Self-Hosted
-
Open-Source MCP Gateway for LLM Connections
Read Full Article: Open-Source MCP Gateway for LLM ConnectionsPlexMCP is an open-source MCP gateway that simplifies the management of multiple MCP server connections by consolidating them into a single endpoint. It supports various communication protocols like HTTP, SSE, WebSocket, and STDIO, and is compatible with any local LLM that supports MCP, such as those using ollama or llama.cpp. PlexMCP offers a dashboard for managing connections and monitoring usage, and can be self-hosted using Docker or accessed through a hosted version at plexmcp.com. This matters because it streamlines the integration process for developers working with multiple language models, saving time and resources.
-
WebSearch AI: Local Models Access the Web
Read Full Article: WebSearch AI: Local Models Access the Web
WebSearch AI is a newly updated, fully self-hosted chat application that enables local models to access real-time web search results. Designed to accommodate users with limited hardware capabilities, it provides an easy entry point for non-technical users while offering advanced users an alternative to popular platforms like Grok, Claude, and ChatGPT. The application is open-source and free, utilizing Llama.cpp binaries for the backend and PySide6 Qt for the frontend, with a remarkably low runtime memory usage of approximately 500 MB. Although the user interface is still being refined, this development represents a significant improvement in making AI accessible to a broader audience. This matters because it democratizes access to AI technology by reducing hardware and technical barriers.
-
Cogitator: Open-Source AI Runtime in TypeScript
Read Full Article: Cogitator: Open-Source AI Runtime in TypeScript
Cogitator is an open-source, self-hosted runtime designed to orchestrate AI agents and LLM swarms, built with TypeScript to offer type safety and seamless web integration. It provides a universal LLM interface that supports multiple AI platforms like Ollama, vLLM, OpenAI, Anthropic, and Google through a single API. The system is equipped with a DAG-based workflow engine, multi-agent swarm strategies, and sandboxed execution using Docker/WASM for secure operations. With a focus on production readiness, it utilizes Redis and Postgres for memory management and offers full observability features like OpenTelemetry and cost tracking. This matters because it aims to provide a more stable and efficient alternative to existing AI infrastructures with significantly fewer dependencies.