ai-protocol

Auto-updated index of MCP servers shipping on GitHub, refreshed every 15 minutes

An activation-based protocol for AI-to-AI knowledge transfer across architectures

SAGE, a modular AI orchestration protocol, enabling intelligent multi-model workflows with confidence-based validation.

MAPLE - Production-ready multi agent communication protocol with integrated resource management, type-safe error handling, secure link identification, and distributed state synchronization.

A peer-review protocol for AI models. Claude, Codex, Gemini and others review each other's code via CLI handoffs. Bidirectional, symmetric, opensource.

Global Notion workspace-accessible MCP server for all Notion pages within the workspace

Empirical proof of SOTA LLM (GPT-5/Gemini-Pro/Claude-Pro) context saturation in complex engineering. Contains the "Misuraca Protocol" for deterministic logical segmentation to prevent entropy drift.

A Slidev presentation and developer guide to the Model Context Protocol (MCP) by Anthropic, covering AI integration, LLM tool use, core concepts, and implementation examples for AI agents. #mcp #a

Zed Editor 逆向分析 — AI协议、登录授权、反向代理方案。Zed reverse engineering: AI protocol, auth flow, reverse proxy design.

Forge an AI that knows you, remembers, and ascends. Open source, free, yours to imprint.

AI with receipts. A local-first governed agent workbench for chat, research, memory, workflows, and tool use, with bounded authority, human approval, replayable evidence, and no self-authorization. Give it a hard task. Prove every action was allowed.

ASHE — capability-broker protocol for AI agents. Open spec by Phor for AI agent capability mediation, multi-agent orchestration, and large language model governance. Apache 2.0 with patent grant.

Enable any AI to collaborate easily. v1.0: publish a Collab Page — one web page, every AI assistant. Plus a minimal file-based transport. 🤖

A structured system prompt protocol that installs constructive adversarial reasoning into any LLM — steelmans before attacking, names logical errors by type, and earns agreement rather than dispensing it.

Agent-to-Agent coordination that doesn't waste your context window. Token-efficient protocol with progressive discovery, zero-schema invocation, gRPC transport, and task lifecycle management.

Protocol for building projects that AI models recommend to users — .ai-starter.json spec, registry, and gap scanner.

An open human–AI cognition protocol for human humour to better enable AI to understand and create humour.

AI Avatar Protocal (AIAP) -An open standard for user-owned, verifiable, portable and extensible personal AI Avatars.

书童 ShuTong — ShuTong Protocol 验证 Demo