{"id":34941965,"url":"https://github.com/dragon1086/prism-insight","last_synced_at":"2026-05-29T08:01:13.983Z","repository":{"id":310031284,"uuid":"1038434342","full_name":"dragon1086/prism-insight","owner":"dragon1086","description":"AI-based stock analysis and trading system","archived":false,"fork":false,"pushed_at":"2026-05-29T06:06:34.000Z","size":64785,"stargazers_count":611,"open_issues_count":0,"forks_count":211,"subscribers_count":14,"default_branch":"main","last_synced_at":"2026-05-29T06:22:02.856Z","etag":null,"topics":["ai","llm","mcp","multi-agent","stock"],"latest_commit_sha":null,"homepage":"https://prism-insight-landing.vercel.app/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dragon1086.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null},"funding":{"github":"dragon1086"}},"created_at":"2025-08-15T07:32:09.000Z","updated_at":"2026-05-29T06:06:39.000Z","dependencies_parsed_at":"2025-08-15T10:06:14.675Z","dependency_job_id":"974d268f-5e3d-444e-ace2-ea81019c080d","html_url":"https://github.com/dragon1086/prism-insight","commit_stats":null,"previous_names":["dragon1086/prism-insight"],"tags_count":87,"template":false,"template_full_name":null,"purl":"pkg:github/dragon1086/prism-insight","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragon1086%2Fprism-insight","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragon1086%2Fprism-insight/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragon1086%2Fprism-insight/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragon1086%2Fprism-insight/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dragon1086","download_url":"https://codeload.github.com/dragon1086/prism-insight/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dragon1086%2Fprism-insight/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33642318,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-29T02:00:06.066Z","response_time":107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","llm","mcp","multi-agent","stock"],"created_at":"2025-12-26T19:19:52.792Z","updated_at":"2026-05-29T08:01:13.970Z","avatar_url":"https://github.com/dragon1086.png","language":"Python","funding_links":["https://github.com/sponsors/dragon1086"],"categories":["📚 Projects (1974 total)","Python"],"sub_categories":["MCP Servers","Trading \u0026 Backtesting"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/images/prism-insight-logo.jpeg\" alt=\"PRISM-INSIGHT Logo\" width=\"300\"\u003e\n  \u003cbr\u003e\u003cbr\u003e\n  \u003cimg src=\"https://img.shields.io/badge/License-AGPL%20v3-blue.svg\" alt=\"License\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/python-3.10+-blue.svg\" alt=\"Python\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/OpenAI-GPT--5-green.svg\" alt=\"OpenAI\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Anthropic-Claude--Sonnet--4.6-green.svg\" alt=\"Anthropic\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/ChatGPT_Plus-Codex_OAuth-ff6b35.svg\" alt=\"ChatGPT Plus\"\u003e\n\u003c/div\u003e\n\n# PRISM-INSIGHT\n\n[![GitHub Sponsors](https://img.shields.io/github/sponsors/dragon1086?style=for-the-badge\u0026logo=github-sponsors\u0026color=ff69b4\u0026label=Sponsors)](https://github.com/sponsors/dragon1086)\n[![Stars](https://img.shields.io/github/stars/dragon1086/prism-insight?style=for-the-badge)](https://github.com/dragon1086/prism-insight/stargazers)\n\n\u003e **AI-Powered Stock Market Analysis \u0026 Trading System**\n\u003e\n\u003e 13+ specialized AI agents collaborate to detect surge stocks, generate analyst-grade reports, and execute trades automatically.