PR Review Engine
review · summaryMulti-agent review on every pull request. Inline comments with severity + recommended fix. PR summary auto-posted at the top.
Learn moreFrom the diff in your editor to the merged-PR analytics view — Mesrai owns the entire review workflow with one consistent engine, controlled by rules you write and models you choose.
Multi-agent review on every pull request. Inline comments with severity + recommended fix. PR summary auto-posted at the top.
Learn moreConvert any PR finding into a trackable Issue in your workspace. Status, severity, assignee, owning repo — every finding has a home.
Custom rules in plain English or YAML. Per-org, per-repo, per-directory overrides. Auto-generate from past merged PRs.
Learn moreRun the same review locally, in CI, or as a pre-push hook. CLI reviews land in your workspace under /cli-reviews with full audit trail.
Learn moreImport rule files from Cursor, GitHub Copilot, Claude, Windsurf, Cody, OpenCode, Aider. One ruleset for your IDE assistant + Mesrai cloud + CLI.
Learn moreOverride the default review prompt per repo. Add your domain context — Mesrai applies it to every PR.
Pick the minimum severity that posts comments — low / medium / high / critical. Tune the noise floor.
Replace the default start-of-review / end-of-review messages. Voice the bot however your team likes.
Mesrai remembers decisions across reviews. Auditable. Promote / discard from the dashboard.
Connect OpenAI, Anthropic, Vertex, Bedrock, or any compatible LLM. You pay your provider directly.
Per-event routing across email, in-app, Slack, Discord, webhook. Critical events sticky-banner the app.
Connect external tools via the MCP protocol — pull in Jira context, Datadog alerts, your own services.
SSO (SAML), role-based access, audit logs, centralized YAML config, merge gates on critical findings.
PR cycle time, deploy frequency, code health by category, throughput, lead time breakdown, per-developer trends.
A well-tuned Mesrai review catches 70-90% of real issues with a false-positive rate under 10% on most codebases. Accuracy improves over time as Mesrai Rules tune themselves from your team's reactions to past findings — bot accuracy is a moving target, but the trend is consistently upward inside any given workspace.
Mesrai Rules are team-specific review rules written in plain English or YAML — things like "always use the structured logger, never console.log" or "tests must live next to their source file". Mesrai applies them on every PR alongside the built-in bug, security, and performance agents.
Yes — BYOK is supported on every paid plan. Connect OpenAI, Anthropic, Google Vertex, AWS Bedrock, Groq, Cerebras, or any OpenAI-compatible endpoint. Mesrai charges the platform fee; your LLM bill flows directly to your provider. Typical savings versus AI-Included at high volumes: 30-60%.
Yes. The mesrai-graph AST engine builds a semantic index across the whole repository, so the review understands cross-package dependencies, type imports, and architectural boundaries — not just the diff in isolation. Tested on monorepos of 1M+ LOC.
Three ways. (1) The cloud reviewer runs automatically on every PR via the git-provider webhook. (2) The Mesrai CLI (`npx mesrai review`) can run as a CI step inside GitHub Actions, GitLab CI, CircleCI, and similar. (3) The pre-push hook gives local-machine review before the PR even opens.
Yes. 14 days, every Pro feature unlocked, 1,000 AI credits included. No credit card required, no auto-charge at the end. Sign up at app.mesrai.com.
Two-minute install. First PR reviewed today. No credit card.