Every comparison, with sources.
LemonCrow and 10 named code-search tools, same 14-repo, 7,213-query benchmark. 7 of 10 publish numbers about themselves; 1 have benchmarked against another tool on this axis.
LemonCrow vs. vanilla Claude Code →
Every published suite: SWE-bench, Exploration, Terminal-Bench, Telegraphic Q&ASame model, same tasks, same environment -- the head-to-head Anthropic itself has never run.
A system-prompt-only instruction anyone can paste in today -- the one DIY alternative every reader can reproduce themselves.
Cuts tokens, barely touches cost →A Bash-output compression proxy -- not a code-search tool, so not in the MRR table below. The most-starred tool anywhere in this comparison.
Supported directly, plus a measured layer on top →AST-based semantic code search built on CocoIndex, a Rust data-transformation engine; tree-sitter parsing plus embeddings.
Self-benchmarked, never vs. standard SWE and TB →Tree-sitter-based persistent knowledge graph (SQLite-backed) across 158 languages -- the most-starred tool in this comparison.
Self-benchmarked, never vs. standard SWE and TB →In-memory, frecency-ranked file and content search with a background watcher -- fast file discovery, not symbol-level code search.
Self-benchmarked, never vs. standard SWE and TB →LSP-wrapped semantic code toolkit -- symbol-level navigation and refactoring via real language servers, 40+ languages.
Self-benchmarked, never vs. standard SWE and TB →Line-oriented regex search CLI -- no AST or symbol awareness, the fastest possible answer to a text-match question.
Benchmarks itself, not vs. this →Tree-sitter AST indexing for 10 core languages, with fallback file indexing for 50+ more.
No published numbers at all →Tree-sitter AST pattern matcher for structural search-and-rewrite -- precise if you already know the exact shape of the code you want.
No published numbers at all →Tree-sitter AST symbol retrieval with a compact wire format (MUNCH) -- optimized for token count, not previously measured for match quality.
Self-benchmarked, never vs. standard SWE and TB →Local SQLite knowledge graph of symbols, call edges, and dependencies, built via tree-sitter and queried over MCP.
Self-benchmarked, never vs. standard SWE and TB →Tag/definition indexer for editor jump-to-definition -- exact tag lookups only, no free-text or semantic query support.
No published numbers at all →Methodology, full 13-tool table, and every raw run → BENCHMARKS.md and docs.atelier.ws .