Skip to content

dl4rce/flaiwheel

v3.9.8 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

analyze_codebase() now caches its cold‑start report for faster subsequent calls.

Full changelog

What's new

analyze_codebase() now caches the cold-start report to /data/coldstart-<project>.md inside the Docker container.

The problem before

Every time an agent called analyze_codebase() (e.g., at session start), it re-ran the full analysis (~20-30 seconds). Console output from install was lost and unrecoverable.

The fix

First call:  analyze_codebase("/src/project")  →  runs analysis (20s) → saves to /data/coldstart-project.md → returns report
Second call: analyze_codebase("/src/project")  →  reads /data/coldstart-project.md → returns report (<1s)
Force:       analyze_codebase("/src/project", force=True)  →  re-runs analysis → overwrites cache

The installer also writes the cache file during the initial cold-start run. So even the very first MCP call by any agent reads from cache instantly.

New parameter

  • force (bool, default False) — set to True to regenerate the report after significant codebase changes

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]