Ragtoolina – MCP tool that adds codebase RAG to AI coding agents
Honest benchmark shows RAG overhead on trivial queries; 63% token savings on complex tasks.
Zero-config grammar-free structural codebase indexer and MCP server. ~0.16s builds, sub-ms queries, 4.7MB binary.
Indexes the Linux kernel in 80 seconds without AST parsers, where tree-sitter tools fail.
Backend developers, AI agent builders, teams with large polyglot repositories
Sourcegraph Cody · Cursor · Continue
Honest benchmark shows RAG overhead on trivial queries; 63% token savings on complex tasks.
MCP query server cuts codebase context by 87% with zero dependencies, measured.
0.79ms VM spawn time beats E2B's 150ms using CoW memory forking on real KVM isolation.
AST-based code indexing saves tokens but Cursor and Continue already do this.
Tree-sitter + FTS5 + MCP = tokens saved for AI agents to actually code, not search.
IP/ASN lookup that's instant, but what problem does it solve better than ipify or ip-api?