Self-hosted agents that research beyond search
Deep Research has become its own category of software, not just a model pointed at a search box. This article compares twelve self-hosted systems and the research architectures behind them.
Local Hermes memory with controlled writes.
Mnemosyne is a local-first memory provider for Hermes Agent, storing working memory, structured facts, temporal data, and episodic history in local SQLite — no hosted service, no mandatory network calls, and unusually granular write control.
When remembered conclusions become new evidence.
Persistent memory turns an agent from a re-explained tool into one that carries context forward — but it opens a failure mode stateless chat avoids: an interpretation can become memory, retrieved as fact, and justify a stronger version of itself.
A safe cutover beyond the one-line import
Migrating an AI assistant is not the same as copying an application config. The hard part is preserving identity, memory, tool behavior, scheduled work, and messaging access without two gateways acting as the same bot.
Skill, MCP server, or both?
Agent Skills and MCP servers are often presented as competing ways to extend an AI agent. That framing is wrong: a skill teaches the agent how to work, while an MCP server gives it governed access to live capabilities.
Headless Hermes server with remote desktop access
Running Hermes Agent on a headless server while connecting from a desktop client on another machine requires two server processes and a single client connection.
Long-running A2A tasks outlive chat sessions.
Most AI agent demos still behave like chat completions with extra steps: you send a prompt, wait a few seconds, and get an answer back in one response.
40% of multi-agent pilots fail. Here's how to pick the right orchestration pattern - and avoid the ones that break.
Single-agent AI systems peaked in 2025 — you gave one LLM a prompt, some tools, and a goal, and it did reasonably well on bounded tasks.
A2A is not dead. It is just not universal.
Google’s Agent2Agent protocol, usually shortened to A2A, had a strange first year.
Reliable polling patterns for AI agents.
Polling agents are one of the least glamorous parts of AI assistant architecture, but they are also one of the most useful.
MCP gives agents tools. A2A gives agents peers.
AI agent architecture is starting to split into two layers.
A2A turns agents into network peers.
The A2A Protocol, short for Agent2Agent Protocol, is an open standard for communication between independent AI agent systems.
Working, structured, and retrieval memory for assistants.
Memory turns assistants from reactive to persistent, but it is also where many systems quietly rot. Surveys argue the short-term versus long-term split is no longer enough for modern agent memory; OpenAI and LangGraph SDKs point to a simpler stack — working memory, durable state, and retrieval.
How serious assistants are actually built.
A production AI assistant is not “an LLM with a prompt”. It is a system that accepts intent, keeps state, decides when to retrieve or act, and exposes enough runtime detail to debug failures.
Stars, tokens, downloads — who actually wins?
Open-source AI agent frameworks are exploding in popularity on GitHub. Two projects at the core of the self-hosted AI systems ecosystem — OpenClaw and Hermes Agent — have pulled so far ahead that the rest of the field is fighting for a distant third place.
Talk to Hermes from your phone
You already chat to Hermes Agent from your phone with text. Now you want to talk to it directly and get spoken replies back. That is usually the right move, especially if you already use Hermes as a persistent self-hosted assistant. Typing long prompts on a small screen is slow and error-prone
