A developer built a shared persistent Linux workspace that gives multiple AI tools (Claude, Claude Code, MCP-compatible

I wanted to give every tool I had access to LLM wiki and didn’t want to pay Mem0 or congee $100 a month for saving text files.

Every AI I use hits the same wall. The conversation ends and everything disappears. Context, files, databases, working state. Next session I’m re-explaining what we built yesterday.

I fixed this by giving every AI tool access to a persistent workspace on a Linux box. Claude, Claude Code, any MCP-compatible tool. They all share the same filesystem, the same database, the same knowledge base. One of them writes an architecture doc, the others can read it.

The whole thing cost an afternoon to build and $10/month to run.

I realized Pi has everything I needed. If you just rip the LLM out of Pi you can teleport any AI in the world into the harness. Pi, Mario Zechner’s open source harness publishes its execution layer as an npm package. File reads, writes, grep, find, directory listing. All exposed as factory functions. I imported Pi’s tools, registered them as MCP tools, and added a bash shell:

import { createReadToolDefinition, createWriteToolDefinition, createGrepToolDefinition, createFindToolDefinition, createLsToolDefinition, } from "@earendil-works/pi-coding-agent";

Five imports. One extra tool for shell access. The bridge is a single TypeScript file with five dependencies: Pi’s package, the MCP SDK, Express, an OTP library, and