Skip to content

dl4rce/flaiwheel

v3.4.5 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 3mo MCP Search & Web
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Affected surfaces

auth

Summary

AI summary

Installer now prominently prompts for required claude mcp add command and CLAUDE.md adds AI‑driven connection check.

Full changelog

What's New

Improved — installer output when claude CLI is not on PATH

Instead of a quiet info line, the installer now prints a boxed ACTION REQUIRED section that is impossible to miss:

  ┌─────────────────────────────────────────────────────┐
  │  ACTION REQUIRED — Claude Code MCP registration     │
  └─────────────────────────────────────────────────────┘
  Run this command once in your terminal to connect Claude Code:

  claude mcp add --transport sse --scope project flaiwheel http://localhost:8081/sse

  Then type /mcp inside Claude Code to verify the connection.
  Cursor users: no action needed — .cursor/mcp.json handles it.

Improved — CLAUDE.md instructs the AI agent to check at session start

The CLAUDE.md template (written to every project by the installer) now includes a ⚠️ First-time setup section. When Claude Code reads it, the agent is instructed to:

  1. Type /mcp to check if Flaiwheel is connected
  2. If not connected, proactively tell the user the exact command to run
  3. Not proceed until Flaiwheel is connected

This means the AI itself becomes the reminder — no need to re-read the installer output.

Upgrade

curl -sSL https://raw.githubusercontent.com/dl4rce/flaiwheel/main/scripts/install.sh | bash
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track dl4rce/flaiwheel

Get notified when new releases ship.

Sign up free

About dl4rce/flaiwheel

Self-hosted memory and governance layer for AI coding agents. 28 MCP tools with structured knowledge capture, hybrid search (semantic + BM25 + cross-encoder reranking), behavioral documentation nudges, cold-start codebase analyzer, and git-native storage. Single Docker container, zero cloud dependencies.

All releases →

Related context

Beta — feedback welcome: [email protected]