Qodo

A hands-on workshop repository and learning resource for building quality-first AI coding workflows with Qodo. It uses a self-contained FastAPI payments API called SignalPay, together with repository rules, agent skills, planning templates, behavior tests, static-analysis configuration, local verification gates, CI, pull-request review, and remediation guidance. The repository is maintained as the source of truth for the workshop and its one-hour teaching flow. The workflow runs from planning and reading repository rules, through test-driven implementation and local checks, to opening a pull request, reviewing it with Qodo, and resolving findings with PR Resolver before rerunning verification. Its payment exercise covers either a refund or capture-retry path and emphasizes idempotency, authorization checks, event-contract shape, and one event per idempotency key. The repository is intentionally not a production payment system; it is a guided API-first exercise with FastAPI documentation at `/docs` and no separate frontend or external service dependencies.

Rovo Dev is Atlassian's AI coding agent for software teams. It plans, generates, and reviews code through a terminal, IDE, Bitbucket, and GitHub, using context from Jira items, Confluence, connected code, documents, and organizational decisions in a sandboxed container. It supports planning and autonomous development, code search, context verification, model and agent selection, deterministic checks, AI review, human review, pull-request interaction within Jira, breaking epics into smaller issues, selecting suitable backlog work, managing review capacity, and clarifying underspecified requirements. Its standards workflow turns engineering standards written in Markdown, such as design-token rules, into reusable code-review rules for selected repositories or repository patterns, enforcing them by posting comments on pull requests.

Open Code Review is an open-source, AI-powered command-line code-review tool developed from Alibaba Group’s internal review assistant. It reads Git diffs and sends changed files to a configurable LLM through an agent with tool-use capabilities; the agent can read complete files, search the repository, and inspect other changed files for context before producing structured comments tied to source lines. Its hybrid architecture combines deterministic engineering with dynamic agent decisions: deterministic stages select and bundle files, match rules to file characteristics, and apply independent comment-positioning and reflection modules, while scenario-specific prompts and tools guide context retrieval and review. The `ocr scan` command audits complete files or directories without requiring a meaningful diff, and the project provides multilingual rules for issues including null-pointer exceptions, thread safety, cross-site scripting, and SQL injection. It supports configurable model endpoints, including OpenAI- and Anthropic-compatible endpoints, and requires Git 2.41 or newer.

An AI-powered code-review platform that automatically analyzes pull requests in repositories hosted on platforms such as GitHub and GitLab, producing review comments, summaries, and suggestions within source-control and code-hosting workflows.

Kilo Code is an open-source AI coding agent and agentic engineering platform from Kilo, available as extensions for VS Code and JetBrains, a command-line interface, and cloud services. It can generate and edit code across multiple files, provide inline autocomplete, run terminal commands and control a browser, and act as an external coding harness for cross-harness model testing. The platform includes Code, Plan, Ask, Debug, and Review agents, supports custom agents, allows model switching during a task, and uses self-checking to review and correct its work. It also provides MCP server discovery, autonomous CI/CD execution, cloud agents, and automated pull-request code reviews.