Report Crawler

Deep Research

Systematic multi-angle research for natural-language questions. search -> fetch -> parse -> evidence-extract -> headline synth. Orchestrator only — every primitive delegates to engines/data/*.

WET Extract

Search the web via SearXNG, extract clean text from URLs, and query indexed library docs with hybrid FTS5 + semantic search — no API keys required.

Proposal Drafter

Generate structured research proposals from topic descriptions, including research questions, objectives, methodology, expected contributions and timeline.

Search Hub

Multi-engine web search: open-source, keyless DuckDuckGo (DDG Lite + duckduckgo_search library); merges and de-dups via reciprocal-rank fusion (RRF) with optional content extraction. Use it for topic research, fact-finding and competitor scans.

Market Weekly

Data-driven weekly investment briefing over your watchlist or given symbols, exported as Markdown. (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)

ChatPaper

Deep Q&A over an academic paper: scholarly snapshot, methodology x-ray, critical appraisal, plain-language explainer, grounded question answering. Use when you need deep q&a over an academic paper. (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)