hack/tools/scripts/llm-key-hunter/results/_cache/content/awsl5714_react-paper-research-agent.json

{"repo": "awsl5714/react-paper-research-agent", "files": {"README.md": {"99e45390d9a5862342ac368feaa1d45db1ed7e9b": {"t": 1785747276.5929573, "n": 3999, "h": "9387383d5a3c2661", "c": "# ReAct Paper Research Agent\n\nA multi-step reasoning research assistant built with LangGraph that automatically plans, searches, summarizes, and generates literature review reports.\n\n## Features\n\n- **ReAct Framework**: Thought → Action → Observation loop for structured research\n- **Multi-Source Search**: arXiv API + Semantic Scholar API\n- **LangGraph State Machine**: Controlled execution with planning, search, summarize, and report nodes\n- **Dual Provider**: Switch between Claude (Anthropic) and DeepSeek\n- **Markdown Reports**: Generates structured literature review with citations\n- **Configurable**: Max iterations, provider selection, output directory\n\n## Architecture\n\n```\n                    ┌─────────┐\n                    │  Plan   │\n                    └────┬────┘\n                         │\n               ┌─────────▼─────────┐\n               │   Search arXiv    │\n               └─────────┬─────────┘\n                         │\n            ┌────────────▼────────────┐\n            │ Search Semantic Scholar │\n            └────────────┬────────────┘\n                         │\n                  ┌──────▼──────┐\n            ┌────►│   Reason    │◄────┐\n            │     └──────┬──────┘     │\n            │            │            │\n            │     ┌──────▼──────┐     │\n            │     │   Route     │     │\n            │     └──┬───┬───┬──┘     │\n            │        │   │   │        │\n    ┌───────▼──┐  ┌──▼─┐ │ ┌─▼──────┐│\n    │Summarize │  │arXiv│ │ │   S2   ││\n    └───────┬──┘  └──┬─┘ │ └─┬──────┘│\n            │        │   │   │        │\n            └────────┘   │   └────────┘\n                         │\n                  ┌──────▼──────┐\n                  │   Report    │\n                  └──────┬──────┘\n                         │\n                      ┌──▼──┐\n                      │ END │\n                      └─────┘\n```\n\n## Quick Start\n\n### Prerequisites\n\n- Python 3.10+\n- API key for at least one provider:\n  - [Anthropic API key](https://console.anthropic.com/) (for Claude)\n  - [DeepSeek API key](https://platform.deepseek.com/) (for DeepSeek)\n\n### Installation\n\n```bash\ngit clone https://github.com/awsl5714/react-paper-research-agent.git\ncd react-paper-research-agent\npip install -e .\n```\n\n### Configuration\n\n```bash\ncp .env.example .env\n# Edit .env and add your API keys\nexport ANTHROPIC_API_KEY=your-key\nexport DEEPSEEK_API_KEY=your-key  # optional\n```\n\n### Usage\n\n```bash\n# Using Claude (default)\npaper-agent \"What are the recent advances in vision-language models?\"\n\n# Using DeepSeek\npaper-agent \"大语言模型的推理能力研究进展\" --provider deepseek\n\n# With verbose logging\npaper-agent \"Retrieval-Augmented Generation techniques\" -v --max-iterations 15\n\n# Custom output directory\npaper-agent \"Diffusion models for image generation\" --output ./reports\n```\n\n### Output\n\nThe agent generates a Markdown report in the output directory:\n\n```markdown\n# Literature Review: [Your Topic]\n\n## Introduction\n...\n\n## Key Themes\n...\n\n## Methodology Overview\n...\n\n## Research Gaps\n...\n\n## Conclusion\n...\n\n## References\n[Author, Year] - Title ...\n```\n\n## Tech Stack\n\n| Component | Technology |\n|-----------|-----------|\n| Agent Framework | [LangGraph](https://github.com/langchain-ai/langgraph) |\n| LLM (Option 1) | Claude via [Anthropic SDK](https://github.com/anthropics/anthropic-sdk-python) |\n| LLM (Option 2) | DeepSeek via [OpenAI SDK](https://github.com/openai/openai-python) |\n| Paper Search | [arXiv API](https://arxiv.org/help/api/), [Semantic Scholar API](https://api.semanticscholar.org/) |\n| Validation | Pydantic v2 |\n\n## Project Structure\n\n```\nsrc/paper_agent/\n├── agent.py           # LangGraph state machine & ReAct nodes\n├── cli.py             # CLI interface\n├── config.py          # Configuration with provider switching\n├── llm.py             # Multi-provider LLM abstraction\n├── state.py           # Agent state definition\n└── tools/\n    ├── arxiv_tool.py           # arXiv API search\n    └── semantic_scholar_tool.py # Semantic Scholar API search\n```\n\n## License\n\nMIT\n"}, "5026a5dbc85ad7b89556ae7b6fcf6401113e4d7e": {"t": 1785772097.1751823, "n": 3999, "h": "9387383d5a3c2661", "c": "# ReAct Paper Research Agent\n\nA multi-step reasoning research assistant built with LangGraph that automatically plans, searches, summarizes, and generates literature review reports.