BLOG

Codebase intelligence,
explained

Guides on auto-generated documentation, MCP tools for AI agents, git intelligence, and how repowise compares to other tools.

Latest

Security review on a Python monolith with 19 hotspots
use-cases10 min read

Security review on a Python monolith with 19 hotspots

A security review codebase case study on a Python monolith: find 19 hotspots, map ownership gaps, and cut duplicate reads with one review path.

2026-05-10Read →
Generate claude.md from a real repo, not a blank page
guides12 min read

Generate claude.md from a real repo, not a blank page

Generate claude.md from repo architecture, ownership, and recent changes with MCP calls. Give Claude Code a day-one brief that cuts guessing.

2026-05-10Read →
RAG for code is not embeddings plus a vector store
concepts9 min read

RAG for code is not embeddings plus a vector store

RAG for code fails when it stops at chunks and vectors. See a 4-layer model with symbols, history, ownership, and a 36% cheaper retrieval path.

2026-05-10Read →
Claude Code vs Cursor on a flaky Flask refactor
ai-coding10 min read

Claude Code vs Cursor on a flaky Flask refactor

Claude Code vs Cursor on one Flask refactor: same prompt, exact edits, and where each agent lost the thread. See the repo context that changed the outcome.

2026-05-10Read →
When an MCP tool should return raw text, not answers
mcp9 min read

When an MCP tool should return raw text, not answers

A practical mcp tools design rule: return raw evidence when the model needs to inspect files, symbols, or decisions. See the boundary in Repowise.

2026-05-08Read →
Why we ship a graph-aware MCP server instead of file readers
mcp10 min read

Why we ship a graph-aware MCP server instead of file readers

Graph aware mcp cuts grep loops: resolve callers, dependents, and review impact in one hop. See the token and latency math.

2026-05-08Read →
Task-Shaped MCP Tools Beat Entity CRUD for Code Agents
mcp11 min read

Task-Shaped MCP Tools Beat Entity CRUD for Code Agents

See mcp tools design on a real regression: task-shaped tools cut re-reading and context loss, with 49% fewer calls and 27× fewer tokens.

2026-05-08Read →
The dead-code detector we shipped with Pagerank and git history
engineering11 min read

The dead-code detector we shipped with Pagerank and git history

Code hotspot detection as ranking, not a linter: Pagerank plus git history sorted quiet files from risky ones, so you can ignore the right 3.

2026-05-08Read →
47 dependents, 23 hotspots: a React refactor without folklore
use-cases11 min read

47 dependents, 23 hotspots: a React refactor without folklore

A large codebase refactor case study: see how dependency graphs, git history, and ownership signals ranked 23 hotspots before the first React edit.

2026-05-08Read →
5 Best Codebase Documentation Tools in 2026 (Compared)
comparisons11 min read

5 Best Codebase Documentation Tools in 2026 (Compared)

For decades, 'good documentation' was the white whale of software engineering. We all knew it was necessary, but the friction of maintaining it—manually upda...

2026-04-01Read →
repowise vs CodeScene: Full Codebase Intelligence Without the Enterprise Price Tag
comparisons9 min read

repowise vs CodeScene: Full Codebase Intelligence Without the Enterprise Price Tag

Technical debt is rarely a single catastrophic event. Instead, it’s a slow accumulation of 'paper cuts'—a complex module here, a high-churn file there, and a...

2026-04-01Read →
repowise vs DeepWiki: Self-Hosted Codebase Docs That Stay Fresh
comparisons9 min read

repowise vs DeepWiki: Self-Hosted Codebase Docs That Stay Fresh

Every engineering team eventually hits the 'Documentation Wall.' It’s the moment when the codebase grows faster than the human capacity to describe it. You’v...

2026-04-01Read →

Try repowise on your repo

One command indexes your codebase and generates docs, graphs, and MCP tools.