cozymori
cozymori

Simpler, Easier, For Developers. Open-source frameworks for AI observability.

Products

  • VectorWave
  • VectorSurfer

Resources

  • Documentation
  • GitHub

© 2026 cozymori. All rights reserved.

Built with simplicity.

Overview

Getting Started

  • Introduction
  • Quick Start

VectorWave

  • VectorWave Overview
  • Installation
  • @vectorize Core
  • Semantic Caching
  • Self-Healing
  • Golden Dataset
  • Drift Detection
  • Replay Testing
  • RAG Search
  • Advanced Configuration
  • API Reference

VectorSurfer

  • VectorSurfer Overview
  • Getting Started
  • Usage Guide

Ecosystem

  • VectorCheck
  • VectorSurferSTL
  • Contributing

Ecosystem

VectorSurferSTL

Lightweight Streamlit-based dashboard for VectorWave monitoring.

What is VectorSurferSTL?

VectorSurferSTL is a lightweight, Python-only alternative to VectorSurfer. Built with Streamlit, it provides core monitoring features with minimal setup — no frontend build step required.

FeatureVectorSurferVectorSurferSTL
Best forProduction, teamsQuick setup, local dev
Setup time~5 min~1 min
AI HealerFull UIBasic UI
Multi-languageEN/JA/KOEN only
CustomizationHighModerate
SourceHosted serviceOpen source (MIT)

Quick Start

pip install vectorsurferstl
vectorsurferstl

Open http://localhost:8501 in your browser.

Prerequisites

  • Python 3.10+
  • Weaviate running with VectorWave data

If you already have Weaviate running for VectorWave, no additional database setup is needed.

Configuration

VectorSurferSTL reads the same environment variables as VectorWave. Create a .env file or set them in your shell:

# Required — Weaviate connection
WEAVIATE_HOST=localhost
WEAVIATE_PORT=8080
WEAVIATE_GRPC_PORT=50051

# Optional — for AI Healer feature
OPENAI_API_KEY=sk-...

For Weaviate Cloud (WCS) connections, add WEAVIATE_API_KEY. See the VectorWave Installation guide for the full environment variable reference.

Features

Dashboard

  • Function execution count and success rate
  • Average latency metrics
  • Cache hit rate
  • Error count and recent errors

Execution Browser

  • List all tracked function executions
  • Filter by function name, status, date range
  • View execution details: inputs, outputs, errors

Search

  • Search executions by keyword
  • Filter by function, team, status

AI Healer (Basic)

  • Select an error to diagnose
  • View AI-generated root cause analysis
  • See suggested code fixes

When to Use VectorSurferSTL

Choose VectorSurferSTL when:

  • You need a quick visual check of your VectorWave data
  • You're developing locally and want minimal setup
  • You prefer an all-Python stack

Choose VectorSurfer when:

  • You're running in production
  • Multiple team members need access
  • You need advanced features (trace waterfall, batch healing, replay testing)

Open Source

VectorSurferSTL is open source under the MIT License. Contributions are welcome.

  • GitHub: Cozymori/VectorSurferSTL — Source code, issues, and pull requests
  • PyPI: vectorsurferstl — Package page

Next Steps

  • VectorSurfer — Full-featured dashboard
  • VectorWave Overview — The core SDK
  • Quick Start — Get VectorWave running