Skip to content

opik

Error & Performance Tracking

Open‑source AI observability, evaluation, and optimization platform for building, testing, and monitoring generative AI applications

Python Latest 2.0.56 · 14h ago Security brief →

Features

  • Comprehensive tracing of LLM calls, conversation logs, and agent activity
  • Advanced evaluation tools including prompt testing, LLM‑as‑a‑judge, and experiment management
  • Production‑ready monitoring dashboards with scalable online evaluation rules

Security Response History

2 CVEs
CVE Severity Disclosed Patched (this tool) vs Ecosystem Median
CVE-2026-42208 KEV critical
CVSS 9.8
2026-05-08 2026-05-08 5h
CVE-2023-4863 KEV high
CVSS 8.8
2023-09-13 2026-01-01 2y 4mo / median 2y 4mo

Recent releases

View all 152 releases →
No immediate action
2.0.55 New feature

Logs filter choice + trace metadata

No immediate action
2.0.54 Breaking risk

Dominant project prompt assignment

No immediate action
2.0.53 Bug fix

KPI error rate percent

No immediate action
2.0.52 Mixed

v2 UI, e2e tiers, dataset replay

No immediate action
2.0.51 Breaking risk

Environment in promptVersion

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.

About

Stars
19,415
Forks
1,494
Languages
Python TypeScript Shell

Install & Platforms

Install via
pip

Community & Support

Beta — feedback welcome: [email protected]