Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost
Omnigraph
Omnigraph
Websitebench
Websitebench
Busbar
Busbar

comet-ml/opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Visit GitHub
Python
23.4k
2.1k
134 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Websitebench

Can AI agents reverse-engineer real websites?

Busbar

Control what AI can do before it acts

Momentum

How fast comet-ml/opik is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 16 – Nov 15, 2026

Stars +1,383 in 61 days

0204060
46

Forks +193 in 61 days

0510
8

Merged PRs 851 in 61 days

0204060
56

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 16Sep 24Oct 2Oct 10Oct 18Oct 26Nov 3Nov 11
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Wed, Sep 16, 2026+25+413
Thu, Sep 17, 2026+31+512
Fri, Sep 18, 2026+25+115
Sat, Sep 19, 2026+13+30
Sun, Sep 20, 2026+26+70
Mon, Sep 21, 2026+18+513
Tue, Sep 22, 2026+18+325
Wed, Sep 23, 2026+7+431
Thu, Sep 24, 2026+17+324
Fri, Sep 25, 2026+17+120
Sat, Sep 26, 2026+10+10
Sun, Sep 27, 2026+9+22
Mon, Sep 28, 2026+12+221
Tue, Sep 29, 2026+17+126
Wed, Sep 30, 2026+22+428
Thu, Oct 1, 2026+17+322
Fri, Oct 2, 2026+12+225
Sat, Oct 3, 2026+19+60
Sun, Oct 4, 2026+16+10
Mon, Oct 5, 2026+14+215
Tue, Oct 6, 2026+18+417
Wed, Oct 7, 2026+30+138
Thu, Oct 8, 2026+23+226
Fri, Oct 9, 2026+14+26
Sat, Oct 10, 2026+19+00
Sun, Oct 11, 2026+22+10
Mon, Oct 12, 2026+18+425
Tue, Oct 13, 2026+46+525
Wed, Oct 14, 2026+27+318
Thu, Oct 15, 2026+25+513
Fri, Oct 16, 2026+28+220
Sat, Oct 17, 2026+30+40
Sun, Oct 18, 2026+33+30
Mon, Oct 19, 2026+25+523
Tue, Oct 20, 2026+38+356
Wed, Oct 21, 2026+21+425
Thu, Oct 22, 2026+35+424
Fri, Oct 23, 2026+13+536
Sat, Oct 24, 2026+33+30
Sun, Oct 25, 2026+31+20
Mon, Oct 26, 2026+29+415
Tue, Oct 27, 2026+24+418
Wed, Oct 28, 2026+23+217
Thu, Oct 29, 2026+28+316
Fri, Oct 30, 2026+29+816
Sat, Oct 31, 2026+21+20
Sun, Nov 1, 2026+24+40
Mon, Nov 2, 2026+28+510
Tue, Nov 3, 2026+28+425
Wed, Nov 4, 2026+23+125
Thu, Nov 5, 2026+31+231
Fri, Nov 6, 2026+19+524
Sat, Nov 7, 2026+27+10
Sun, Nov 8, 2026+8+30
Mon, Nov 9, 2026+29+42
Tue, Nov 10, 2026+25+52
Wed, Nov 11, 2026+34+40
Thu, Nov 12, 2026+19+24
Fri, Nov 13, 2026+29+22
Sat, Nov 14, 2026+20+50
Sun, Nov 15, 2026+11+10
Total+1,383+193851
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1

    • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Nov 29, 2024 – May 13, 2025Best #2

    #1#5#10#15#20#25
    Top 10
    Oct 2024Jan 2025AprJulOctJan 2026AprJul
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about comet-ml/opik, and every badge it has earned
    1. Nov 81 post

      • 04｜Langfuse 把模型呼叫、成本、提示詞版本與評測放在同一個平台。想比較修改前後的品質與花費，可以從追蹤一條任務開始。

        Read full on X, posted by @2015ayien

        @2015ayien · x.com

    2. Nov 41 post

      • 5. Agent Scan (3.2k ★) Snyk's scanner for the MCP servers and skills already on your machine. Formerly mcp-scan. 6. ModelScan (793 ★) Protect AI's check for model files that run code when you load…

        Read full on X, posted by @FarisBrni

        @FarisBrni · x.com

    3. Nov 31 post

      • 很多 Agent demo 的问题不是不会回答，而是没人知道它为什么这次答对、下次答错，也不知道一次改 prompt 到底改变了什么。下面五个项目分别覆盖评测、追踪、可观测性和 OpenTelemetry 接入，适合把实验带进工程流程。

