Zero-overhead MCP proxy for AI coding agents — transparent wrapper gives subagents MCP access without loading schemas into the main context
A Model Context Protocol (MCP) server enabling cross-pane communication between AI CLI agents running in WezTerm terminal - build collaborative multi-agent teams with OpenCode, Gemini CLI, Claude Code
One terminal UI for the skills, subagents, MCP servers and prompts scattered across Claude Code, Codex and Gemini CLI — with a shared canonical store so editing one place updates everywhere.
A modular AI agent framework built on Vercel AI SDK. Zero-config agents with real tools, durable workflows, and HTTP interfaces.
Persistent, shared memory for AI agents: an MCP server over a plain-markdown Obsidian vault with hybrid search, a browsable knowledge graph and a self-maintaining caretaker
Build your own local LLM Wiki in 30 seconds. Multi-agent native (Claude/Codex/Cursor/VSCode/Trae), MCP server built-in, Astro static site publishing.
27-week Model Context Protocol curriculum — building AI agents with tool use, context management, and multi-agent orchestration
MCP server to orchestrate parallel AI coding agents (omp, Claude Code, any model) in Tern terminal tabs and git worktrees, from Claude Desktop or Claude Code.
Open-source voice agent platform with visible reasoning. Build a roster of AI experts with their own retrieval, guardrails, rules and RAG sources - configured from the UI, with per-step model routing
Zero-infrastructure multi-agent orchestration via tmux + filesystem. 11 CLI backends, one MCP server, zero dependencies beyond the MCP SDK.
Local Agentic AI Framework using Model Context Protocol (MCP), LangGraph, and Ollama
Daedalus is a standalone terminal-based AI coding assistant that runs on your machine. It connects to local LLM servers (LM Studio, Ollama, llama.cpp, vLLM) or remote providers (OpenAI, Groq, OpenRout
Content-addressable substrate for multi-agent memory systems. BLAKE3 CAS, Merkle DAG, Dolt SQL, tree-sitter CDOM, MCP server, and Python bindings.
MCP loader and registry written in rust
麦门圆桌(mcd-roundtable)|五个 AI 人格辩论,逼出最优麦当劳订单。基于麦当劳 MCP(mcd-mcp / Model Context Protocol)的多智能体点餐决策 Skill:菜单、券、营养、价格全部来自官方接口,金额只认 calculate-price,绝不估算。凑单最省 / 优惠券最大化 / 营养配餐 / 一键下单。Multi-agent McDonald's MCP
Run a crew of coding agents across all your machines. One manager session hands out tasks; workers running Claude Code, Codex, opencode or any agent CLI take them, each in its own clone, and push a br
The Declaration of Intelligence — signed in public, by pull request. https://thedeclaration.ai
Production-grade agentic RAG system built from scratch. LangGraph multi-agent orchestration, MCP, enterprise middleware, and RAGAS evaluation, with real production bugs diagnosed and fixed along the w
Experimental Python Trust Kernel for agent interoperability, authorization, budgets, durable governance and verifiable evidence. Bounded protocol support; production qualification pending.
A collaborative BrAPI v2.1 workspace for multi-agent research via MCP. Search studies, germplasm, genotypes, and more across Breedbase, T3, Sweetpotatobase, and any BrAPI v2-compliant server.
Local coordination for parallel coding agents: scoped claims, isolated Git worktrees, shared resources and verified integration. MCP + VS Code/Cursor extensions. No hosted service.
Powerful Python agent runtime with tools, MCP, Hooks, Skills, Rag, memory, sessions, reasoning, and streaming packets.
A股多Agent量化交易决策框架 — LangGraph 15位AI分析师辩论式分析,反思闭环+Token优化,支持DeepSeek/Qwen/GLM,附零依赖MCP server | Multi-agent A-share trading framework with reflection loop & MCP server
Your AI coding agent says the tests pass. Mythify makes it prove it: executed verification, product plans with human gates, and memory that survives the session. Any model, zero dependencies.
Zero Trust for Agentic AI. Secure Every Tool Boundary. Control which AI agents can use which tools
The self-hosted bureau for AI agents: they get briefed on missions from a durable task queue, file what they learn into a markdown+git brain, and show up for work in a 8-bit Gameboy inspired office.
One MCP stdio endpoint for a whole toolchain — GitHub, GitLab, cloud, mail, browser and research tools — with capability-gated dispatch, a machine-checked ABI, and cartridges fetched on demand from bo
Mount MCP servers as filesystems to access reads via standard file commands and perform writes through a CLI tool.
MCP server for AI memory, governance, and continuity across session-death. A self-verifying chronicle: honest on write, on read, on reach, and about itself — a failed write can't report success, a par
AI agents that turn a prompt, spreadsheets and docs into an editable deck. Interview, outline, live build, a Critic that checks every slide, and native PowerPoint, PDF and PNG export. Next.js + FastAP
Risk Intelligence MCP Server for Crypto Agents | 52 tools, 560+ signals, 72B AI model
Rust-core agentic framework with durable journal, exactly-once replay, Ed25519 A2A identity, and MCP tool server. Bindings for Go, Python, TypeScript, .NET, and Java via C ABI.
Orchestration layer for spec-driven AI development — multi-phase pipeline, isolated subagents, deterministic guardrails, persistent state based on MCP server
Local CLI and daemon for supervising collaboration between Claude Code, Codex, Grok, Gemini, and other AI coding agents over MCP. Supports work directory sandboxing preventing unexpected writes by rev
Lightweight CWE-Mapped Pre-Audit Security Scanner & Agent Skill for MCP Servers, Agent Hooks, and Firebase Rules — Scientist HM Shihabuddin Jashory (Vision Flow Group)
Sovereign AI-Native Linux OS powered by Linux 7.3.0 Rust Kernel, autonomous agent runtime (Mr. Flow), 320+ clean-room reverse-engineering tools & rolling OTA.
Annuaire complet
Orchestration et contrôle multi-agents. 804 serveurs, les plus utilisés en premier. Chacun ouvre la page de l'éditeur.