Opik Files

Debug, evaluate, and monitor your LLMapps, RAG systems, and agentic AI

This is an exact mirror of the Opik project, hosted at https://github.com/comet-ml/opik. SourceForge is not affiliated with Opik.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
2.2.18 source code.tar.gz	2026-08-04	335.5 MB	0
2.2.18 source code.zip	2026-08-04	342.6 MB	3
README.md	2026-08-04	1.4 kB	0
Totals: 3 Items		678.1 MB	3

What's Changed

[OPIK-7728] [QA] fix: scope studio prompt editors to their message role by @AndreiCautisanu in https://github.com/comet-ml/opik/pull/7723
[OPIK-7521] [SDK] fix: trace optimizer LLM spend so the backend can price and attribute it by @awkoy in https://github.com/comet-ml/opik/pull/7674
[OPIK-7705] [BE] perf: bound the existing-item lookup in insertItemsIntoVersion by @JetoPistola in https://github.com/comet-ml/opik/pull/7699
[OPIK-7400] [BE] Benchmark the spans_local_v2 per-column codecs and apply the real-data refinements by @thiagohora in https://github.com/comet-ml/opik/pull/7691
[OPIK-7455] [BE] feat: retarget trace mutation DAOs to traces_local behind a wrap toggle by @andrescrz in https://github.com/comet-ml/opik/pull/7713
[OPIK-7711] [QA][FE] test: add E2E coverage for multi-trace deletion by @AndreiCautisanu in https://github.com/comet-ml/opik/pull/7707
[OPIK-7105] [BE] [FE] refactor: remove Opik V1 workspace-version and project-migration machinery by @andrescrz in https://github.com/comet-ml/opik/pull/7724
[OPIK-7609] [SDK] feat: add num_threads to Dataset.insert() for parallel upload by @JetoPistola in https://github.com/comet-ml/opik/pull/7671
[OPIK-7331] [BE][FE] perf: speed up projects-list stats (invert span-score lookup + 30-day window) by @miguelgrc in https://github.com/comet-ml/opik/pull/7684

Full Changelog: https://github.com/comet-ml/opik/compare/2.2.17...2.2.18

Source: README.md, updated 2026-08-04

Other Useful Business Software

99.99% Uptime for MySQL and PostgreSQL Databases Icon

99.99% Uptime for MySQL and PostgreSQL Databases

Sub-second maintenance. 2x read/write performance. Built-in vector search for AI apps.

Cloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.

Try Free

$300 Free Credits to Build on Google Cloud Icon

$300 Free Credits to Build on Google Cloud

New to Google Cloud? Get $300 in credits to explore Compute Engine, BigQuery, Cloud Run, Gemini Enterprise Agent Platform, and more.

Start your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.

Claim $300 Free

$300 Free Credits to Build on Google Cloud

New to Google Cloud? Get $300 in credits to explore Compute Engine, BigQuery, Cloud Run, Gemini Enterprise Agent Platform, and more.

Start your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.

Claim $300 Free

Recommended Projects

DeepEval
DeepEval is a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning, LangChain, or LlamaIndex, DeepEval has you covered. With it, you can easily determine the optimal hyperparameters to improve your RAG pipeline, prevent prompt drifting, or even transition from OpenAI to hosting your own Llama2 with confidence.
LLM Action
Technical principles related to large models
kolosal
Open Source and Lightweight Local LLM Platform
Lunary
The production toolkit for LLMs. Observability, prompt management
promptfoo
Evaluate and compare LLM outputs, catch regressions, improve prompts