#code-analysis

Local code-context engine for AI coding agents: structural answers within a token budget.

Static code-analysis + knowledge-graph for AI coding agents. Index your codebase once — agents query only what they need. 87–91% token reduction, 12 MCP tools, 13 languages. MCP stdio + HTTP API. Works with Claude Code, Cursor, Antigravity, Codex.

Reverse-engineer any Python codebase into an interactive architecture knowledge graph with AI-powered layer detection, community discovery, and living documentation

Local‑only Query Risk & Scope Analyzer for AI coding prompts — estimate risk, scope, likely files, and token pressure before sending queries to agents like Cursor, Copilot, or Claude.

Atomic, build-gated developer tools for AI coding agents: type-checked refactors, semantic search, and verify→fix loops over MCP, CLI, and TUI.

🤖 Multi-Agent Code Intelligence Platform — 12 AI agents + 4-round consensus debate + RAG + continuous watcher. Powered by Xiaomi MiMo V2.5 via Hermes Agent.

Codebase knowledge management plugin for Claude Code — analyze repos, build a structured wiki, compare architectures, and query design decisions. Built on the Karpathy LLM Wiki pattern.

Local, incremental repository context for AI coding agents, designed to reduce repeated discovery cost.

Verinoda + Claude Code, together: Verinoda with verinoda-live, a Claude Code mod that keeps the code index fresh, nudges the agent to use it, reviews commits, and shows it in a pane with an animated mascot.

AI-powered codebase assistant that helps developers understand and interact with GitHub repositories using natural language.