repowiserepowise
Features
Code health
A defect-validated 1 to 10 score per file. Zero LLM.
Agent provenance
See how much of your code AI wrote, and whether it is healthy.
AI context (MCP)
Ten MCP tools that give your agent real codebase context.
Change risk
A 0 to 10 defect-risk score for any commit or PR.
Security
Reachability-aware CVE triage on your dependency graph.
Auto wiki
A documented wiki of your codebase that rebuilds itself.
Git intelligence
Hotspots, ownership, hidden coupling, and bus factor.
Architecture (C4)
C4 system context, containers, and components.
Decisions
Architectural decisions mined from eight sources.
Solutions
developers
Give Claude Code, Cursor, and any MCP client a queryable model of your repo.
teams
One shared index, one credit pool, one org install. The whole team on the same brain.
team leads
Flag the risky PRs, the hotspots, and the hidden coupling, on every pull request.
engineering leaders
See how much of your code AI wrote, whether it is healthy, and who owns it.
security
CVE triage that knows whether you actually call the vulnerable code.
enterprise
Self-hosted, air-gapped, and commercially licensed for the whole org.
Book a demo →
Guides
Code healthAI context & MCPGit intelligenceChange riskArchitectureAuto-wikiDecisions & ADRsAgent provenanceSecurityAll guides →
Compare
vs CodeScenevs DeepWikivs Sourcegraphvs Cursorvs GitClearvs SonarQubeAll comparisons →
PricingExploreBlogDocs
Star—Sign in
Start free
  1. Home
  2. Blog
BLOG

Codebase intelligence, explained

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

Index your repo freeBrowse the guides
AllComparisonsGuidesMCP & AI AgentsEngineeringUse CasesConceptsIndustryAI Coding

The data behind these posts

Every number we publish, with its conditions. Measured against four open source tools and a bare-agent control, with sample sizes, p-values, raw data, and the rows where we lose.

See the benchmarks

Featured

mcp10 min read

Your MCP Server Is Probably Not Being Called

We ran the same MCP servers and questions on two agent harnesses. Under Claude Code most tools were barely called at all. Here is the measured cause of it.

2026-08-06Read →
use-cases10 min read

Case Study: We Build repowise With repowise

repowise is developed against an index of itself: every pull request is gated by the same risk and health checks we ship. The setup, measurements, and limits.

2026-07-04Read →

Latest

mcp10 min read

Your MCP Server Is Probably Not Being Called

We ran the same MCP servers and questions on two agent harnesses. Under Claude Code most tools were barely called at all. Here is the measured cause of it.

2026-08-06Read →
engineering8 min read

35x or 16%? we published both, and they measure different things

The same tool on the same codebase gives 35.6x fewer tokens on one measurement and 15.9% on another. Both are correct, and they measure different things.

2026-08-06Read →
engineering7 min read

a tool that did nothing came out 43% cheaper than the bare agent

A tool that never called its own server measured 43% cheaper than a bare agent. Prompt caching explains it, and it shows why dollar-cost benchmarks mislead.

2026-08-06Read →
engineering12 min read

how to benchmark a codebase tool so the number survives a rerun

JetBrains reran two token-saving claims and both collapsed. Here is the eight-part methodology we used to build a benchmark that survives an independent rerun.

2026-08-06Read →
engineering10 min read

we benchmarked ourselves against four open source tools and came last

We ran a sealed retrieval benchmark against four open source tools, scored last at 0.228, published it, found the bug, fixed it, and reran the sealed half once.

2026-08-06Read →
use-cases10 min read

Case Study: We Build repowise With repowise

repowise is developed against an index of itself: every pull request is gated by the same risk and health checks we ship. The setup, measurements, and limits.

2026-07-04Read →
guides8 min read

CLAUDE.md & AGENTS.md: The Complete Guide

What CLAUDE.md and AGENTS.md are, what to put in them, best practices, and how to keep them fresh automatically. Learn to give coding agents real repo context.

2026-06-26Read →
guides9 min read

Code Health: The Complete Guide (2026)

Code health is a defect-validated measure of how risky code is to change, scored from 49 deterministic markers across three pillars. Reproduce it on your repo.

2026-06-26Read →
guides10 min read

Codebase Documentation That Stays Current

Living codebase documentation rebuilds on every commit, scores its own freshness, and feeds AI agents. Learn how it works and start with repowise free.

2026-06-26Read →
guides9 min read

Git Intelligence: Hotspots, Ownership & Coupling Explained

Git intelligence reads your git history to surface hotspots, code ownership, bus factor, and change coupling. Learn how the signals work and where to start.

2026-06-26Read →
guides9 min read

How to Prioritize Technical Debt (Impact-per-Effort)

Prioritize technical debt by impact-per-effort: rank refactoring targets, find dead code, and read coverage as risk. Build your ranked worklist today.

2026-06-26Read →
mcp10 min read

Giving AI Coding Agents Real Codebase Context

Codebase context for AI agents turns one index into 10 task-shaped MCP tools, cutting real agent-loop output tokens 31.6% on Codex. See how structured context works, try repowise.

2026-06-26Read →

Index your repo free

Index your repo freeRead the docs
repowiserepowise

Codebase intelligence for AI agents. Open source under AGPL-3.0, hosted SaaS for teams.

Features
  • Code health
  • Agent provenance
  • AI context (MCP)
  • Change risk
  • Security
  • Auto wiki
  • Git intelligence
  • Architecture (C4)
  • Decisions
Solutions
  • For developers
  • For teams
  • For team leads
  • For engineering leaders
  • For security
  • For enterprise
Compare
  • vs CodeScene
  • vs DeepWiki
  • vs Sourcegraph
  • vs Cursor
  • vs GitClear
  • vs SonarQube
  • vs Snyk Code
  • vs Codacy
  • vs Code Climate / qlty
  • vs Qodo
  • vs Greptile
  • vs Swimm
  • vs CodeRabbit
  • vs CodeGraph
  • vs Graphify
  • vs Serena
  • vs code-review-graph
  • All comparisons
Guides
  • Code health
  • AI context & MCP
  • Git intelligence
  • Change risk
  • Architecture
  • Auto-wiki
  • Decisions & ADRs
  • Agent provenance
  • Security
  • All guides
Product
  • Pricing
  • PR Bot
  • Browse indexed repos
  • Health leaderboard
  • Book a demo
Resources
  • GitHub
  • Docs
  • Benchmarks
  • Blog
  • Discord
About
  • Founder
  • Architecture
  • Contact
Legal
  • Privacy
  • Terms
  • Security
© 2026 repowise. AGPL-3.0.hello@repowise.dev
Featured on Aura++