AI Systems

This section collects guides on persistent knowledge and memory for AI systems — how assistants keep facts, preferences, and distilled context across sessions without stuffing every token into one prompt. Here, memory means intentional retention (user facts, summaries, plugin-backed stores), not GPU RAM or model weights.

You know the drill. You open a chat with an AI agent, explain your project, share your preferences, get some work done, and close the tab. Come back the following week and it’s like talking to a stranger — all context gone, every preference forgotten, the project re-explained from scratch.

OpenClaw did not fail as a product. It lost its fuel.

Hermes AI assistant, officially documented as Hermes Agent, is not positioned as a simple chat wrapper.

OpenClaw has two extension stories, and they are easy to mix up.

Plugins extend the runtime. Skills extend the agent’s behavior.

This article is about OpenClaw plugins — native gateway packages that add channels, model providers, tools, speech, memory, media, web search, and other runtime surfaces.

OpenClaw looks simple in demos. In production, it becomes a system.

The quiet loophole that powered a wave of agent experimentation is now closed.

Hermes Agent is a self-hosted, model-agnostic AI assistant that runs on a local machine or low-cost VPS, works through terminal and messaging interfaces, and improves over time by turning repeated tasks into reusable skills.

Most local AI setups start with a model and a runtime.

OpenClaw is a self-hosted AI assistant designed to run with local LLM runtimes like Ollama or with cloud-based models such as Claude Sonnet.

Most local AI setups start the same way: a model, a runtime, and a chat interface.

Cognee is a Python framework for building knowledge graphs from documents using LLMs. But does it work with self-hosted models?

Related guides for persistent knowledge layers — agent memory plugins, graph tooling, and stack context — live under the AI Systems Memory hub.

Choosing the Best LLM for Cognee demands balancing graph-building quality, hallucination rates, and hardware constraints. Cognee excels with larger, low-hallucination models (32B+) via Ollama but mid-size options work for lighter setups.

The Model Context Protocol (MCP) is revolutionizing how AI assistants interact with external data sources and tools. In this guide, we’ll explore how to build MCP servers in Python, with examples focused on web search and scraping capabilities.

Here we have a description of The Model Context Protocol (MCP), short notes on how to implement an MCP server in Go, including message structure, protocol specifications.