SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI coding

2,763 results · Page 35 of 77

Reqode

AI coding

Reqode is a product specification and implementation alignment platform for AI coding agents. It provides software developers using tools such as Codex, Cursor, and Claude Code with a connected, branch-aware product and implementation model that links requirements, APIs, data, UI, architecture, and code, giving AI agents focused context and enabling them to validate their work against this source of truth. Its core philosophy is to make the product model the memory of AI, reducing repeated prompting and handoffs, and helping teams maintain architectural consistency in complex systems while avoiding context loss and architectural drift.

Read more

Retained mode documentation

AI coding

Roo Code's Modes are specialized personas used to let the AI assistant adjust its behavior according to the current task. Each mode provides different capabilities, expertise, and access levels to help accomplish specific goals. Modes remember the last used model, automatically select it when switching, and persist across sessions. Built-in modes include Code (default), Ask, Architect, Debug, and Orchestrator (also known as Boomerang). Users can switch modes via the dropdown menu, slash commands (such as /architect), keyboard shortcuts (macOS: ⌘ + .; Windows/Linux: Ctrl + .), or by accepting suggestions. Modes support customization, allowing you to define tool access, file permissions, and behavioral instructions. Tool groups include read (file reading, listing, searching), edit (file modification and creation), command (terminal command execution), and mcp (Model Context Protocol server interaction).

Read more

reticle

AI coding

Reticle is a runtime verification tool for AI coding agents. It can drive a real running web or desktop application and read from within it information that is not visible on screen, such as clicks, network requests, application state, and the console, giving a clear conclusion of pass, fail, or cannot tell for code generated by the agent, along with file:line locations. It works with agents such as Claude Code, Cursor, Codex, Windsurf, VS Code, and Gemini CLI through MCP. Its artifacts do not enter production builds, making it suitable for development scenarios that need to verify the authenticity of AI modifications.

Read more

ReviewPhin

AI coding

ReviewPhin is a self-hosted code review automation tool for GitLab merge requests and GitHub pull requests. It is deployed as a container, runs via Docker Compose or a published Helm Chart, and the same image provides the review worker, the initial setup process, and documentation. Users can register GitLab or GitHub platform credentials and onboard projects or repositories as tenants; on the model side, they can use the built-in Copilot CLI path, or create named model configurations for OpenAI-compatible, Azure, Anthropic, and other endpoints. Storage can start with SQLite, switch to Flotiq when an admin panel is needed, or load a custom storage adapter. After a review is triggered, ReviewPhin uniformly coordinates review findings, replies, summaries, and status, helping engineers focus review time on design, risk, and intent rather than hunting for typos and obvious issues. In production, /app/data and /app/tmp must be persisted.

Read more

Revolte

AI coding

Revolte is an AI platform for software engineering that uses AI agents to automate development, testing, deployment, and production operations. It is positioned across the entire software delivery lifecycle, rather than as a coding assistant or ordinary automation tool. Engineers define requirements and approve outcomes, while AI agents execute code generation, commits, testing, deployment, and runtime operations, maintaining human-in-the-loop governance. The platform provides a CLI to keep developers in control, supports Git code merges, automatic provisioning of preview environments, structured ticket drafts, and approval gates before deployment. Features cover application development and delivery, automated quality engineering, security and performance, production reliability, data migration validation, and legacy system modernization. Observability spans runtime performance, errors, reliability, delivery speed, quality, team performance, and cloud costs. The platform emphasizes sandboxed execution environments, context management, internal developer platform integration, and audit trails, making every agent action reviewable. It is suitable for engineering teams that need to accelerate releases, reduce incidents, and have compliance and traceability requirements.

Read more

Roo-Code

AI coding

Roo Code is a programming tool that provides an AI agent development team within a code editor, supporting code generation from natural language, refactoring and debugging, writing documentation, answering questions about the codebase, and automating repetitive tasks. It offers Code, Architect, Ask, Debug, and custom modes, adaptable to different workflows, and supports MCP servers. The extension was shut down on May 15, and the official recommendation is to look for alternatives, such as the community fork ZooCode or Cline.

Read more

Rookout

AI coding

Rookout is a developer-oriented observability tool that provides real-time code-level insights from development to production environments, helping to quickly identify root causes. It supports live debugging, log analysis, and profiling, and can intelligently correlate logs, traces, metrics, and events with Dynatrace. Through the IDE or web interface, developers can instantly capture full-stack debugging data, continuously observing code, services, and runtime dependencies without manual instrumentation. It is suitable for debugging and troubleshooting cloud-native and AI-native applications, improving delivery efficiency and security.

Read more