strategic Stock Trader.\n\n### `tasks/`\n\nDefines the responsibilities assigned to each agent.\n\n* `analysis_task.py` — Task for analyzing market information.\n* `trading_task.py` — Task for generating the final trading recommendation.\n\n### `tools/`\n\nContains external tools used by the agents.\n\n* `stock_tool.py` — Retrieves stock market information using Yahoo Finance.\n\n### `crew.py`\n\nInitializes the CrewAI crew and defines the sequential execution of the agents and tasks.\n\n### `main.py`\n\nApplication entry point that accepts a stock symbol and runs the complete workflow.\n\n---\n\n## Installation\n\n### 1. Clone the Repository\n\n```bash\ngit clone https://github.com/your-username/multi-ai-agent-trader.git\ncd multi-ai-agent-trader\n```\n\n### 2. Create a Virtual Environment\n\n```bash\npython -m venv venv\n```\n\nActivate it on Windows:\n\n```bash\nvenv\\Scripts\\activate\n```\n\n### 3. Install Dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n---\n\n## Environment Setup\n\nCreate a `.env` file in the project root:\n\n```env\nGEMINI_API_KEY=your_gemini_api_key\n```\n\nThe API key is loaded using `python-dotenv`.\n\n**Never commit your `.env` file or expose your API key publicly.**\n\n---\n\n## Running the Project\n\nRun the application from the project root:\n\n```bash\npython main.py\n```\n\nEnter a stock ticker when prompted:\n\n```text\nEnter stock symbol (e.g., AAPL or RELIANCE.NS): AAPL\n```\n\nThe system will then execute:\n\n```text\nStock Symbol\n     ↓\nAnalyst Agent\n     ↓\nYahoo Finance Tool\n     ↓\nMarket Data\n     ↓\nAnalyst Report\n     ↓\nTrader Agent\n     ↓\nBUY / SELL / HOLD\n```\n\n---\n\n## Example Workflow\n\nFor:\n\n```text\nAAPL\n```\n\nthe system retrieves market information and passes it to the Analyst Agent.\n\nThe Analyst produces observations such as:\n\n```text\nCurrent price and daily movement\nTrading activity\n52-week price range\nOverall market condition\nPotential risks\n```\n\nThe Trader Agent then evaluates the analysis and produces a recommendation such as:\n\n```text\nRecommendation: BUY\n\nReason:\nThe available market indicators show positive short-term\nmomentum with favorable price movement, although market\nvolatility remains a risk.\n```\n\n*The actual output depends on the latest available market data and the Gemini model's analysis.*\n\n---\n\n## Agent Responsibilities\n\n### Financial Market Analyst\n\n**Role:** Market researcher and analyst\n\n**Responsibilities:**\n\n* Retrieve market data using the Yahoo Finance tool\n* Analyze current market conditions\n* Identify relevant market signals\n* Highlight potential risks\n* Provide an objective analysis to the Trader Agent\n\n### Strategic Stock Trader\n\n**Role:** Decision-making agent\n\n**Responsibilities:**\n\n* Evaluate the Analyst Agent's report\n* Consider potential opportunities and risks\n* Make a BUY, SELL, or HOLD recommendation\n* Explain the reasoning behind the decision\n\n---\n\n## Why a Multi-Agent Architecture?\n\nInstead of asking a single LLM to perform the entire workflow, the project separates responsibilities between specialized agents.\n\n```text\nSingle Agent:\n\nMarket Data → Analysis → Decision\n                  │\n                 LLM\n```\n\nThe V1 architecture separates these responsibilities:\n\n```text\nMarket Data\n     ↓\nAnalyst Agent\n     ↓\nAnalysis\n     ↓\nTrader Agent\n     ↓\nDecision\n```\n\nThis separation makes the system easier to understand, extend, and maintain.\n\n---\n\n## Current Limitations\n\nV1 is intentionally designed as a lightweight proof of concept.\n\nCurrent limitations include:\n\n* Uses a limited set of market indicators.\n* Does not perform advanced technical analysis.\n* Does not retrieve financial news.\n* Does not analyze company financial statements.\n* Does not include a financial-document RAG pipeline.\n* Does not execute real trades.\n* Trading recommendations are generated by an LLM and should not be treated as financial advice.\n* No historical backtesting or quantitative performance evaluation is included in V1.