Skip to content

dl4rce/flaiwheel

v3.4.2 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

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

Summary

AI summary

Claude Code support added out of the box via auto‑generated .mcp.json and CLAUDE.md.

Full changelog

What's New

Added

  • Claude Code support out of the boxinstall.sh now generates .mcp.json and CLAUDE.md in the project root automatically. After a single install run, both Cursor and Claude Code connect to the same Flaiwheel instance and follow the same behavioral workflow. One flywheel, two agents.

Fixed

  • Test: test_execute_move_stages_targeted_paths — filter compared list[:2] against a tuple ("git", "add") which always returns False in Python. Corrected to list comparison ["git", "add"].
  • Test: test_setup_keyword_path — expected "docs" for ops/install-guide.md, but the path contains the install token so the classifier correctly returns "setup". Fixed the test expectation to match actual behaviour.

Files added to project root by installer

| File | Purpose |
|------|---------|
| .mcp.json | Claude Code MCP server config (points to http://localhost:8081/sse) |
| CLAUDE.md | Claude Code instruction file — session start checklist + Flaiwheel rules |

Both files are idempotent — re-running install.sh updates the Flaiwheel section without touching anything else.

Upgrade

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

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

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 →

Beta — feedback welcome: [email protected]