context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.; research-hub: research-hub connects Zotero, Obsidian, and NotebookLM into a unified, AI-operable research workspace. It provides a CLI, MCP server, REST API, and dashboard for repeatable literature workflows. The tool is local-first and allows users to start with any two of the three platforms.
Deep repository research and analysis (e.g., architecture, contributors, issues)
Connect Zotero + Obsidian for paper search, metadata enrichment, and Markdown note generation