Codebase intelligence for AI coding agents.
Your agent stops guessing. Starts knowing.

repowise.dev · pip install repowise · Discord ·

Repowise indexes your codebase into four intelligence layers — dependency graph, git history, auto-generated documentation, and architectural decisions — then exposes them to Claude Code (or any MCP-compatible agent) through precisely designed tools.

The result: your AI agent answers "why does auth work this way?" instead of "here is what auth.ts contains."

Repo	What it does
repowise	Core engine — AST graph, git analytics, wiki generation, dead code detection, 8 MCP tools. pip install repowise
claude-code-prompts	Independently authored prompt templates for AI coding agents — system prompts, tool routing, agent delegation, memory, multi-agent coordination
modpack	15 Claude Code skills that change how your agent thinks, debugs, and reviews. npx skills add repowise-dev/modpack
repowise-bench	SWE-QA benchmark — 36% cost reduction, 49% fewer tool calls, quality at parity

pip install repowise
cd your-project
repowise init        # builds all four layers (~25 min first time)
repowise serve       # MCP server + local dashboard

_{Built for engineers who got tired of asking "why does this code exist?"
[email protected]}