Features
Human-in-the-loop approval – review, edit, and approve AI comments before publishing
Multi-model AI – runs Claude, Gemini, and GPT in parallel, smart-merges findings
Deep Review (Agent Mode) – AI explores full codebase, runs linter, checks tests
Full project context – examines related files, imports, dependencies
Jira integration – reads ticket context, verifies acceptance criteria against diff
Security scanning – 20+ built-in rules + AI security pass (SQLi, XSS, secrets)
Confidence scoring – each finding rated 0-100%, filter low-confidence noise
Code quality scores – 6-category assessment: design, clarity, error handling, complexity, testability, production readiness
Review Profiles – named configurations for models, API keys, prompts, rules
.gitautoreview.md config file – team-wide rules versioned in git
BYOK (Bring Your Own Key) – code goes directly to your AI provider, zero storage
VS Code extension – native editor integration
GitHub (Cloud & Enterprise) support
GitLab (Cloud & Self-Managed) support
Bitbucket (Cloud, Server & Data Center) support
Autonomous vulnerability scanning and PR generation
PR review for quality, security, and best practices
Legacy COBOL to Java migration with testing
Incident triage and root cause analysis
Agent Canvas: manage multiple agents in one workspace
Cloud agents run even when your machine is off
Schedule recurring tasks via cron or event triggers
Trigger workflows from GitHub, Slack, PagerDuty
Model-agnostic: supports Claude Code, Codex, Gemini CLI, MiniMax M2.7
Isolated sandbox execution on VM or cloud
Fine-grained access control and budget guardrails
Audit trails for enterprise compliance
Self-hosted deployment in your VPC
Open-source SDK for custom agent development
In-chat model switching with saved LLM profiles
