AwesomeRepos
Sign in

Tags / LLM tools /

LLM observability

A tool that records LLM calls, traces, token use, and cost of LLM applications; not general APM.

Repositories

10

Net stars gained, last 7 days

+1,254

Top-level Tag

LLM tools

Net stars gained each day, last 90 days

2026-08-10: +272 net stars. Most from openobserve/openobserve, +148.2026-10-11: +423 net stars. Most from jwuthri-cloud/Tracely-ai, +314.2026-10-13: +430 net stars. Most from jwuthri-cloud/Tracely-ai, +290.2026-10-17: +350 net stars. Most from Cygnux-Labs/Tracekit, +131.2026-10-25: +616 net stars. Most from actioneer-hq/Actioneer-Pulse, +232.

Peak days

  1. 1

    Aug 10, 2026 +272 net stars (median day +121)

  2. 2

    Oct 11, 2026 +423 net stars (median day +121)

  3. 3

    Oct 13, 2026 +430 net stars (median day +121)

  4. 4

    Oct 17, 2026 +350 net stars (median day +121)

  5. 5

    Oct 25, 2026 +616 net stars (median day +121)

A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.

Largest

Most stars in total now.

  1. langfuse/langfuse37K

    readme: Instrument your app and start ingesting traces to Langfuse, thereby tracking LLM calls and other relevant logic in your app

  2. mlflow/mlflow29K

    readme: Capture complete traces of your LLM applications and agents for deep behavioral insights.

  3. comet-ml/opik23K

    readme: Track all LLM calls and traces with detailed context during development and in production (Quickstart).

  4. openobserve/openobserve23K

    readme: Monitor your GenAI and LLM applications: track cost, tokens, latency percentiles, and error rates across models, with agent graphs, session traces, and evaluation/quality scoring.

  5. raga-ai-hub/RagaAI-Catalyst16K

    readme: The module includes utilities for cost tracking, performance monitoring, and debugging agent behavior.

  6. jwuthri-cloud/Tracely-ai1.2K

    readme: Traces arrive over plain OTLP.

  7. onllm-dev/onWatch769

    readme: Track usage across Synthetic, Z.ai, Anthropic, Codex, GitHub Copilot, MiniMax, Gemini CLI (legacy), Cursor, Grok, Kimi Code, and Antigravity in one place.

  8. ThinkWatchProject/ThinkWatch-Lite584

    readme: Every request is recorded with its cost and route

  9. Cygnux-Labs/Tracekit388

    description: Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

  10. actioneer-hq/Actioneer-Pulse233

    readme: Open-source, self-hosted observability for voice AI agents.

Newest Admissions

Entered the index by the rising rule, newest first.

  1. ThinkWatchProject/ThinkWatch-Lite584

    readme: Every request is recorded with its cost and route

  2. actioneer-hq/Actioneer-Pulse233

    readme: Open-source, self-hosted observability for voice AI agents.

  3. Cygnux-Labs/Tracekit388

    description: Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

  4. jwuthri-cloud/Tracely-ai1.2K

    readme: Traces arrive over plain OTLP.

All 10 in the Repository Index

How a repository gets this Tag

An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.