What they say vs. what it produces

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.

The flagship comparison

LemonCrow vs. vanilla Claude Code →

Every published suite: SWE-bench, Exploration, Terminal-Bench, Telegraphic Q&A

Same model, same tasks, same environment -- the head-to-head Anthropic itself has never run.

Code-search retrieval tools, ranked by MRR
LemonCrow vs cocoindex-code 0.557 MRR

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 →
LemonCrow vs codebase-memory-mcp 0.502 MRR

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 →
LemonCrow vs fff (fff-mcp) 0.430 MRR

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 →
LemonCrow vs Serena 0.401 MRR

LSP-wrapped semantic code toolkit -- symbol-level navigation and refactoring via real language servers, 40+ languages.

Self-benchmarked, never vs. standard SWE and TB →
LemonCrow vs ripgrep 0.376 MRR

Line-oriented regex search CLI -- no AST or symbol awareness, the fastest possible answer to a text-match question.

Benchmarks itself, not vs. this →
LemonCrow vs code-index-mcp 0.343 MRR

Tree-sitter AST indexing for 10 core languages, with fallback file indexing for 50+ more.

No published numbers at all →
LemonCrow vs ast-grep 0.312 MRR

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 →
LemonCrow vs jCodeMunch 0.299 MRR

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 →
LemonCrow vs CodeGraph 0.296 MRR

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 →
LemonCrow vs Universal Ctags 0.237 MRR

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 .