// five modes
Semantic, structural, graph, text, grounded
Five retrieval lenses ranked into one answer. Not single-mode RAG over chunks.
self-serve, free tier
Not full-text search wearing a trenchcoat.
Code needs more than semantic chunks. Maguyva fuses five retrieval modes into one ranked answer, grounded in the real repo.
RAG over code chunks finds text that looks similar, not code that is actually connected. Maguyva ranks semantic, structural (AST), graph, and text search into one answer, and every result points at a real file and line.
free plan: 3 repos, 50K indexed lines, no card.
// grounded
File paths and line numbers
Every result points at real code you can open and verify. No confident hallucination.
// any client
Remote MCP, 285 languages
Works with Claude, Codex, Cursor, and any MCP client. No local indexer to run.
Try it on a repo where you can verify.
Index one repo you already know and ask one question you can check against the source.
-
// step 01
Index a repo you know
Pick one where you can verify the answer against the source. Free tier: 3 repos, 50K indexed lines.
-
// step 02
Connect over MCP
Claude, Codex, Cursor, or any MCP client. One remote server, no embeddings to manage.
-
// step 03
Ask a question RAG usually fumbles
Find the real implementation, not the test mock. Watch five modes rank it first.