\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"README.md\"\u003eEnglish\u003c/a\u003e |\n  \u003ca href=\"README_ko.md\"\u003e한국어\u003c/a\u003e |\n  \u003ca href=\"README_ja.md\"\u003e日本語\u003c/a\u003e |\n  \u003ca href=\"README_zh.md\"\u003e中文\u003c/a\u003e |\n  \u003ca href=\"README_es.md\"\u003eEspañol\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n### Platinum Sponsor\n\n\u003cdiv align=\"center\"\u003e\n\u003ca href=\"https://wrks.ai/en\"\u003e\n  \u003cimg src=\"docs/images/wrks_ai_logo.png\" alt=\"AI3 WrksAI\" width=\"50\"\u003e\n\u003c/a\u003e\n\n**[AI3](https://www.ai3.kr/) | [WrksAI](https://wrks.ai/en)**\n\nAI3, creator of **WrksAI** - the AI assistant for professionals,\u003cbr\u003e\nproudly sponsors **PRISM-INSIGHT** - the AI assistant for investors.\n\u003c/div\u003e\n\n---\n\n## NEW: ChatGPT Plus/Pro Subscription Support\n\n**No API key? No problem.** PRISM-INSIGHT now supports running analysis directly through your ChatGPT Plus ($20/mo) or Pro ($200/mo) subscription via the **Codex OAuth Proxy**.\n\n```bash\n# One-time login (browser will open for ChatGPT auth)\npython -m cores.chatgpt_proxy.oauth_login\n\n# Re-authenticate (switch account, or refresh expired tokens)\npython -m cores.chatgpt_proxy.oauth_login --force\n\n# Run with your ChatGPT subscription\nPRISM_OPENAI_AUTH_MODE=chatgpt_oauth python stock_analysis_orchestrator.py --mode morning\n```\n\n\u003e Tokens auto-refresh in the background, so you only need to log in again if you change ChatGPT accounts or your password.\n\nZero API bills. Same powerful analysis. Your existing subscription does the work.\n\n---\n\n## Mobile App\n\n\u003cdiv align=\"center\"\u003e\n\n**Get AI stock analysis on the go**\n\n\u003ca href=\"https://play.google.com/store/apps/details?id=com.prisminsight.prism_mobile\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Google_Play-Download-green?style=for-the-badge\u0026logo=google-play\" alt=\"Google Play\"\u003e\n\u003c/a\u003e\n\u003ca href=\"https://apps.apple.com/us/app/prism-insight-stock-analysis/id6759331074\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/App_Store-Download-blue?style=for-the-badge\u0026logo=apple\" alt=\"App Store\"\u003e\n\u003c/a\u003e\n\n\u003c/div\u003e\n\n- **Smart Filtering** — Receive only the Telegram alerts you care about\n- **PDF Reports** — Mobile-optimized AI analysis reports\n- **Launch Promo (until Apr 23, 2026)** — Install now and get **20 free credits** (normally 10)\n\n---\n\n## Watch PRISM-INSIGHT in Action\n\n[![PRISM-INSIGHT Demo](https://img.youtube.com/vi/zAywb1G0wRA/maxresdefault.jpg)](https://www.youtube.com/watch?v=zAywb1G0wRA)\n\n---\n\n## Try It Now (No Installation Required)\n\n### 1. Live Dashboard\nSee AI trading performance in real-time:\n**[analysis.stocksimulation.kr](https://analysis.stocksimulation.kr/)**\n\n### 2. Telegram Channels\nGet daily surge stock alerts and AI analysis reports:\n- **[English Channel](https://t.me/prism_insight_global_en)**\n- **[Korean Channel](https://t.me/stock_ai_agent)**\n- **[Japanese Channel](https://t.me/prism_insight_ja)**\n- **[Chinese Channel](https://t.me/prism_insight_zh)**\n- **[Spanish Channel](https://t.me/prism_insight_es)**\n\n### 3. Sample Report\nWatch an AI-generated Apple Inc. analysis report:\n\n[![Sample Report - Apple Inc. Analysis](https://img.youtube.com/vi/LVOAdVCh1QE/maxresdefault.jpg)](https://youtu.be/LVOAdVCh1QE)\n\n---\n\n## Try in 60 Seconds (US Stocks)\n\nThe fastest way to try PRISM-INSIGHT. Only requires an **OpenAI API key**.