Browse 246 tools for your AI coding workflow.
A reusable GitHub Action that uses AI to review pull requests with support for self-hosted or cloud models.
MCP server to integrate CodeRabbit AI reviews into LLM workflows for GitHub pull requests.
A performance optimization system for AI coding agents, providing skills, memory, security, and research-first development.
Connect AI assistants like Claude to Penpot designs via Model Context Protocol for automated design workflows.
A desktop app for visually managing Claude Code, including settings, hooks, MCP servers, memory, and more.
Open-source AI control plane to securely connect, observe, and distribute MCPs, skills, and agents across your organization.
AI-powered GitHub issue triage dashboard with parallel agent tooling for isolated worktree development.
Zero-config AI code review, auto-fix, test generation, and HTML report CLI supporting 6 AI providers.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM, reducing tokens by 20-95% while preserving answers.
A Kubernetes-native framework for building, deploying, and managing AI agents.
Context engineering patterns and templates for AI coding agents — single-file through agent teams with Jira integration.
AI-driven semantic code search as an MCP tool using Windsurf's reverse-engineered SWE-grep protocol.
AI-powered CLI and MCP server for browsing GitHub project documentation without manual source diving.
AI-powered video editing agent for talking-head videos using Claude Code Skills.
Internal package for Remotion agent skills, enabling AI-driven video composition.
A living wiki for your codebase, maintained by AI coding agents.
AI-powered browser automation framework using CodeAgent and CDP for autonomous web interaction.
Open-source, local-first memory and context for AI agents with scoped memory, provenance, and MCP/HTTP access.
Open-source gateway that securely connects AI agents to any API, with credential injection and NAT traversal.
UIZZE stops AI coding agents from shipping generic UI with 800,000+ real screens, anti-ui-slop skills, MCP tools, and a GitHub Action.
