context-protocol

Multi-Model Collaboration Pipeline — orchestrate AI models as a DAG. RL routing, multi-verifier voting, agent mesh, self-improving. Works with OpenAI, Anthropic, Gemini, DeepSeek. npm install mmcp-core | pip install mmcp-core

The Audited Context Generation (ACG) Protocol prevents AI hallucinations with a dual-layer system. The UGVP layer links every fact to a precise source for verification. The RSVP layer audits the AI's logical reasoning when combining facts. This creates a fully transparent, machine-auditable trail for both source and logical integrity.

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

Local MCP server for batch inspection of Ableton Live (.als) sets: missing samples, plugin audits, and structural hashing.

Open-source agent middleware — shared memory, credential isolation, and schema learning for AI agents. What one agent learns, every agent knows.

MCP server for pūrmemo — AI conversation memory that works everywhere. Save and recall conversations across Claude Desktop, Cursor, and other MCP-compatible platforms.

Paradigm is a procedural learning and trust layer for AI agents. It learns from validated deliberative decisions, compiles stable behaviors into specialized reflexes, and keeps uncertain or unsupported states on the deliberative path.

A small, human-readable context handoff protocol for carrying working context across AI systems.

Sovereign context, memory and provenance infrastructure for AI agents. Bitemporal knowledge, evidence and decision lineage, delivered to any agent over the EPCTX/1 protocol (SDK/REST/MCP). Local-first, zero-egress, no mandatory LLM. MIT.

Reference identity provider and gateway for context requests and contributions.

User Context Protocol — the missing standard for human-to-AI memory

📝 Enhance your Markdown workflow with this MCP server, designed for structured editing and full compliance with MCP 2025 standards.

🛠️ Enhance RAG systems with ACG to reduce hallucinations in LLM responses by improving accuracy and grounding in reliable external knowledge.

Context-sync protocol for AI agents. Persistent memory, async messaging, codebase indexing. One-command setup.

🔍 Record browser sessions → Auto-discover hidden APIs → Export TypeScript SDK + OpenAPI 3.0 + MCP Server. Local-first, privacy-safe.

A lightweight Model Context Protocol (MCP) server that provides a bridge between Claude AI and a local Python environment.

An MCP server that delegates mechanical code edits to a cheap worker model, validates them through a chain of gates, and applies them atomically. Supports PHP & Python.

MCP server for LangSearch Web Search & Semantic Rerank API. Use with Claude Code, Claude Desktop, and any MCP-compatible client.

Leak-safe caching for the Model Context Protocol's SEP-2549 cache hints (ttlMs + cacheScope) — set them right server-side, and never serve a private result across users/tenants client-side.