v0.60.0is outSee what changed

Open source · codebase intelligence for the agent era

Your agents read the code.Repowise knows the rest.

The history, owners, tests and decisions behind every file, in one index kept current on every commit. Your agents read it before they edit, and every pull request is checked for what it breaks, what it leaves untested and what it puts at risk.

Or ask your agentSet up Repowise for this repository. Follow https://docs.repowise.dev/hosted/setup.md
Your repo → one living index → every surface

Used by developers at

  • Microsoft
  • Red Hat
  • Siemens
  • AWS
  • Atlassian
  • Accenture
  • NVIDIA
  • SAP
  • Meta
  • Thoughtworks
  • Wix
  • EY
  • Deutsche Telekom
  • Wipro
  • Glovo
  • Google DeepMind
  • Apple
  • OpenAI
  • Intel
  • IBM
  • Oracle
  • Salesforce
  • Adobe
  • Cisco
  • Cloudflare
  • GitLab
  • Spotify
  • PayPal
  • Adyen
  • Revolut
  • Wise
  • Nubank
  • UBS
  • Santander
  • Thomson Reuters
  • Booking.com
  • Trivago
  • ByteDance
  • Tencent
  • LINE
  • Samsung
  • Yandex
  • Arista Networks
  • F5
  • OVHcloud
  • GoDaddy
  • Autodesk
  • Intuit
  • Rippling
  • Gusto
  • SurveyMonkey
  • Scale AI
  • Midjourney
  • Criteo
  • CleverTap
  • TCS
  • Capgemini
  • Endava
  • Nagarro
  • Fujitsu
  • Shopware

Engineers who use Repowise for their projects work at these companies.

The problem

Agents write fast. They write without the map.

An agent reads a few files, edits one and moves on. The callers, the history and the tests it never opened are where the change breaks.

The index

One index of everything an agent never reads.

Repowise maps your repo once and keeps it current on every commit.

Structure
Symbols, imports and every call edge
History
Churn, co-change and owners from git
Tests
Which tests reach which code
Decisions
The why behind the code, linked to it
See every feature

Agents read it first

Every agent asks before it edits.

Ten MCP tools, over the open Model Context Protocol, give Claude Code, Cursor, Codex and any agent the callers, owners and tests of a file before it edits.

31.6%fewer agent output tokensCodex (gpt-5.6-sol) on django/django at a single pinned commit

See agent context

Code health

Know which files break next.

Every file gets a 1 to 10 score from 23 deterministic markers, validated against real bug fixes and tracked commit by commit on the dashboards in every plan.

0.74
AUC predicting the next bug fix
n = 2,826 · 21 repositories, 9 languages, 2,826 files · 2026-08
2.3x
more defects found under the same review budget
n = 2,770 · p = 0.003 · 2,770 files scored by both tools at the same leakage-free commit · 2026-08

Then fix it

Refactoring plans
Ranked plans, each with a prompt to hand to your agent.
Dead code
Unused files, exports and packages, each with a confidence.
Performance
N+1 queries, I/O in loops and blocking calls, traced across files.

Integrations

Works with the agents and tools you already run.

Coding agents, code hosts, CI and the team's tools all read the same index.

See all integrations
  • GitHub
  • GitLab
  • Bitbucket
  • GitHub Actions
  • Jira
  • Confluence

The PR bot

AI code review for about 5 cents a reviewed PR.

Every pull request gets what it breaks, coverage on the lines it changed and a review that learns from your team's replies. When a PR is fine, it stays quiet.

Never more than 60 cents a PR · $5 a repo a month by default

How the bot works
What it breaksThe callers a change reaches, named before anyone merges it.
Coverage on every changed lineThe lines a pull request adds that no test runs.
Learns from your repliesA reply on a review is saved for your team and applied in the next one.
Priced per PR, not per seatAbout 5 cents a reviewed PR from credits. The risk, coverage and health checks cost nothing.

For engineering organizations

Govern agent‑written code at scale.

The same index, run where your code lives, with a record of every change across every repository.

Self-hosted or on-prem
In your cloud, in your data centre or fully air-gapped.
An audit trail
A Change Record for every merged change: what it touched, the tests that reach it, which agent wrote it and what happened after.
Portfolio health
Health, hotspots and owners across every repository.
Security rollup
Secrets and vulnerable dependencies across the portfolio.
Jira and Confluence
Findings and decisions where the team already plans.

Plans

Start free. Grow into Teams. Run it your way on Enterprise.

  • Free

    $0

    Public repos, free PR checks for risk and coverage, and 10 AI answers a month.

  • Pro

    $15/mo

    Private repos, a fresh index on every push and AI review from credits.

  • Teams

    $20/seat/mo, 3 seats min

    Shared repos, portfolio health and one PR bot across the org.

  • Enterprise

    Self-hosted

    Your cloud or on-prem, unlimited repos and a named contact.

Compare every plan

Get started

Point it at a repo. See what it knows.

Paste a repo

A public repo maps free, no card.

Or browse repos already mapped

See pricing

Free, Pro, Teams and Enterprise, side by side.

See pricing

Talk to us

Self-hosting, security and rollout across the org.

Talk to usRead the guide: Who Wrote This?
FREQUENTLY ASKED

Questions, answered

What does Repowise index?

Repowise analyzes source structure, dependencies, call relationships, git history, ownership, code-health signals, tests, and engineering decisions. It turns that evidence into one codebase model that agents query over MCP, pull requests are checked against, and every merged change is recorded in.

Can I browse without signing in?

Yes. You can open and browse supported public repositories without an account or installation.

What do I get when I sign in?

Free indexes up to 2 public repositories and includes 10 grounded answers a month, which use indexed repository evidence instead of treating the codebase as an unstructured prompt. Pro ($15/month) adds private repositories and AI review on pull requests, about 5 cents a reviewed PR from credits and never more than 60 cents a PR. Teams ($20/seat/month, 3-seat minimum) shares them across a team.

What does hosted add over the open-source CLI?

The same engine, run for you. Hosted re-indexes on every push, lets Claude.ai and ChatGPT reach your index over MCP, comments on pull requests, scans for secrets and new vulnerabilities, gives the team one shareable link, and includes models and credits so nobody manages an API key.

Does Repowise replace my coding agent or IDE?

No. Repowise supplies codebase context to developers and existing tools through the hosted application, CLI, and Model Context Protocol. Your agent or editor remains where the work happens.

Can I run it myself or inside my organization?

Yes. The core engine is open source under AGPL-3.0 and runs locally with your model provider or a local model. For organizations, the commercial edition runs self-hosted in your VPC or air-gapped, with Change Records, change policy and cross-repository views, licensed per seat, per repository or enterprise-wide.