Measured, not claimed
Used by developers at
Engineers who use Repowise for their projects work at these companies.
One index. Four answers.
AI made producing a change cheap. Understanding what it touches is still expensive, and someone pays that cost on every task. Repowise pays it once, in one index that every agent, reviewer and team reads.
Agents guess.
One question over MCP returns the answer, the lines it came from and everything that depends on them.
31.6% fewer agent output tokensn = 43 · p = <0.0001 · Codex (gpt-5.6-sol) · django/django at a single pinned commit · 2026-08
See agent context› is it safe to simplify provider_retry_wait?
get_context · get_why · 2 calls
Not as written. Seven providers call it, and its wait follows the 429 rate-window decision.
base.py:522Before the edit
Keep the rate-window wait. Run the 10 tests that reach it.
Humans re-verify.
Every pull request gets one comment: the callers it reaches, the files that usually move with it and the tests to run first.
anthropic.py, openai.py, gemini.pyrepowise bot · on the PR
Reaches 189 files. Three providers usually change with base.py and are missing.
Teams forget.
Each merged change becomes a Change Record with its owners, tests and the decisions it crossed, and your policy checks it in CI.
Simplify provider_retry_wait
merged · 4 files · component providers/llm
base.py:522repowise check · require_owner_review
The change crosses a recorded decision. An owner reviews it before it merges.
Debt hides.
Every file is scored on defect risk, maintainability and performance, and the riskiest come with a named fix.
2.3x more defects found, same review budgetn = 2,770 · p = 0.003 · 2,770 files scored by both tools at the same leakage-free commit · 2026-08
See code healthproviders/llm/base.py6.4providers/llm/anthropic.py7.9providers/llm/openai.py8.3base.py · 6 bug fixes in 6 monthsFix first · extract method
Split provider_retry_wait into 3 helpers. Run the 10 reaching tests.
› is it safe to simplify provider_retry_wait?
get_context · get_why · 2 calls
Not as written. Seven providers call it, and its wait follows the 429 rate-window decision.
base.py:522Before the edit
Keep the rate-window wait. Run the 10 tests that reach it.
Also in the indexPerformance traces across files, secrets across the whole git history, docs that drifted from the code, and contracts between repositories.
Same evidence, every surface
One index behind your agent, your pull requests, your editor and your team's dashboard. Nothing new to switch to.
Your agent calls it over MCP
Ten MCP tools, session hooks and a generated CLAUDE.md, so the agent starts with the map.
hosted · Claude.ai and ChatGPT reach it too
One comment per PR with callers, missing tests and risk, and a merge check beside it.
hosted · on every pull request
File health in the status bar, blast radius from source control, decisions on hover.
Architecture, owners, hotspots, decisions and health in one place, shareable by link.
hosted · current on every push, one link for the team
Two ways in
Give your agent the whole repo, and keep the map current without thinking about it.
Know what every change touched, what it was checked against and who owns it, across every repository.
Coming to hosted and enterprise
Trained models that learned from years of real commits and fixes. Paste a bug report and Foresight ranks the files the fix will touch, each with a reason. No LLM, milliseconds on a CPU.
Issue #4127 · open
Checkout sometimes charges twice after a timeout
On a slow connection the payment page times out, the customer tries again, and the card is charged twice.
payments/retry.pyfix lands here
41def charge_with_retry(order):42 try:43 return charge(order, key=new_key())44 except Timeout:45 return charge(order, key=new_key())The retry asks for a new idempotency key, so the second attempt becomes a second charge.
Keyword searchForesight · files the fix will touch
search rank
payments/retry.pyfixed for a similar timeout bug 3 weeks ago.71#9billing/ledger.pychanges with retry.py 9 of 11 times.14#7payments/gateway.pyraises the Timeout that retry.py catches.06#6web/checkout_page.tsxmatches “checkout” 14 timesUI only, no payment calls.02#1tests/test_checkout_ui.pymatches “checkout” 9 timestests the page, not the charge.01#2README.mdmatches “charges” 3 times.01#3web/checkout.cssmatches “checkout” 6 times.01#4docs/checkout.mdmatches “timeout” 2 times.01#5Repowise 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.
Yes. You can open and browse supported public repositories without an account or installation.
The Free hosted experience includes 10 grounded answers each month. Those answers use indexed repository evidence instead of treating the codebase as an unstructured prompt.
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.
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.
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 repository with unlimited seats.
Start with a real repository
Public repositories cost nothing to index. Pro adds your private ones and keeps them current on every push.
Evidence you can inspect
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Reverse engineer anything with agents, from app behavior down to native binaries.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
