Mega Hackathon ITMO 2026, AI, Coding Agents
# Final Project Report: AI-Powered SDLC Automation ## ITMO Megaschool 2026, "Coding Agents" Track --- ## Table of Contents 1. [Project Overview](#project-overview) 2. [Architecture and Technologies](#architecture-and-technologies) 3. [Two Independent Agents](#two-independent-agents) 4. [Operating Modes: CLI and Cloud Deployment](#operating-modes-cli-and-cloud-deployment) 5. [GitHub Integration via Webhooks](#github-integration-via-webhooks) 6. [Quality and Testing](#quality-and-testing) 7. [Areas for Improvement](#areas-for-improvement) 8. [Conclusion](#conclusion) --- ## Project Overview [Assignment Link](https://docs.google.com/document/d/1JIRdWHDSp1RsT7A0_wlADy_4lTHEg-DwoeIjSjB4MBo/edit?tab=t.0#heading=h.ess5k7fvs5zw) [Pitch Link](https://drive.google.com/file/d/1EbgpbNtI6KWY-YZNkeblTyDxq1YMztPB/view?usp=share_link) A full-featured automated Software Development Lifecycle (SDLC) system has been developed based on LangChain, capable of autonomously solving full development cycle tasks in GitHub: - **Issue Analysis** — understanding requirements and task context - **Autonomous Development** — exploring the codebase, making changes - **Pull Request Creation** — formatting and publishing changes - **Code Review** — automatic analysis and code quality verification - **Iterative Development** — processing feedback and improving the solution The system works with **any programming language** and can be connected to **any GitHub repository** via cloud deployment. --- ## Architecture and Technologies ### Technology Stack #### LangChain Framework The system is built on **LangChain** — a modern framework for creating agent systems: - **`create_tool_calling_agent`** — base agent architecture with tool calling support - **`AgentExecutor`** — agent execution orchestration with iteration management (up to 20 iterations for complex tasks) - **Custom Tools** — integration of custom tools via the `@tool` decorator - **OpenAI-compatible LLM Integration** — connectin
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.