        Read full on X, posted by @taozi0603

        @taozi0603 · x.com

    4. Nov 21 post

      • Demo 过了、上线翻车——坏在提示词、召回还是模型？说不清。想让 AI 上线前真能验收、链路真能看清，先收藏这 6 个开源项目： 1 → Langfuse（约 3.7 万星 · 核心 MIT） 开源评测 + 可观测一体：Trace、打分、改进同一套平台 2 → Promptfoo（约 2.7 万星 · MIT） 提示词 / Agent / RAG 回归测试，还能做红队扫描

        Read full on X, posted by @perry_weijie

        @perry_weijie · x.com

    5. Oct 311 post

      • your agent says "done". the trace is the only place that shows what it actually did. open-source tools to see inside agent runs, then score them: - langfuse: traces, evals, prompt versions - phoenix:…

        Read full on X, posted by @MohakBajaj5

        @MohakBajaj5 · x.com

    6. Oct 291 post

      • 🚨 Someone built the observability layer that lets you see exactly what your AI agent is doing, in production, right now. 14,600 GitHub stars. Every LLM call, every tool invocation, every agent…

        Read full on X, posted by @RituWithAI

        @RituWithAI · x.com

    7. Oct 261 post

      • Langfuse、Helicone 都进过 YC，Comet 把监控也开源了。想少烧 token 又少翻车，先把每次 LLM 调用的成本、延迟和出错路径钉死。下面 5 个仓够起步。 1. Langfuse 开源 LLM 工程平台，追踪、评测、提示词版本都能自己部署。 2. Opik Comet 开源的观测与评测仓，盯 Agent、RAG 和生产看板。 3. Phoenix Arize…

        Read full on X, posted by @firelight279

        @firelight279 · x.com

    8. 12 days earlier
    9. Oct 142 posts

      • promptfoo — prompt testing + AI red teaming DeepEval — automated LLM and agent evaluations Inspect AI — framework for LLM evaluations Langfuse — tracing, prompt management and evals

        Read full on X, posted by @arjunkshah21

        @arjunkshah21 · x.com

      • 如果你想做一个真正能用的 AI 数据分析助手，这 6 个开源项目刚好能拼出一条完整流程： 用户提问 → 生成 SQL → 安全检查 → 执行查询 → 整理数据 → 验证答案 → 记录问题 Vanna 让用户直接用自然语言提问，再根据你的数据库结构生成 SQL。 DuckDB 直接在程序内部运行分析型 SQL，处理本地文件和数据集很方便。 SQLGlot 解析、检查和改写…

        Read full on X, posted by @bdall_1

        @bdall_1 · x.com

    10. Oct 131 post

      • AI 老忘记前面聊过的事、调用偶尔失败、出了错又查不清原因。 做 AI 应用时，这 7 个项目可以帮你补上不同的问题： 1. vLLM 在自己的服务器上跑模型，同时处理更多人的请求。 2. llama.cpp 在自己的电脑上跑模型，也可以接成备用服务。 3. RouteLLM 简单任务交给便宜模型，难题再用能力更强的，减少不必要的花费。 4. Portkey Gateway…

        Read full on X, posted by @bdall_1

        @bdall_1 · x.com

    You might also like

    Repositories close to comet-ml/opik
    FeaturedAdvertise to 180K+ monthly visitors
    Busbar

    Control what AI can do before it acts

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    Websitebench

    Can AI agents reverse-engineer real websites?

    langfuse/langfuse

    TypeScript

    🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

    37.4k4.4k

    truera/trulens

    Python

    Evaluation and Tracking for LLM Experiments and AI Agents

    3.6k411

    Arize-ai/phoenix

    Python

    AI Observability & Evaluation

    12.3k1.4k

    litefuse/litefuse

    TypeScript

    Litefuse - Agent Observability and Evaluation Platform

    11321

    langwatch/langwatch

    TypeScript

    Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.

    5k458

    lmnr-ai/lmnr

    TypeScript

    Laminar - open-source observability platform purpose-built for AI agents. YC S24.

    3.5k282

    raga-ai-hub/RagaAI-Catalyst

    Python

    Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view

    16.2k3.6k

    Helicone/helicone

    TypeScript

    🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

    6.3k707

    future-agi/future-agi

    Python

    Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

    2.3k795