model-context-protocol

Memory that learns what works.

One TypeScript interface for 24+ LLM providers — swap providers without rewriting. MCP-native (connect any MCP server), voice (TTS/STT/realtime), RAG, memory, file processors. Production-origin: powers Tara, Yama, and Clairvoyance at Juspay.

Rails Engine with MCP compliant Spec.

MCP server that lets Claude Code and other AI agents work through large PDFs, and whole folders of them, without overflowing context: hybrid semantic + keyword search, selective page reading, tables, images, OCR, chart data, and multi-column/CJK layouts.

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.

Shared memory + orchestration for your coding agents — one MCP server, persistent vector memory, agent registry

Self improving agents through iterations

Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots

MCP OAuth Proxy incl. dynamic client registration (DCR), MCP prompt analytics and MCP firewall to build enterprise grade MCP servers.

The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.

Wan 3.0 API Python SDK and MCP server for AI video generation: text-to-video, image-to-video, multimodal references, uploads, and async job polling.

Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.

Study materials, code examples, and practice scenarios for Anthropic's Claude Certified Architect: Foundations (CCA-F) certification exam. Covers all five exam domains: agentic architecture, MCP integration, Claude Code workflows, prompt engineering, and context management.

OmniMCP uses Microsoft OmniParser and Model Context Protocol (MCP) to provide AI models with rich UI context and powerful interaction capabilities.

A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (DWS) Processor API, providing powerful PDF processing capabilities for AI assistants.

One model's answer sounds confident even when it's wrong. brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude and local Ollama models, then returns a structured synthesis — as an MCP server. Hosted mode needs no API keys.