\n\n```bash\n# Clone and run the quickstart script\ngit clone https://github.com/dragon1086/prism-insight.git\ncd prism-insight\n./quickstart.sh YOUR_OPENAI_API_KEY\n```\n\nThis generates an AI analysis report for Apple (AAPL). Try other stocks:\n```bash\npython3 demo.py MSFT              # Microsoft\npython3 demo.py NVDA              # NVIDIA\npython3 demo.py TSLA --language ko  # Tesla (Korean report)\n```\n\n\u003e **Get your OpenAI API key** from [OpenAI Platform](https://platform.openai.com/api-keys)\n\u003e\n\u003e **Optional**: Add a [Perplexity API key](https://www.perplexity.ai/) to `mcp_agent.config.yaml` for news analysis\n\u003e\n\u003e **Optional**: Add `ADANOS_API_KEY` to enrich US stock news analysis with structured social sentiment context\n\nYour AI-generated PDF reports will be saved in `prism-us/pdf_reports/`.\n\n\u003cdetails\u003e\n\u003csummary\u003eOr use Docker (no Python setup needed)\u003c/summary\u003e\n\n```bash\n# 1. Set your OpenAI API key\nexport OPENAI_API_KEY=sk-your-key-here\n\n# 2. Build and start the local quickstart image\ndocker compose -f docker-compose.quickstart.yml up --build -d\n\n# 3. Run analysis\ndocker exec -it prism-quickstart python3 demo.py NVDA\n```\n\nThe first run builds the image locally, so it may take several minutes.\n\nReports will be saved to `./quickstart-output/`.\n\n\u003c/details\u003e\n\n---\n\n## Full Installation\n\n### Prerequisites\n- Python 3.10+ or Docker\n- OpenAI API Key ([get one here](https://platform.openai.com/api-keys)) or ChatGPT Plus/Pro subscription\n\n### Option A: Python Installation\n\n```bash\n# 1. Clone \u0026 Install\ngit clone https://github.com/dragon1086/prism-insight.git\ncd prism-insight\npip install -r requirements.txt\n\n# 2. Install Playwright for PDF generation\npython3 -m playwright install chromium\n\n# 3. Install perplexity-ask MCP server\ncd perplexity-ask \u0026\u0026 npm install \u0026\u0026 npm run build \u0026\u0026 cd ..\n\n# 4. Setup config\ncp mcp_agent.config.yaml.example mcp_agent.config.yaml\ncp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml\n# Edit mcp_agent.secrets.yaml with your OpenAI API key\n# Edit mcp_agent.config.yaml with KRX credentials (Kakao account)\n\n# 5. Run analysis (no Telegram required!)\npython stock_analysis_orchestrator.py --mode morning --no-telegram\n```\n\n### Option B: Docker (Recommended for Production)\n\n```bash\n# 1. Clone \u0026 Configure\ngit clone https://github.com/dragon1086/prism-insight.git\ncd prism-insight\ncp mcp_agent.config.yaml.example mcp_agent.config.yaml\ncp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml\n# Edit config files with your API keys\n\n# 2. Build \u0026 Run\ndocker compose up -d\n\n# 3. Run analysis manually (optional)\ndocker exec prism-insight-container python3 stock_analysis_orchestrator.py --mode morning --no-telegram\n```\n\n**Full Setup Guide**: [docs/SETUP.md](docs/SETUP.md)\n\n---\n\n## What is PRISM-INSIGHT?\n\nPRISM-INSIGHT is a **completely open-source, free** AI-powered stock analysis system for **Korean (KOSPI/KOSDAQ)** and **US (NYSE/NASDAQ)** markets.