Yerassyl khan Akhmetov@yeraasil

Modern software teams review hundreds of lines of code through Pull Requests every day. Manual code review is essential, but it can be time-consuming, inconsistent, and difficult to scale. Important issues such as security vulnerabilities, missing tests, performance problems, and implementation mistakes can be overlooked, especially in large Pull Requests. DevGuard AI is an AI-powered Code Review Assistant that automatically analyzes GitHub Pull Requests and produces a structured review report. A developer provides a GitHub repository and Pull Request number through a simple web interface. The backend retrieves the Pull Request metadata, changed files, patches, commit information, and project documentation such as README files. This context is passed to multiple specialized AI agents. Instead of relying on one general-purpose reviewer, DevGuard AI uses specialized agents with different responsibilities: • Code Agent analyzes code quality, bugs, maintainability, and potential performance issues. • Security Agent looks for vulnerabilities, authorization problems, insecure practices, and potential data exposure. • Test Agent analyzes test coverage and identifies important missing test scenarios. • Aggregator Agent combines the results, removes duplicate findings, prioritizes existing issues, and generates a concise review report. The final result contains structured findings with severity, category, affected file, line number when available, explanation, and recommended remediation. Developers can also view statistics, agent execution status, a summarized report, and a Markdown version of the review. The target users are software developers, engineering teams, and organizations that use GitHub Pull Requests as part of their development workflow. The main creative aspect of DevGuard AI is its multi-agent architecture. Each agent focuses on a specific engineering concern, while the Aggregator creates a unified review from their results. The agents can analyze the same Pull Request independently and work in parallel, making the system easier to extend with additional specialized reviewers in the future. DevGuard AI combines GitHub integration, FastAPI, PostgreSQL, and AI agents into a single workflow that can turn a Pull Request into an actionable code review within a few steps.

🌎 Online Hackathon | 💻 Online Build: Sept 26 - Oct 5, 2026 A virtual, global hackathon. Build from anywhere in the world. Dark Factory is the official hackathon of WeAreDevelopers World Congress North America, presented by BAND, but you don't need to be in San Jose to take part. For one week, you build a software factory in BAND Desktop: a band of coding agents that plans work, implements it and checks its own results. 🎟️ Bonus for sign-ups: you are eligible for a free ticket to WeAreDevelopers World Congress North America in San Jose (Sep 23–25). If you do go, stop by the BAND booth: a surprise is waiting for you.

💻 Online Hackathon | ⏳ Build: 48 hours | 📅 September 25–27, 2026 The official IBM Bob 2.0 hackathon. Build what's next in AI-assisted development, alongside the developers and experts shaping it. ⭐ Get help from experts throughout the event 🤝 Join a team or build solo 💰 Prize pool: $12,000 🧑🏻‍💻 Register before the Kick-Off Stream to start building with Bob

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.