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.

VectorSurfer

See everything.
Fix anything.

Real-time execution monitoring, distributed trace analysis, and AI-powered error healing — all in one dashboard.

Open DashboardView Docs

AI observability at a glance

Monitor executions, success rates, cache performance, and error trends across all your AI functions.

0

Total Executions

0.0%

Success Rate

0

Errors

0.0%

Cache Hit Rate

0ms

Avg Duration

Success
Error
Cache Hit
08:0009:0010:0011:0012:0013:0014:0015:00
Distributed Tracing

Trace every function call

Waterfall timeline shows exactly where time is spent. Spot bottlenecks, cache hits, and errors in distributed function chains.

0ms171ms342ms
api.generate_response
342ms
└cache.check
└llm.complete
285ms
└tokenizer.encode
└gpt4.infer
260ms
└db.log_execution
38ms
└webhook.notify
SUCCESS
CACHE HIT
ERROR
AI Healergenerate_response

Diagnosis

|

Suggested Fix

AI Healer
AI diagnoses and fixes errors
Feed error patterns to GPT-4 and get root cause analysis with suggested code fixes — automatically.
Deep analysis
Input scatter plots, cache hit gauges, and drift detection help you understand how your AI functions behave.
Input Scatter
PC1PC2
SUCCESS
CACHE HIT
ERROR
Cache Analytics
0.0%
Cache Hit67.2%
Golden28.5%
Miss32.8%
VectorWave
Powered by VectorWave
Every chart above is built from data captured by VectorWave's @vectorize decorator. One line of Python powers the entire dashboard.
Learn about VectorWave
Start monitoring
Open the dashboard and see your AI functions in real-time.
Open DashboardDocumentation