\n\n### Core Capabilities\n- **Surge Stock Detection** — Automatic detection of stocks with unusual volume/price movements\n- **AI Analysis Reports** — Professional analyst-grade reports generated by 13 specialized AI agents\n- **Trading Simulation** — AI-driven buy/sell decisions with portfolio management\n- **Automated Trading** — Real execution via Korea Investment \u0026 Securities API\n- **Telegram Integration** — Real-time alerts and multi-language broadcasting\n- **Macro Intelligence** — Market regime detection, sector rotation analysis, risk event monitoring\n\n### AI Models\n- **Analysis \u0026 Trading**: OpenAI GPT-5 / GPT-5.4-mini (via API or ChatGPT Plus subscription)\n- **Report Generation**: Anthropic Claude Sonnet 4.6\n- **Translation**: OpenAI GPT-5 (EN, JA, ZH, ES support)\n\n---\n\n## AI Agent System\n\n13+ specialized agents collaborate in teams:\n\n| Team | Agents | Purpose |\n|------|--------|---------|\n| **Macro** | 1 agent | Market regime, sector rotation, risk events |\n| **Analysis** | 6 agents | Technical, Financial, Industry, News, Market analysis |\n| **Strategy** | 1 agent | Investment strategy synthesis |\n| **Communication** | 3 agents | Summary, Quality evaluation, Translation |\n| **Trading** | 3 agents | Buy/Sell decisions, Journal |\n| **Consultation** | 2 agents | User interaction via Telegram |\n\n\u003cdetails\u003e\n\u003csummary\u003eView Agent Workflow Diagram\u003c/summary\u003e\n\u003cbr\u003e\n\u003cimg src=\"docs/images/aiagent/agent_workflow2.png\" alt=\"Agent Workflow\" width=\"700\"\u003e\n\u003c/details\u003e\n\n**Detailed Agent Documentation**: [docs/CLAUDE_AGENTS.md](docs/CLAUDE_AGENTS.md)\n\n---\n\n## Key Features\n\n| Feature | Description |\n|---------|-------------|\n| **AI Analysis** | Expert-level stock analysis through GPT-5 multi-agent system |\n| **Surge Detection** | Automatic watchlist via morning/afternoon market trend analysis |\n| **Telegram** | Real-time analysis distribution to channels |\n| **Trading Sim** | AI-driven investment strategy simulation |\n| **Auto Trading** | Execution via Korea Investment \u0026 Securities API |\n| **Dashboard** | Transparent portfolio, trades, and performance tracking |\n| **Self-Improving** | Trading journal feedback loop — past trigger win rates automatically inform future buy decisions ([details](docs/TRADING_JOURNAL.md#performance-tracker-피드백-루프-self-improving-trading)) |\n| **US Markets** | Full support for NYSE/NASDAQ analysis |\n| **Macro Intelligence** | Market regime detection and sector rotation for smarter stock selection |\n| **Mobile App** | iOS \u0026 Android app with smart filtering and PDF reports |\n\n\u003cdetails\u003e\n\u003csummary\u003eView Dashboard Screenshots\u003c/summary\u003e\n\u003cbr\u003e\n\u003cimg src=\"docs/images/dashboard_portfolio.png\" alt=\"Portfolio Overview\" width=\"700\"\u003e\n\u003cbr\u003e\u003cbr\u003e\n\u003cimg src=\"docs/images/dashboard_trades.png\" alt=\"Trading Simulator\" width=\"700\"\u003e\n\u003cbr\u003e\u003cbr\u003e\n\u003cimg src=\"docs/images/dashboard_performance.png\" alt=\"AI Trading Scenario\" width=\"700\"\u003e\n\u003c/details\u003e\n\n---\n\n## Trading Performance\n\n### KR Market — Season 2\n\n| Metric | Value |\n|--------|-------|\n| Period | 2025.09.30 ~ 2026.03.24 |\n| Total Trades | 86 |\n| Win Rate | 45.35% |\n| Avg Return per Trade | +2.84% |\n| **Cumulative Return** | **+244.63%** |\n| Current Holdings | 5 stocks |\n\n### US Market (Beta)\n\n| Metric | Value |\n|--------|-------|\n| Period | 2026.01.28 ~ 2026.03.21 |\n| Total Trades | 13 |\n| Current Holdings | 6 stocks |\n\n**[Live Dashboard](https://analysis.stocksimulation.kr/)**\n\n---\n\n## US Stock Market Module\n\nSame AI-powered workflow for US markets:\n\n```bash\n# Run US analysis\npython prism-us/us_stock_analysis_orchestrator.py --mode morning --no-telegram\n\n# With English reports\npython prism-us/us_stock_analysis_orchestrator.py --mode morning --language en\n```\n\n**Data Sources**: yahoo-finance-mcp, sec-edgar-mcp (SEC filings, insider trading)\n\n---\n\n## Documentation\n\n| Document | Description |\n|----------|-------------|\n| [docs/SETUP.md](docs/SETUP.md) | Complete installation guide |\n| [docs/CLAUDE_AGENTS.md](docs/CLAUDE_AGENTS.md) | AI agent system details |\n| [docs/TRIGGER_BATCH_ALGORITHMS.md](docs/TRIGGER_BATCH_ALGORITHMS.md) | Surge detection algorithms |\n| [docs/TRADING_JOURNAL.md](docs/TRADING_JOURNAL.md) | Trading memory system |\n\n---\n\n## Frontend Examples\n\n### Dashboard\nReal-time portfolio tracking and performance dashboard.