Wienerdog: Shared File-Based Memory and Self-Improving Skills for Claude Code and Codex
Wienerdog is a serverless, zero-telemetry CLI tool that creates a shared Markdown memory vault and auto-improving skills across Claude Code and Codex CLI. It features a nightly dreaming process that condenses session histories into Obsidian-compatible PARA notes.
Why it matters
Switching between AI coding tools usually resets context. Wienerdog maintains persistent, file-based memory shared across tools locally on your machine without running extra daemons or sending telemetry.
TL;DR
- 01Wienerdog provides zero-telemetry, daemon-less memory vault using plain Markdown files.
- 02Memory is shared across Claude Code and Codex CLI, eliminating duplicated prompting.
- 03Nightly dreaming passes refine workflows into reusable skills and update long-term memory.
Cross-Agent Memory Vault
Wienerdog sets up a single file-based memory vault shared between Claude Code and Codex CLI. Context learned during a session in Claude Code is stored as Markdown in an Obsidian-compatible PARA structure, making it immediately available to Codex CLI without manual re-prompting.
Automated Nightly Dreaming Routine
A background OS scheduler runs a nightly dreaming pass that reviews conversation history, promotes key context into long-term memory, and converts repeated workflow patterns into structured skills. All operations execute strictly through your existing Claude or Codex CLI credentials.