[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:codebase-memory-mcp":3},"\u003Ch1>codebase-memory-mcp\u003C\u002Fh1>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Freleases\u002Flatest\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FDeusData\u002Fcodebase-memory-mcp?style=flat&color=blue\" alt=\"GitHub Release\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-green\" alt=\"License\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Factions\u002Fworkflows\u002Fdry-run.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002FDeusData\u002Fcodebase-memory-mcp\u002Fdry-run.yml?label=CI\" alt=\"CI\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ftests-5604_passing-brightgreen\" alt=\"Tests\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flanguages-158-orange\" alt=\"Languages\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"#hybrid-lsp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHybrid_LSP-10_languages-blue\" alt=\"Hybrid LSP\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fagent_surfaces-43-purple\" alt=\"Agents\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpure_C-zero_dependencies-blue\" alt=\"Pure C\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Freleases\u002Flatest\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FmacOS_%7C_Linux_%7C_Windows-supported-lightgrey\" alt=\"Platform\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fscorecard.dev\u002Fviewer\u002F?uri=github.com\u002FDeusData\u002Fcodebase-memory-mcp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fapi.scorecard.dev\u002Fprojects\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Fbadge\" alt=\"OpenSSF Scorecard\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fslsa.dev\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fslsa.dev\u002Fimages\u002Fgh-badge-level3.svg\" alt=\"SLSA 3\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Freleases\u002Flatest\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVirusTotal-scanned_every_release-brightgreen?logo=virustotal\" alt=\"VirusTotal\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.27277\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2603.27277-b31b1b?logo=arxiv\" alt=\"arXiv\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Cstrong>The fastest and most efficient code intelligence engine for AI coding agents.\u003C\u002Fstrong> Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. Ships as a single static binary for macOS, Linux, and Windows — download, run \u003Ccode>install\u003C\u002Fcode>, done.\u003C\u002Fp>\n\u003Cp>High-quality parsing through \u003Ca href=\"https:\u002F\u002Ftree-sitter.github.io\u002Ftree-sitter\u002F\" rel=\"nofollow ugc noopener\">tree-sitter\u003C\u002Fa> AST analysis across all 158 languages, enhanced with \u003Ca href=\"#hybrid-lsp\" rel=\"nofollow ugc noopener\">\u003Cstrong>Hybrid LSP\u003C\u002Fstrong> semantic type resolution\u003C\u002Fa> for Python, TypeScript \u002F JavaScript \u002F JSX \u002F TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. Zero dependencies. Plug and play across 43 supported automatic\u002Fconditional client surfaces.\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>Research\u003C\u002Fstrong> — The design and benchmarks behind this project are described in the preprint \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.27277\" rel=\"nofollow ugc noopener\">\u003Cem>Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP\u003C\u002Fem>\u003C\u002Fa> (arXiv:2603.27277). Evaluated across 31 real-world repositories: 83% answer quality, 10× fewer tokens, 2.1× fewer tool calls vs. file-by-file exploration.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>Security & Trust\u003C\u002Fstrong> — This tool reads your codebase and writes to your agent configuration files. That is what it is designed to do. If you prefer to audit before running, the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\" rel=\"nofollow ugc noopener\">full source is here\u003C\u002Fa> — every release binary is signed, checksummed, and scanned by 70+ antivirus engines. All processing happens 100% locally; your code never leaves your machine. Found a security issue? We want to know — see \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDeusData\u002Fcodebase-memory-mcp\u002Fblob\u002FHEAD\u002FSECURITY.md\" rel=\"nofollow ugc noopener\">SECURITY.md\u003C\u002Fa>. Security is Priority #1 for us.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002FDeusData\u002Fcodebase-memory-mcp\u002FHEAD\u002Fdocs\u002Fgraph-ui-screenshot.png\" alt=\"Graph visualization UI showing the codebase-memory-mcp knowledge graph\" width=\"800\" \u002F>\n  \u003Cbr \u002F>\n  \u003Cem>Built-in 3D graph visualization (UI variant) — explore your knowledge graph at localhost:9749\u003C\u002Fem>\n\u003C\u002Fp>\u003Ch2>Why codebase-memory-mcp\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Extreme indexing speed\u003C\u002Fstrong> — Linux kernel (28M LOC, 75K files) in 3 minutes. RAM-first pipeline: LZ4 compression, in-memory SQLite, fused Aho-Corasick pattern matching. Memory released after indexing.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Plug and play\u003C\u002Fstrong> — single static binary for macOS (a\u003C\u002Fli>\n\u003C\u002Ful>\n",1784828822577]