\n\n**[Live Demo](https://analysis.stocksimulation.kr/)**\n\n```bash\ncd examples/dashboard\nnpm install\nnpm run dev\n# Visit http://localhost:3000\n```\n\n**Features**: Portfolio overview, trading history, performance metrics, market selector (KR/US), return comparison vs KOSPI/KOSDAQ\n\n**Dashboard Setup Guide**: [examples/dashboard/DASHBOARD_README.md](examples/dashboard/DASHBOARD_README.md)\n\n---\n\n## MCP Servers\n\n### Korean Market\n- **[kospi_kosdaq](https://github.com/dragon1086/kospi-kosdaq-stock-server)** — KRX stock data\n- **[firecrawl](https://github.com/mendableai/firecrawl-mcp-server)** — Web crawling\n- **[perplexity](https://github.com/perplexityai/modelcontextprotocol)** — Web search\n- **[sqlite](https://github.com/modelcontextprotocol/servers-archived)** — Trading simulation DB\n\n### US Market\n- **[yahoo-finance-mcp](https://pypi.org/project/yahoo-finance-mcp/)** — OHLCV, financials\n- **[sec-edgar-mcp](https://pypi.org/project/sec-edgar-mcp/)** — SEC filings, insider trading\n\n---\n\n## Contributing\n\n1. Fork the project\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Create a Pull Request\n\n---\n\n## License\n\n**Dual Licensed:**\n\n### For Individual \u0026 Open-Source Use\n[![License: AGPL v3](https://img.shields.io/badge/License-AGPL%20v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)\n\nFree under AGPL-3.0 for personal use, non-commercial projects, and open-source development.\n\n### For Commercial SaaS Use\nSeparate commercial license required for SaaS companies.\n\n**Contact**: dragon1086@naver.com\n**Details**: [LICENSE-COMMERCIAL.md](LICENSE-COMMERCIAL.md)\n\n---\n\n## Disclaimer\n\nAnalysis information is for reference only, not investment advice. All investment decisions and resulting profits/losses are the investor's responsibility.\n\n---\n\n## Sponsorship\n\n### Support the Project\n\nMonthly operating costs (~$310/month):\n- OpenAI API: ~$235/month\n- Anthropic API: ~$11/month\n- Firecrawl + Perplexity: ~$35/month\n- Server infrastructure: ~$30/month\n\nCurrently serving 450+ users for free.\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://github.com/sponsors/dragon1086\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Sponsor_on_GitHub-❤️-ff69b4?style=for-the-badge\u0026logo=github-sponsors\" alt=\"Sponsor on GitHub\"\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n---\n\n## Project Growth\n\n[![Star History Chart](https://api.star-history.com/svg?repos=dragon1086/prism-insight\u0026type=Date)](https://star-history.com/#dragon1086/prism-insight\u0026Date)\n\n---\n\n**If this project helped you, please give us a Star!**\n\n**Contact**: [GitHub Issues](https://github.com/dragon1086/prism-insight/issues) | [Telegram](https://t.me/stock_ai_agent) | [Discussions](https://github.com/dragon1086/prism-insight/discussions)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdragon1086%2Fprism-insight","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdragon1086%2Fprism-insight","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdragon1086%2Fprism-insight/lists"}