Vibe Coding Discoverdexter-jp
View on GitHub日本株の自律型リサーチAIエージェント｜AI agent for deep financial research on Japanese listed companies. Powered by EDINET DB + J-Quants.
Dexter JP is a TypeScript autonomous research agent for Japanese listed companies, built on LangChain and the Claude Agent SDK. It plans, calls EDINET DB and J-Quants tools in parallel, checks hypotheses against filing paragraphs with citations, and outputs structured financial reports via CLI or chat gateways.
Use Cases
Deep financial research on Japanese listed companiesCompare two companies as investment targetsDCF valuation with Japan-specific WACC assumptionsScreen stocks by ROE, dividend yield, equity ratioRead and summarize annual reports (有価証券報告書) risk factorsVerify user hypotheses against filing paragraphs with citationsCross-source analysis via EDINET DB and J-QuantsAutonomous multi-tool planning and report generationStock price retrieval and disclosure monitoringRun the agent through Slack, Discord, LINE or WhatsApp botsCustom research rules via .dexter/RULES.mdLong-session context compression and cross-session memory
Built With
- Language
- TypeScript
- Frameworks
- LangChain · Claude Agent SDK · @langchain/anthropic · @langchain/openai · @langchain/google-genai · @langchain/ollama · Bun · Playwright · Slack Bolt · Discord.js · Baileys · LangSmith · Zod · better-sqlite3
Tags
ai-agent · finance · japanese-stocks · edinet · jquants · langchain · research-agent · autonomous-agent · cli · typescript · rag · tool-use · multi-source · agent-skills · disclosure-analysis · slack-discord-bot