\n\n---\n\n## Future Improvements\n\nPlanned improvements for future versions include:\n\n### V2 — Expanded Multi-Agent Analysis\n\nAdd specialized agents for:\n\n* Technical analysis\n* Fundamental analysis\n* Financial news analysis\n* Risk assessment\n\n### V3 — Financial RAG\n\nIntegrate company documents such as:\n\n* Annual reports\n* Earnings reports\n* Financial statements\n* Investor presentations\n\nThis would allow the agents to combine real-time market data with company-specific financial information.\n\n### V4 — Interactive Dashboard\n\nAdd a Streamlit interface with:\n\n* Stock price charts\n* Market indicators\n* Agent analysis\n* Trading recommendation\n* Risk summary\n\n### V5 — Backtesting & Evaluation\n\nEvaluate recommendations against historical market data using:\n\n* Historical backtesting\n* Strategy returns\n* Maximum drawdown\n* Sharpe ratio\n* Win rate\n\n---\n\n## Disclaimer\n\nThis project is intended for **educational and research purposes only**.\n\nThe BUY, SELL, or HOLD recommendations generated by the system are produced by an AI model and should not be considered professional financial advice. The project does not execute real trades or manage financial assets.\n\n---\n\n## Author\n\n**Abhisek Gupta**\n\nGitHub: [spycoder01](https://github.com/spycoder01)\n","readmeExcerpt":"Multi-AI Agent Trader An LLM-powered multi-agent system for stock market analysis and trading recommendations using **CrewAI, Google Gemini, and Yahoo Finance**. The V1 system uses two specialized AI agents: a **Financial Analyst Agent** that retrieves and analyzes live market information, and a **Trader Agent** that evaluates the analysis and generates a **BUY, SELL, or HOLD** recommendation. --- Architecture --- Ho","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"User\n                           │\n                           │ Stock Symbol\n                           ▼\n                  ┌─────────────────┐\n                  │  Analyst Agent  │\n                  │                 │\n                  │   Gemini LLM    │\n                  └────────┬────────┘\n                           │\n                           │ Uses Tool\n                           ▼\n                  ┌─────────────────┐\n                  │ Stock Research  │\n                  │      Tool       │\n                  └────────┬────────┘\n                           │\n                           ▼\n                    Yahoo Finance\n                           │\n                           ▼\n                     Market Data\n                           │\n                           ▼\n                  Analyst's Report\n                           │\n                           ▼\n                  ┌─────────────────┐\n                  │   Trader Agent  │\n                  │                 │\n                  │   Gemini LLM    │\n                  └────────┬────────┘\n                           │\n                           ▼\n                    BUY / SELL / HOLD"},{"language":"text","snippet":"AAPL"},{"language":"text","snippet":"RELIANCE.NS"},{"language":"text","snippet":"BUY\nSELL\nor\nHOLD"},{"language":"text","snippet":"Multi-AI-Agent-Trader/\n│\n├── agents/\n│   ├── analyst_agent.py\n│   └── trader_agent.py\n│\n├── tasks/\n│   ├── analysis_task.py\n│   └── trading_task.py\n│\n├── tools/\n│   └── stock_tool.py\n│\n├── crew.py\n├── main.py\n├── requirements.txt\n├── .env\n└── .gitignore"},{"language":"bash","snippet":"git clone https://github.com/your-username/multi-ai-agent-trader.git\ncd multi-ai-agent-trader"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"LLM-powered multi-agent stock trading system using CrewAI, Gemini, and Yahoo Finance to analyze market data and generate BUY, SELL, or HOLD recommendations. Multi-AI Agent Trader An LLM-powered multi-agent system for stock market analysis and trading recommendations using **CrewAI, Google Gemini, and Yahoo Finance**. The V1 system uses two specialized AI agents: a **Financial Analyst Agent** that retrieves and analyzes live market information, and a **Trader Agent** that evaluates the analysis and generates a **BUY, SELL, or HOLD** recommendation. --- Architecture --- Ho","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":418,"uniquenessScore":59,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T11:16:31.537Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T11:16:31.537Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:10:54.969Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}