Agent Skills & Prompts

Persistent memory layer for AI coding agents — keeps Claude Code, Codex, Cursor, and any MCP agent in context across sessions

agentmemory is an open-source MCP server that gives AI coding agents persistent, cross-session memory. Built on hybrid vector-graph search, it achieves 95.2% recall on the LongMemEval-S benchmark while using up to 92% fewer context tokens than naive context injection. Works out of the box with Claude Code, Codex, Cursor, Windsurf, Cline, OpenCode, Kilo Code, Hermes, and any MCP client through 51 MCP tools plus 12 hooks and 4 skills.

React components for building AI chat interfaces

assistant-ui is a TypeScript/React component library for building AI chat interfaces with streaming responses, tool rendering, branching conversations, and LLM provider integrations. It supports Vercel AI SDK, LangGraph, and custom backends out of the box. Used by LangChain, Browser Use, and Stack AI. YC W25-backed with 9,000+ GitHub stars and 450K+ monthly npm downloads.

AI chatbot framework for WeChat with multi-model and plugin support

chatgpt-on-wechat is an open-source framework for deploying AI chatbots on WeChat, the dominant messaging platform in China. It supports OpenAI, Claude, Gemini, Qwen, and local models through a plugin architecture. Features group chat management, image generation, voice messages, and knowledge base integration. Over 42,700 GitHub stars reflecting massive adoption in the Chinese developer community.

Filesystem-first framework for durable AI agents

Eve is Vercel's filesystem-first TypeScript framework for building durable AI agents as ordinary project files. It combines Markdown instructions and skills, typed tools, channels, connections, subagents, schedules, sandboxes, and evals with Vercel's agent runtime so teams can ship deployable agents without hand-rolling orchestration. The current beta fits Vercel-native backend agent projects.

NVIDIA's LLM vulnerability scanner and red-teaming tool

garak is NVIDIA's open-source LLM vulnerability scanner for red-teaming AI models and applications. Probes for prompt injection, data leakage, hallucination, toxicity, encoding-based attacks, and dozens of other vulnerability categories. Runs automated attack sequences against any LLM endpoint and generates detailed vulnerability reports. Features a modular probe/detector architecture that is extensible with custom attack patterns. Named after the Star Trek character known for deception.

AI agent skill that researches topics across social platforms and web

last30days-skill is an agent skill for Claude Code and other AI coding agents that researches topics by scanning social platforms, news sites, and web sources from the past 30 days. It aggregates recent discussions, launches, and community sentiment into actionable research summaries. With 17,400 GitHub stars and MIT license, it has become one of the most popular agent skills in the emerging ACP ecosystem.

Composable agent orchestration via MCP servers

mcp-agent is an open-source framework with 8K+ GitHub stars for building AI agents that leverage MCP (Model Context Protocol) servers as composable tool providers. Agents connect to multiple MCP servers simultaneously, gaining access to diverse capabilities without custom integrations. Supports multi-agent workflows, parallel tool execution, and automatic server discovery. Designed to make MCP the universal interface between AI agents and external tools, databases, and services.

Protocol bridge converting MCP stdio transport to HTTP/SSE endpoints

mcp-proxy is a protocol bridge that converts MCP servers using stdio transport into HTTP and Server-Sent Events endpoints accessible over the network. This enables remote MCP server hosting, load balancing, and sharing servers across multiple AI clients. Supports both directions: wrapping stdio servers with HTTP and connecting to remote SSE servers through local stdio. Over 2,400 GitHub stars.

Fullstack MCP framework connecting any LLM to MCP servers

mcp-use is an open-source framework that enables any LLM to interact with MCP servers through a unified client interface. It bridges the gap between models that lack native MCP support and the growing ecosystem of MCP tools by providing automatic tool discovery, execution management, and multi-server orchestration. Supports both direct LLM connections and agent-based workflows. Over 9,000 GitHub stars.

Hosted MCP server platform

Platform for running MCP servers securely in WebAssembly sandboxes. One-click install for Claude Desktop, VS Code, and other MCP-compatible clients with no Docker required. Simplifies MCP server deployment and management by handling isolation, security, and distribution, making it easy to extend AI assistants with custom tools without infrastructure overhead.

Turn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI — at runtime, with zero codegen.

mcp2cli turns MCP servers, OpenAPI specs, and GraphQL endpoints into standard CLIs at runtime — no codegen, no schema bloat. Tools and arguments load only when requested via --list and --help flags, cutting up to 96–99% of the tokens that native MCP integrations waste on schema preloading. Works with Claude Code, Cursor, Codex, and any agent that can call shell commands, and ships with OAuth, stdio/HTTP/SSE transports, and a bake mode for reusable connections.

Community MCP server for n8n node knowledge, workflow drafting, and validation

n8n-MCP is an independent, MIT-licensed community server that gives MCP-compatible assistants structured access to n8n node documentation, properties, templates, and workflow validation helpers. It is distinct from the existing n8n product page and covers the MCP layer used from clients such as Claude, Cursor, Windsurf, and Codex.

All-in-one embeddings database with RAG, search, and agent capabilities

txtai is a self-contained AI search and RAG platform that combines vector embeddings, semantic search, LLM pipelines, and agent workflows in a single Python library. It handles embedding generation, similarity search, extractive QA, summarization, translation, and custom pipelines without external dependencies. Runs locally with over 12,400 GitHub stars and Apache 2.0 license.