Blar reviews your Pull Requests using specialized agents that analyze your code for bugs, bad practices, optimization opportunities, and more. It also adapts to your team’s specific rules through a custom Wiki and a continuous learning system.
Agents are intelligent modules, each focused on a specific dimension of code. When reviewing a PR, Blar activates the selected agents, and each one performs a targeted analysis.
🐛 Debugger Agent: Detects bugs, logic errors, and problematic flows in your code.
⚡️Optimizer Agent: Identifies inefficient code snippets and suggests performance improvements.
🛡Cybersecurity Agent: Reviews for vulnerabilities, unsafe library usage, and validation issues.
🎨 Design Patterns Agent: Suggests structural improvements based on recognized design patterns.
🐽 Code Smells Agent: Detects poor practices and “code smells” like overly long functions or unclear naming.
🎯 You can enable or disable agents depending on your needs and your current plan.
Blar doesn’t rely on static analysis alone — it learns from your team:
Learns from your feedback
When you give a comment a 👍 or 👎, Blar records that to improve future reviews.
Learns from your rules (Wiki)
You can define your technical standards in a Wiki. Blar uses it as a guide during every review.
Learns from your conversations
If you chat with Blar inside a PR (e.g., asking it to ignore specific rules), it will remember that behavior for future reviews in the same context (function, repo, or team).