CodePeel reviews every pull request for security holes, broken logic, and race conditions — then opens a PR with the fix applied. No API key. No config.
527
PRs reviewed
2,143
Issues found
29s
Avg review
User input concatenated into SQL query. Use parameterized queries to prevent injection.
db/queries.ts:23
Setup
One click from the marketplace. No CI/CD changes needed.
CodePeel triggers automatically — no commands, no webhooks to configure.
Security score, findings, walkthrough, and auto-fix PRs — typically under a minute.
The Difference
feat/network-helper wants to merge into main · 3 files changed
The Payoff
Every other reviewer leaves you a comment. CodePeel writes the patch, opens a real PR, and waits for your merge.
SQL Injection
db/queries.ts:23
Patch generated
parameterized query
+12 −8
codepeel/fix-pr-42
Shipped ✓
health 41 → 87
Features
Free users get the full review engine. Pro adds the fixes and tests.
When CodePeel finds a fixable issue, it opens a real PR with the fix applied to your branch. Review the diff, merge, done.
Every PR runs through bug detection, OWASP security scanning, and architecture analysis in parallel. Findings are severity-rated.
Generates framework-appropriate tests (Jest, Vitest, pytest, flutter_test, Go, Rust) and opens them as a PR. Covers happy paths and error cases.
Commit statuses that fail if critical findings exist. Works with your existing branch protection rules. Block bad merges automatically.
Everywhere You Code
GitHub, your editor, and your AI coding agent — all feeding into one review engine, one account, one quota.
codepeel-vscode
Review changes before you push. Inline comments, one-click fixes, and severity ratings — right in your editor.
@codepeel/mcp-server
Let your AI coding agent review its own output. Works with Claude Code, Cline, Roo, Kiro, and any MCP client.
Pricing
Early adopter pricing — these rates are locked for your account permanently.
Free
Pro
50% off — locked forever for early adopters
Max
Launch price — locked forever
Security
We analyze your diffs in-memory and never persist raw source code. Review results power your dashboard — your codebase never leaves GitHub.
Diffs are analyzed in-memory and never persisted. We store review results (findings, scores) to power your dashboard — not your source code.
Your code is never used to train any model. We use zero-retention LLM providers exclusively.
Read-only access for analysis. Write access is only used for auto-fix branches — never touches your main branch.
FAQ
No. CodePeel provides AI analysis out of the box. No OpenAI key, no model config, nothing to set up. Install the GitHub App and you're done.
Diffs are analyzed in-memory during review and not persisted. We store review results (findings, health scores) to power your dashboard. Your source code stays on GitHub.
CodePeel flags bugs, security vulnerabilities, and architectural issues — not style preferences. You can dismiss findings or use @codepeel learn: to suppress patterns you don't care about.
Private repositories require Pro ($9.99/mo). The free tier works on up to 3 public repositories with 30 reviews per month.
CodePeel reviews your PRs, opens fix PRs with the code applied, generates tests, and works inside your AI coding agent (Claude Code, Cursor) — at $9.99/user/month with no API key required.
Install the GitHub App. Open a PR. Get your first review.
Get Started Free