<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>vtriv blog</title><description>Writing on durable AI context, authored Markdown, task records, MCP, and the external runners that use shared state across sessions.</description><link>https://vtriv.com/</link><item><title>What is an MCP memory server?</title><link>https://vtriv.com/blog/what-is-an-mcp-memory-server/</link><guid isPermaLink="true">https://vtriv.com/blog/what-is-an-mcp-memory-server/</guid><description>An MCP memory server gives AI clients durable context. Learn what MCP does, what the server stores, and how to choose a record you can correct.</description><pubDate>Sun, 27 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Basic Memory alternatives: which record do you need?</title><link>https://vtriv.com/blog/basic-memory-alternatives/</link><guid isPermaLink="true">https://vtriv.com/blog/basic-memory-alternatives/</guid><description>Considering a Basic Memory alternative? Choose local Markdown and a graph, browser-first notes, hosted team knowledge, or durable task state for AI work.</description><pubDate>Sun, 20 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Assigned tasks for AI agents: state, not a queue</title><link>https://vtriv.com/blog/assigned-tasks-ai-agents/</link><guid isPermaLink="true">https://vtriv.com/blog/assigned-tasks-ai-agents/</guid><description>Assigned tasks for AI agents need a shared, inspectable record. See what a task should contain, what a runner decides, and how handoffs stay clear.</description><pubDate>Sun, 13 Sep 2026 17:00:00 GMT</pubDate></item><item><title>What is a knowledge layer for AI?</title><link>https://vtriv.com/blog/what-is-a-knowledge-layer/</link><guid isPermaLink="true">https://vtriv.com/blog/what-is-a-knowledge-layer/</guid><description>What is a knowledge layer? It is a durable record of context and work that helps AI clients begin informed, share updates, and survive new sessions.</description><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate></item><item><title>What to store in AI memory (and what to leave out)</title><link>https://vtriv.com/blog/what-to-store-in-ai-memory/</link><guid isPermaLink="true">https://vtriv.com/blog/what-to-store-in-ai-memory/</guid><description>What to store in AI memory: save preferences, decisions, procedures, and live work. Leave chat debris behind so fresh sessions get useful context.</description><pubDate>Sun, 30 Aug 2026 00:00:00 GMT</pubDate></item><item><title>How to share context between AI tools</title><link>https://vtriv.com/blog/share-context-between-ai-tools/</link><guid isPermaLink="true">https://vtriv.com/blog/share-context-between-ai-tools/</guid><description>Share context between AI tools without rebuilding your brief in every chat. Keep one readable record for Claude, Cursor, and ChatGPT apps that support MCP.</description><pubDate>Sun, 23 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Best MCP memory servers compared</title><link>https://vtriv.com/blog/best-mcp-memory-servers/</link><guid isPermaLink="true">https://vtriv.com/blog/best-mcp-memory-servers/</guid><description>The best MCP memory server depends on the record: compare Basic Memory, Hjarni, Mem0, Notion, local options, and vtriv for context and task records.</description><pubDate>Sun, 16 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Persistent memory for long-running AI agents</title><link>https://vtriv.com/blog/persistent-memory-long-running-agents/</link><guid isPermaLink="true">https://vtriv.com/blog/persistent-memory-long-running-agents/</guid><description>Long-running AI agents use separate sessions. Persistent memory and task records give an external runner clear handoffs between them.</description><pubDate>Sun, 09 Aug 2026 17:00:00 GMT</pubDate></item><item><title>Mem0 alternatives for shared AI memory</title><link>https://vtriv.com/blog/mem0-alternatives/</link><guid isPermaLink="true">https://vtriv.com/blog/mem0-alternatives/</guid><description>Compare Mem0&apos;s hosted MCP server and OpenMemory with Zep, Letta, and vtriv for shared AI memory, readable context, and durable task records.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate></item><item><title>CLAUDE.md at scale: when one file stops working</title><link>https://vtriv.com/blog/claude-md-at-scale/</link><guid isPermaLink="true">https://vtriv.com/blog/claude-md-at-scale/</guid><description>CLAUDE.md is right for one repo. It runs out across twelve repos, two machines, and clients that never read the file. What to keep, and what to move out.</description><pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate></item><item><title>A ChatGPT memory alternative you can read</title><link>https://vtriv.com/blog/chatgpt-memory-alternative/</link><guid isPermaLink="true">https://vtriv.com/blog/chatgpt-memory-alternative/</guid><description>ChatGPT&apos;s memory lives inside one product. vtriv keeps your context in plain markdown; ChatGPT access depends on your plan and MCP permissions.</description><pubDate>Sun, 26 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to give Claude persistent memory across sessions</title><link>https://vtriv.com/blog/claude-persistent-memory/</link><guid isPermaLink="true">https://vtriv.com/blog/claude-persistent-memory/</guid><description>Claude&apos;s chat memory has plan and Cowork boundaries. vtriv keeps portable, authored Markdown context and task state for shared MCP access.</description><pubDate>Mon, 20 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The cost of starting over</title><link>https://vtriv.com/blog/starting-over/</link><guid isPermaLink="true">https://vtriv.com/blog/starting-over/</guid><description>AI chat memory helps, but it doesn&apos;t create a portable project record. Keep decisions, instructions, and work context in a durable layer.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>What&apos;s worth keeping for your AI</title><link>https://vtriv.com/blog/what-to-keep/</link><guid isPermaLink="true">https://vtriv.com/blog/what-to-keep/</guid><description>Once your assistant can read a context layer, the real question is what to store in AI memory. Four kinds that earn their place, and what to leave out.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>