Tag

Structures AI-assisted development as deterministic YAML workflows—planning, implementation, validation, review, and PR creation—so agent runs are repeatable and isolated. Mixes deterministic nodes with AI nodes and runs from CLI, Web UI, or chat integrations.

Lets agentic AI (Cursor, Claude Code) read and programmatically modify Figma designs via an MCP bridge — includes a TypeScript MCP server, a Figma plugin, and a WebSocket relay for batch text edits, instance-override propagation, and flow conversion.

Lets AI assistants query market data and execute/manage trades on MetaTrader 5 using natural language. Implements the MCP bridge with multiple transports (stdio/SSE/HTTP), a WebSocket quote streamer, and local-credentials-first design for prototyping AI-driven trading integrations.

Orchestrates sub-agents, persistent memory, and sandboxed execution to run long-horizon LLM workflows and multi-step automation. Ships extensible skills, parallel sub-agents, filesystem sandboxes, and LangChain/LangGraph integration — aimed at research and automation pipelines.

A GitHub Action that runs Claude Code inside PRs and issues to answer code questions, perform code review, and implement simple changes; auto-detects execution mode and supports Anthropic, AWS Bedrock, Google Vertex AI, and Microsoft Foundry.

Claude-Flow is an enterprise-ready multi-agent orchestration framework (by ruvnet) that turns Claude Code into a coordinated multi-agent platform. It supports 54+ specialized agents, swarm topologies, RAG and vector memory (HNSW/AgentDB), self-learning components (SONA, EWC++), multi-LLM routing, MCP server integration and production security features — intended for complex software engineering, automation and AI-driven workflows.

Provides semantic code search for AI coding agents by making an entire codebase available as context via hybrid BM25 + vector retrieval, reducing token costs. Uses incremental indexing, AST-based chunking, and Zilliz/Milvus-backed vectors for large-codebase and IDE workflows.

Provides a Python SDK for building and running Claude Agent apps — async query APIs, an interactive ClaudeSDKClient, bundled Claude Code CLI, in-process MCP tool servers, tool permission controls, hooks, and examples for agent workflows.

Browser-based desktop and mobile UI that exposes Claude Code, Cursor CLI, Codex and Gemini-CLI sessions — session management, integrated shell, file/Git explorers, and a plugin system. Use self‑hosted or via the CloudCLI Cloud managed option.

Provides a template and workflow for 'context engineering'—structuring documentation, examples, rules, and validation so AI coding assistants (especially Claude Code) can implement features reliably. Includes PRP/INITIAL templates and example-driven guidance.

An open-source GitHub Action from Anthropic that uses Claude (Claude Code) to perform semantic security reviews of code changes. It analyzes PR diffs, reports findings as PR comments, filters false positives, and is language-agnostic. Designed to integrate into CI/CD to automate security reviews.

Displays model info, token usage, git branch and other runtime metrics as a customizable Powerline-style status line for Claude Code CLI. Includes an interactive TUI, many widgets (usage, speeds, block timer), OSC8 links, and cross-platform support via npx/bunx.