cqs
v1.54.0 ExperimentalCode intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, type dependencies, and smart context assembly — in single tool calls. 54 languages + L5X/L5K PLC exports. 69.8% R@5 / 43.6% R@1 / 83.5% R@20 on v3.v2 dual-judge code-search (218 queries, EmbeddingGemma-300m default with per-category SPLADE α; 2026-07-03 snapshot, scoring unchanged through v1.54.0). Daemon mode (3-19ms queries). MCP server (`cqs mcp`, 30 read tools, full input+output schemas). Local-first, GPU-accelerated.
Quick Verdict
- ✓Actively maintained (updated 10d ago)
- !Heavy dependency tree (121 direct deps)
- ✓Permissive license (MIT)
Security
Deep Insights
357 downloads in the last 30 days (12/day), up 97% from the previous period.
121 direct dependencies. Consider the impact on compile times and supply chain complexity.
7.1MB is relatively large. May impact download and compile times.
Health Breakdown
Recency, release consistency, active ratio
Yanked ratio, deps, size, maturity, features
Reverse deps, ownership, ecosystem
Downloads, momentum, growth trend
Docs, repo, license, metadata
Download Trend
Version Adoption
Release Timeline
Feature Flags
default =["lang-rust", "lang-python", "lang-typescript", "lang-javascript", "lang-go", "lang-c", "lang-cpp", "lang-java", "lang-csharp", "lang-fsharp", "lang-powershell", "lang-scala", "lang-ruby", "lang-bash", "lang-hcl", "lang-kotlin", "lang-swift", "lang-objc", "lang-sql", "lang-protobuf", "lang-graphql", "lang-php", "lang-lua", "lang-zig", "lang-r", "lang-yaml", "lang-toml", "lang-elixir", "lang-elm", "lang-erlang", "lang-haskell", "lang-ocaml", "lang-julia", "lang-gleam", "lang-css", "lang-perl", "lang-html", "lang-json", "lang-xml", "lang-ini", "lang-nix", "lang-make", "lang-latex", "lang-solidity", "lang-cuda", "lang-glsl", "lang-svelte", "lang-razor", "lang-vbnet", "lang-vue", "lang-markdown", "lang-aspx", "lang-st", "lang-l5x", "lang-dart", "convert", "llm-summaries", "serve"]