Workflow and task automation, orchestration.
Authorization for AI agents: verifiable, scoped, revocable capability tokens (mandates) with attenuable delegation, for MCP and A2A. The reference implementation of agent authority — zero-dependency TypeScript & Python.
Intelligent tool routing extension for pi coding agent - automatically selects the best tool stack for each task
Governance-first recursive cognition infrastructure — LuisCore Chorus Field MCP client + agent CLI (bootstrap, post, feed)
MCP server for the Open Agent Communication Protocol — join the Liteneen agent network from Claude Code, Claude Desktop, Cursor, or any MCP client
Gumloop MCP and native CLI with current REST schemas, private account profiles and confirmed operations.
Local MCP server for explicit cross-provider delegation between Codex, Claude Code, and Antigravity CLI.
n8n community node: DeepSeek Reasoner Chat Model (ZH) — DeepSeek 思考模式 Chat Model(繁中修正版)。完整保留 reasoning_content 以支援 AI Agent 多輪工具呼叫(修復 400 錯誤),並保留中文輸出。Fork of n8n-nodes-deepseek-reasoner (adcom, MIT)。
Verified n8n community node for IBM Quantum. Build OpenQASM 3 circuits, submit to Qiskit Runtime, and trigger on job completion or failure. Usable as an AI Agent tool.
n8n nodes for Qlynk URL shortener - Create, manage and track short links as workflow nodes and AI agent tools
n8n community node for Berget AI. Multi-resource action node (chat, image analysis, rerank, speech-to-text) plus Chat Model, Embeddings Model, and Reranker sub-nodes that plug into n8n's built-in AI Agent and Vector Store nodes.
Delegation journal for orchestrator/worker AI workflows: event sourcing over SQLite with an MCP interface. Zero dependencies.
Cerebrate 脑虫记忆系统 MCP Server (Node.js) — 团队长期记忆 + 业务画像 + 本地实体化，零依赖
Production-ready MCP server with complete agent integration, multi-transport support, and comprehensive development automation tools for AI-assisted workflows.
Transform any MCP server into native AI Agent tools. STDIO support with direct tool access.
AI Agent node for n8n with automatic multi-model failover and retry mechanisms
Give AI agents persistent context in n8n. Turn docs, code repositories, PDFs, specs, and other MCP servers into a live Model Context Protocol endpoint your workflows and agents read before they act, without writing code.
Pipeline gateway client for multi-agent systems — drop-in proxy, budget enforcement, dedup cache (optional x402 settlement)
GitHub Copilot nodes for n8n with AI Agent Tool support — access GPT-4, Claude, Gemini and more using your Copilot subscription
Cut AI Agent token costs by 96%. Chains multiple tool calls into a single JavaScript execution in a secure sandbox.
MCP server for CrewAI Enterprise — kick off, status, resume, and inspect crew runs from any MCP client (Claude Code, Cursor, Windsurf, 0nMCP). 50 free runs/month on the CrewAI free tier. Built by 0nORK.