gpt-researcher

GPT Researcher is an LLM-based autonomous agent using a planner-executor-publisher pattern with parallelized agent work for speed and reliability. For detailed architecture diagrams : See references/architecture.md For complete feature addition guide with Image Generation case study : See references/adding-features.md For complete retriever documentation : See references/retrievers.md Config keys are lowercased when accessed: Priority: Environment Variables → JSON Config File → Default Values For complete configuration reference : See references/config-reference.md For MCP integration details : See references/mcp.md For deep research configuration : See references/deep-research.md Always use graceful degradation in skills: - Config → Add to gpt_researcher/config/variables/default.py - Provider → Create in gpt_researcher/llm_provider/my_feature/ - Skill → Create in gpt_researcher/skills/my_feature.py - Agent → Integrate in gpt_researcher/agent.py - Prompts → Update gpt_researcher/prompts.py - WebSocket → Events via stream_output() - Frontend → Handle events in useWebSocket.ts - Docs → Create docs/docs/gpt-researcher/gptr/my_feature.md