\n\n## Features\n\n- **ReAct Framework**: Thought → Action → Observation loop for structured research\n- **Multi-Source Search**: arXiv API + Semantic Scholar API\n- **LangGraph State Machine**: Controlled execution with planning, search, summarize, and report nodes\n- **Dual Provider**: Switch between Claude (Anthropic) and DeepSeek\n- **Markdown Reports**: Generates structured literature review with citations\n- **Configurable**: Max iterations, provider selection, output directory\n\n## Architecture\n\n```\n                    ┌─────────┐\n                    │  Plan   │\n                    └────┬────┘\n                         │\n               ┌─────────▼─────────┐\n               │   Search arXiv    │\n               └─────────┬─────────┘\n                         │\n            ┌────────────▼────────────┐\n            │ Search Semantic Scholar │\n            └────────────┬────────────┘\n                         │\n                  ┌──────▼──────┐\n            ┌────►│   Reason    │◄────┐\n            │     └──────┬──────┘     │\n            │            │            │\n            │     ┌──────▼──────┐     │\n            │     │   Route     │     │\n            │     └──┬───┬───┬──┘     │\n            │        │   │   │        │\n    ┌───────▼──┐  ┌──▼─┐ │ ┌─▼──────┐│\n    │Summarize │  │arXiv│ │ │   S2   ││\n    └───────┬──┘  └──┬─┘ │ └─┬──────┘│\n            │        │   │   │        │\n            └────────┘   │   └────────┘\n                         │\n                  ┌──────▼──────┐\n                  │   Report    │\n                  └──────┬──────┘\n                         │\n                      ┌──▼──┐\n                      │ END │\n                      └─────┘\n```\n\n## Quick Start\n\n### Prerequisites\n\n- Python 3.10+\n- API key for at least one provider:\n  - [Anthropic API key](https://console.anthropic.com/) (for Claude)\n  - [DeepSeek API key](https://platform.deepseek.com/) (for DeepSeek)\n\n### Installation\n\n```bash\ngit clone https://github.com/awsl5714/react-paper-research-agent.git\ncd react-paper-research-agent\npip install -e .\n```\n\n### Configuration\n\n```bash\ncp .env.example .env\n# Edit .env and add your API keys\nexport ANTHROPIC_API_KEY=your-key\nexport DEEPSEEK_API_KEY=your-key  # optional\n```\n\n### Usage\n\n```bash\n# Using Claude (default)\npaper-agent \"What are the recent advances in vision-language models?\"\n\n# Using DeepSeek\npaper-agent \"大语言模型的推理能力研究进展\" --provider deepseek\n\n# With verbose logging\npaper-agent \"Retrieval-Augmented Generation techniques\" -v --max-iterations 15\n\n# Custom output directory\npaper-agent \"Diffusion models for image generation\" --output ./reports\n```\n\n### Output\n\nThe agent generates a Markdown report in the output directory:\n\n```markdown\n# Literature Review: [Your Topic]\n\n## Introduction\n...\n\n## Key Themes\n...\n\n## Methodology Overview\n...\n\n## Research Gaps\n...\n\n## Conclusion\n...\n\n## References\n[Author, Year] - Title ...\n```\n\n## Tech Stack\n\n| Component | Technology |\n|-----------|-----------|\n| Agent Framework | [LangGraph](https://github.com/langchain-ai/langgraph) |\n| LLM (Option 1) | Claude via [Anthropic SDK](https://github.com/anthropics/anthropic-sdk-python) |\n| LLM (Option 2) | DeepSeek via [OpenAI SDK](https://github.com/openai/openai-python) |\n| Paper Search | [arXiv API](https://arxiv.org/help/api/), [Semantic Scholar API](https://api.semanticscholar.org/) |\n| Validation | Pydantic v2 |\n\n## Project Structure\n\n```\nsrc/paper_agent/\n├── agent.py           # LangGraph state machine & ReAct nodes\n├── cli.py             # CLI interface\n├── config.py          # Configuration with provider switching\n├── llm.py             # Multi-provider LLM abstraction\n├── state.py           # Agent state definition\n└── tools/\n    ├── arxiv_tool.py           # arXiv API search\n    └── semantic_scholar_tool.py # Semantic Scholar API search\n```\n\n## License\n\nMIT\n"}}}}