LeanKG: LeanKG is a local-first knowledge graph that provides accurate codebase context to AI coding tools. It indexes code, builds dependency graphs, and exposes an MCP server for direct querying. No cloud services or external databases are required.; 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.
AI-assisted code impact analysis before changes
Deep repository research and analysis (e.g., architecture, contributors, issues)