feedback-loop

Strategic Map: AI-Assisted Development with Continuous Learning

feedback-loop is a production-ready framework that transforms test failures into reusable patterns, creating a living pattern library that improves AI code generation, review, and team collaboration.

What it does

• Learns from tests: captures failures and turns them into structured metrics.
• Builds a living pattern library: good/bad examples + explanations.
• Improves AI outputs: pattern-aware code generation and review.
• Supports teams (optional): cloud sync and shared configuration.

🚀 Quick Start (30 seconds!)

Easiest option: Download and run automatically!

# 🌟 One-liner install + setup + demo + dashboard
curl -fsSL https://raw.githubusercontent.com/doronpers/feedback-loop/main/install.sh | bash

---

Already cloned? Run this single command (from the repo root):

# ✨ Auto-setup + interactive demo + dashboard - everything you need!
python3 bin/fl-start

Both options will:

• ✅ Auto-detect your environment and install everything
• 🎭 Launch an interactive demo showing patterns in action
• 📊 Open the analytics dashboard in your browser
• 🚀 Get you productive immediately

First time? Just run one command and explore!

📖 Complete Guide - For detailed instructions and advanced usage.

Installation

Automated Setup (Recommended)

The bootstrap command handles everything automatically:

python3 bin/fl-bootstrap

Manual Installation

Requirements: Python 3.13+

# Clone and install
git clone https://github.com/doronpers/feedback-loop.git
cd feedback-loop

# Install with dependencies
pip install -e .

Alternative: Using requirements.txt:

pip install -r requirements.txt

🎯 Cursor Integration (Recommended)

For Cursor IDE users: feedback-loop provides seamless AI-powered development:

# 1. Install feedback-loop (see above)
# 2. Open this repository in Cursor
# 3. Cursor automatically reads .cursorrules file
# 4. Start coding with pattern-aware AI assistance!

See Cursor Integration Guide for complete setup.

Desktop Launchers (Easy Mode!)

Mac: Double-click launch-feedback-loop.command Windows: Double-click launch-feedback-loop.bat

These launchers provide an interactive menu to run any feedback-loop tool. See DESKTOP_LAUNCHERS.md for details.

Common workflows

# Collect metrics from pytest
pytest --enable-metrics

# Analyze and update patterns
feedback-loop analyze

# Generate code with pattern awareness
feedback-loop generate "Create a safe file handler"

# Multi-perspective review with Council AI (local import or HTTP)
feedback-loop council-review --file path/to/file.py

Documentation

Start here: See documentation/INDEX.md for a complete table of contents.

Key guides:

• Getting Started - Installation and first steps
• AI Patterns Guide - Living pattern library philosophy
• Cursor Integration - IDE setup with pattern-aware AI
• Memory Integration - Semantic pattern learning
• Cloud Sync - Team collaboration features

Memory-Enhanced Patterns (Optional)

feedback-loop supports intelligent pattern memory via MemU, enabling:

✨ Semantic Search: Query patterns by concept, not just name 🧠 Self-Evolving: Patterns improve based on usage over time 🔗 Cross-Project: Share learnings across all your codebases 💡 Smart Recommendations: Get context-aware pattern suggestions

Quick Setup

# 1. Enable memory (optional)
export FEEDBACK_LOOP_MEMORY_ENABLED=true
export OPENAI_API_KEY=sk-...  # For embeddings

# 2. Sync patterns to memory
feedback-loop memory sync

# 3. Query semantically
feedback-loop memory query "How do I handle JSON serialization with NumPy?"

# 4. Get recommendations
feedback-loop memory recommend --context "Building FastAPI file upload endpoint"

Note: Memory integration is opt-in and backward compatible. All existing functionality works without MemU.

See Memory Integration Guide for detailed documentation.

Core patterns (short list)

The framework ships with 9 production-tested patterns, including:

• NumPy type conversion
• NaN/Inf validation
• Bounds checking
• Specific exception handling
• Structured logging
• Temp file hygiene
• Large file streaming
• FastAPI streaming uploads
• Metadata-driven logic

Use Quick Reference for the full catalog and examples.

Architecture (high-level)

┌─────────────────────────────┐
│            Tests            │
│          (pytest)           │
└──────────────┬──────────────┘
               │ failures
               ▼
┌─────────────────────────────┐
│     Metrics Collector       │
│   (collector/analyzer)      │
└──────────────┬──────────────┘
               ▼
┌─────────────────────────────┐
│     Pattern Library          │
│ (pattern_manager/generator)  │
└──────────────┬──────────────┘
               ▼
┌─────────────────────────────┐
│     AI + Code Review         │
│   (pattern-aware outputs)    │
└─────────────────────────────┘
               │
               ▼
┌─────────────────────────────┐
│   Apache Superset Dashboards│
│     (analytics/insights)     │
└─────────────────────────────┘

Analytics & Visualization

feedback-loop integrates with Apache Superset to provide powerful analytics dashboards:

📊 Code Quality Dashboard - Track bugs, test failures, and code review issues 📈 Pattern Analysis Dashboard - Visualize pattern frequency and effectiveness 🚀 Development Trends Dashboard - Monitor AI-assisted development metrics

See Superset Integration Guide for setup instructions.

Project status

See documentation/Status/RESULTS.md for test coverage and verification details.

Agent Instructions

CRITICAL: All AI agents MUST read AGENT_KNOWLEDGE_BASE.md before performing any tasks. It contains non-negotiable Patent, Security, and Design rules.

Additional resources:

• Agent Behavioral Standards