AI code reviewer
Severity-ranked review findings with line references and a concrete fix for each.
Your key stays in your browser.It goes straight to the provider, never to our servers, and we neither log nor keep it. Use a dedicated key with a spending cap, and delete it in the provider's dashboard when you are done.
Input
Result
The result will appear here.A second pair of eyes before you open the pull request. Paste a function, a file or a git diff and get findings ordered Critical, High, Medium, Low — each with the lines it concerns, the input or situation that triggers the problem, and the corrected code. The prompt adapts the review_code pattern from danielmiessler/Fabric and checks correctness, security (injection, path traversal, secrets, missing authorisation), error handling, performance such as N+1 queries, and readability, in that order of importance.
How it works
- Snippets are line-numbered before review; diffs are cited as file:line in the new version, worked out from the @@ hunk headers.
- A focus setting narrows the review to bugs, security, performance or readability — Critical issues are reported whatever the focus.
- When the code is fine the review says so, instead of inventing findings to fill the page.
Where your data goes
With your own key, what you type and the key go from your browser straight to the provider you choose; neither passes through Hysen Labs. In hosted mode, your text goes through our server to our provider (DeepSeek) and is billed in credits; we keep the token counts and cost of each run for billing, never the text itself or the answer. How the provider handles the text is governed by its own privacy policy.
This tool handles keys and credentials, so nothing about a run is saved, not even to your own history.
About your API key
We do not collect, store or leak your key: it lives only in this page's memory (unless you tick “remember in this tab”) and is gone when you close it. Still, treat any key you have pasted into a web page with care — create a dedicated key with a spending cap for use here, and delete or rotate it in your provider's dashboard when you are done.
What it costs
This tool is free, with no sign-in and no points.
Common questions
- Does this replace a human review?
- No. It is good at mechanical mistakes — a missing await, string-built SQL, an unchecked null — and at spotting them fast. It does not know your architecture, product requirements or the rest of the codebase, which is what a colleague's review is really for.
- Who sees the code I paste?
- Only the AI provider you choose. The request goes from your browser to that provider with your own API key and never touches hysenlabs.com. Reviewing company code? Check the provider is approved, and use a throwaway key with a spending cap.
- Why are the line numbers off for my diff?
- For a diff the model computes new-file line numbers from each @@ header, which it can occasionally miscount on large hunks. Paste the whole file instead of a diff when exact line numbers matter; snippets are numbered by the tool itself, so those references are exact.
- Which model gives the best reviews?
- Larger reasoning models find more real bugs and invent fewer; small, fast models tend to fill the page with style nits. For security-sensitive code use the strongest model your key can reach.
The open-source behind it
This tool's prompt is adapted from danielmiessler/Fabric (MIT) and runs on the model you choose. To use the same capability from the command line or inside your own program, start with that project.
danielmiessler/FabricAlso known as
- ai code review
- online code reviewer
- code review tool free
- review my code ai
- find bugs in code