High-performance MCP server for AI coding agents: persistent knowledge graph, blast radius analysis, semantic search. Built in Rust.
This repository also configures its own agents. See what lain tells them →
Skill Claude CodeCodex
Structural code intelligence for AI coding agents. Use this skill when the user wants to understand how a codebase is organized (modules, call graphs, file dependencies), find where to start reading, trace the impact of a change, find code by meaning, or understand what a symbol does in its full context. Do NOT use…
Skill Claude CodeCodex
Use for system-shape questions through Lain — "map this subsystem", "compare these modules", "trace the dependency chain", "how deep is this in the stack", "where is the god object", "run a raw graph query". Covers the arch and raw packages.
Skill Claude CodeCodex
Use when reading, locating, or assessing code through Lain's MCP tools — "where is X", "explain this", "what breaks if I change this", "what should I read first", "is this answer trustworthy". Covers the default core surface and the honest-answer contract.
Skill Claude CodeCodex
Use when working alongside other agents with Lain — "claim these files", "who else is here", "will we collide", "leave a note for the next agent", "what happened while I was away". Covers the session, social, and notes packages.
Skill Claude CodeCodex
Use when answering questions across repositories with Lain — "which repos know about X", "what breaks across repos if I change this", "what is in this workspace group". Covers the federation and workspace packages.
Skill Claude CodeCodex
Use to verify a change through Lain — "run the tests", "does it build", "what is untested", "what changed", "which branch am I on". Covers the verify package (build/test/lint/coverage/git state).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: