[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:repowise":3},"\u003Cdiv align=\"center\">\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.repowise.dev\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Frepowise-dev\u002Frepowise\u002FHEAD\u002F.github\u002Fassets\u002Fbanner.png\" alt=\"repowise: the codebase intelligence layer for your AI coding agent\" width=\"100%\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp align=\"center\">\u003Cstrong>Five intelligence layers · Nine MCP tools · 15 languages · Multi-repo workspaces · One \u003Ccode>pip install\u003C\u002Fcode>\u003C\u002Fstrong>\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.repowise.dev\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLIVE_DEMO-repowise.dev-F59520?style=for-the-badge&labelColor=0A0A0A\" alt=\"Live demo: repowise.dev\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frepowise-dev\u002Frepowise\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FStar_this_repo-1E293B?style=for-the-badge&logo=github&logoColor=white&labelColor=0A0A0A\" alt=\"Star repowise on GitHub\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frepowise\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Frepowise?style=for-the-badge&color=1E293B&labelColor=0A0A0A&logo=pypi&logoColor=white\" alt=\"PyPI version\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fagpl-3.0\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-AGPL--v3-059669?style=for-the-badge&labelColor=0A0A0A\" alt=\"License: AGPL v3\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frepowise\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.11%2B-1E293B?style=for-the-badge&labelColor=0A0A0A&logo=python&logoColor=white\" alt=\"Python 3.11+\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fmodelcontextprotocol.io\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMCP-compatible-1E293B?style=for-the-badge&labelColor=0A0A0A\" alt=\"MCP compatible\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frepowise-dev\u002Frepowise\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frepowise-dev\u002Frepowise?style=for-the-badge&logo=github&color=1E293B&labelColor=0A0A0A&logoColor=white\" alt=\"GitHub stars\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.repowise.dev\u002F#contact\" rel=\"nofollow ugc noopener\">\u003Cstrong>Hosted for teams →\u003C\u002Fstrong>\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fdocs.repowise.dev\" rel=\"nofollow ugc noopener\">\u003Cstrong>Docs\u003C\u002Fstrong>\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FcQVpuDB6rh\" rel=\"nofollow ugc noopener\">\u003Cstrong>Discord\u003C\u002Fstrong>\u003C\u002Fa> ·\n  \u003Ca href=\"mailto:hello@repowise.dev\" rel=\"nofollow ugc noopener\">\u003Cstrong>Contact\u003C\u002Fstrong>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\u003Csub>\n  \u003Ca href=\"#the-five-layers\" rel=\"nofollow ugc noopener\">Layers\u003C\u002Fa> ·\n  \u003Ca href=\"#learns-from-how-you-actually-use-it\" rel=\"nofollow ugc noopener\">Learns from you\u003C\u002Fa> ·\n  \u003Ca href=\"#-code-health-the-layer-nobody-else-nails\" rel=\"nofollow ugc noopener\">Code Health\u003C\u002Fa> ·\n  \u003Ca href=\"#refactoring-intelligence\" rel=\"nofollow ugc noopener\">Refactoring\u003C\u002Fa> ·\n  \u003Ca href=\"#benchmarks\" rel=\"nofollow ugc noopener\">Benchmarks\u003C\u002Fa> ·\n  \u003Ca href=\"#supported-languages\" rel=\"nofollow ugc noopener\">Languages\u003C\u002Fa> ·\n  \u003Ca href=\"#quickstart\" rel=\"nofollow ugc noopener\">Quickstart\u003C\u002Fa> ·\n  \u003Ca href=\"#nine-mcp-tools\" rel=\"nofollow ugc noopener\">MCP tools\u003C\u002Fa> ·\n  \u003Ca href=\"#how-it-compares\" rel=\"nofollow ugc noopener\">Comparison\u003C\u002Fa> ·\n  \u003Ca href=\"#for-teams--enterprises\" rel=\"nofollow ugc noopener\">Hosted\u003C\u002Fa>\n\u003C\u002Fsub>\u003C\u002Fp>\u003Chr \u002F>\n\u003Cp align=\"center\">\n  \u003Cstrong>measure, locate, and fix what your AI ships\u003C\u002Fstrong>\u003Cbr \u002F>\n  \u003Cstrong>code health that predicts real bugs\u003C\u002Fstrong>  ·  \u003Cstrong>ROC AUC 0.74 across 21 repos\u003C\u002Fstrong>  ·  \u003Cstrong>2.3×\u003C\u002Fstrong> CodeScene's defects under a fixed review budget\u003Cbr \u002F>\n  \u003Cstrong>graph-aware refactoring plans\u003C\u002Fstrong> your agent can execute  ·  \u003Cstrong>up to −96% context tokens\u003C\u002Fstrong>  ·  \u003Cstrong>−70% agent tool calls\u003C\u002Fstrong> at answer-quality parity\n\u003C\u002Fp>\u003Cp align=\"center\">\u003Csub>Measured, reproducible, on public codebases. \u003Ca href=\"#benchmarks\" rel=\"nofollow ugc noopener\">See the benchmarks ↓\u003C\u002Fa>\u003C\u002Fsub>\u003C\u002Fp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Frepowise-dev\u002Frepowise\u002FHEAD\u002F.github\u002Fassets\u002Fdemo.gif\" alt=\"repowise demo: Claude Code querying the codebase through repowise's MCP tools, then a tour of the local dashboard\" width=\"100%\" \u002F>\u003Chr \u002F>\n\u003C\u002Fdiv>\u003Cp>AI now writes a large and growing share of the code, and the humans accountable\nfor it have to trust what ships. A score that says \u003Cem>\"this file is risky\"\u003C\u002Fem> isn't\nenough: you need to know \u003Cstrong>where\u003C\u002Fstrong> the risk concentrates and \u003Cstrong>how\u003C\u002Fstrong> to fix it.\u003C\u002Fp>\n\u003Cp>repowise closes that loop. It indexes your codebase once and scores \u003Cstrong>every file\nfor defect risk, maintainability, and performance\u003C\u002Fstrong> from 25 deterministic\nmarkers, calibrated against a real defect corpus, no LLM, in under 30 seconds\n([the proof ↓](#-\u003C\u002Fp>\n",1784240407959]