cqs

jamie8johnson/cqs
★ 11 stars Rust AI/LLM Updated 1d ago
Code intelligence and RAG for AI agents: semantic search, call graphs, impact analysis, and context assembly in single tool calls. 54 languages + L5X/L5K PLC. 70.7% R@5 / 47.2% R@1 / 86.7% R@20 on v3.v2 dual-judge eval. Daemon mode (3-19ms). MCP server (cqs mcp). Local-first, GPU-accelerated.
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "cqs": {
      "command": "cargo",
      "args": [
        "run",
        "--",
        "cqs"
      ]
    }
  }
}

README Excerpt

Code intelligence and RAG for AI agents. Semantic search, call graph analysis, impact tracing, type dependencies, smart context assembly, and MCP server — all in single tool calls. Local ML embeddings, GPU-accelerated. **TL;DR:** Code intelligence toolkit for Claude Code. Instead of grep + sequential file reads, cqs understands what code *does* — semantic search finds functions by concept, call graph commands trace dependencies, and `gather`/`impact`/`context` assemble the right context in one c

Tools (20)

CQS_API_BASECQS_BATCH_AUDIT_RELOAD_SECSCQS_BATCH_CONFIG_RELOAD_SECSCQS_BATCH_DATA_IDLE_MINUTESCQS_BATCH_IDLE_MINUTESCQS_BATCH_MAX_LINE_LENCQS_BATCH_STALENESS_CHECK_MSCQS_BLAST_HIGH_MINCQS_BLAST_LOW_MAXCQS_BRUTE_FORCE_BATCH_SIZECQS_BUSY_TIMEOUT_MSCQS_CACHE_ENABLEDCQS_CACHE_MAX_SIZECQS_CAGRA_GRAPH_DEGREECQS_CAGRA_INTERMEDIATE_GRAPH_DEGREECQS_CAGRA_ITOPK_MAXCQS_CAGRA_ITOPK_MINCQS_CAGRA_MAX_BYTESCQS_CAGRA_MAX_GPU_BYTESCQS_CAGRA_PERSIST

Topics

ai-agentscall-graphclaude-codecode-intelligencecode-searchembeddingsragrustsemantic-searchvector-search