Agent frameworks & infrastructure

Observability & evaluation

5,667 agents · most starred first

Observability & evaluation, page 38 of 57

llm-usage-tracker

Drop-in token + cost tracker for OpenAI / LiteLLM / Gemini with caching awareness

llm-warehouse

Auto-capture OpenAI and Anthropic LLM calls for warehousing and observability

llm-watch-sdk

Lightweight LLM observability SDK

llm-woodpecker

LLM Woodpecker - AI Model Debugging Tool with Chat and Raw JSON modes

llm-workers-evaluation

Evaluation framework for LLM Workers

llm-xray

A real-time visualization and training tool for GPT-2

llm4s

K9s-inspired observability control tower for LLM & MCP Servers

llmSHAP

Multi-threaded explainability for LLMs: words, sentences, documents, images, and tools.

llm_common
llm_cost_estimation

A Python library for estimating the cost of LLM API calls

llm_fingerprint

Identify LLMs by their response fingerprints

llm_math

A tool designed to evaluate the performance of large language models on mathematical tasks.

llm_mathjudger

A sitreamlined version of "LLM-Math" that judges the math solutions of LLMs.

llm_mri

Package to visualize LLM's Neural Networks activation regions

llmarena
llmasajudge

LLM Judge: simple right/wrong voting across models

llmasjudge

LLM as Judge

llmauditor

LLMAuditor is an execution-based evaluation and monitoring framework for LLM, GenAI, and agentic AI applications, providing hallucination detection, cost tracking, and governance auditing.

llmbench-cmri

A framework for load testing llmbench APIs

llmcache
llmcache-test-nb

LLMCache is an open-source caching solution designed to operate seamlessly within your cloud infrastructure.

llmcalc

Calculate LLM token costs from litellm pricing data

llmcap

Real-time LLM spend enforcement — CLI and tray app

llmcheesbench

A chess LLM benchmark scored against a local UCI master engine.

llmci

CI-native regression testing and migration for LLMs

llmcomp

Research library for black-box experiments on language models.

llmcost

llmcost

llmdebug

Structured debug snapshots for LLM-assisted debugging

llmdebugger
llmdep

Distributed LLM Evaluation Benchmark Server

llmdoctor

Find LLM cost leaks before your bill does. Static analysis for Anthropic and OpenAI client code.

llmebench

A Flexible Framework for Accelerating LLMs Benchmarking

llmesh-lleval

Reserved name — lleval: LLM eval framework for the FullSense LLM family (on-prem + cloud unified A/B, progressive size matrix, honest disclosure). Reference implementation in development.

llmeter

A lightweight, cross-platform latency and throughput profiler for LLMs

llmetrics

A metrics and evaluation library for LLMs

llmeval
llmeval-sdk

Python SDK for the evaluate LLM evaluation framework

llmevalkit

LLM evaluation, hallucination detection, AI content detection, compliance, document parsing, governance, security, observability, ground truth testing, conversation evaluation, red team testing, and anomaly detection. 78 metrics across 13 modules. Works with or without API.

llmevals

Eval

llmfaker

In-process LLM client faker that patches OpenAI, Anthropic, LiteLLM, and LangChain for fast, deterministic testing without network calls

llmfeedback

Package to integrate feedback into LLMs

llmfsd

llmfsd: LLM Fake Structured Data, faking Structured Data from any LLM

llmgatekeeper

Semantic caching library for LLM and RAG systems

llmgovernor

LLMGovernor — anomaly engine for LLM apps (core SDK with optional LiteLLM bundle)

llmgrader

Open-source LLM evaluation framework — 50+ metrics for RAG, agents, safety, async eval, regression tracking, custom benchmarks, and exportable reports

llmgym
llmhq-releaseops

Release engineering infrastructure for AI behavior - bundle, promote, evaluate, and replay agent behavior artifacts

llmjudge

A package for evaluating language model outputs.

llmlab-ai

Unified LLM testing lab - test, compare, and interact with multiple AI providers through a single UI

llmlog-engine

High-performance columnar scan engine for LLM logs stored as JSONL

llmobserve

Automatic cost tracking and observability for LLM applications

llmobserve-sdk

Automatic cost tracking and observability for LLM applications

llmock

Chaos engineering for LLM apps: mock OpenAI, Anthropic, Gemini and more, break them on demand, and get a verdict on your client's resilience.

llmonitor

Observability and monitoring for AI apps

llmoptimize

Reduce LLM costs by 90% - AI recommendations with NO API keys needed!

llmperf

A CLI tool for LLM performance testing

llmppl

A package for calculating perplexity using various language models

llmprice-kit

Fast, offline-first LLM pricing lookup with auto-sync from LiteLLM data. Get token costs, context windows, and capabilities for 2500+ models.

llmq-gate

LLM Quality Gate - A provider-agnostic evaluation framework for LLM applications

llmqa
llmreader

Intercept OpenAI inputs

llmregress

Prompt regression testing for RAG pipelines. Like git diff, but for AI.

llmreplay

Deterministic replay debugger for LLM agents

llmscorecard

Regression-based LLM benchmark ratings + publication-ready scorecards.

llmsearch

Find the Best Generation Parameters for your LLM & Dataset

llmsessioncontract

Runtime monitor for LLM agent interaction protocols based on session type theory

llmshark

Comprehensive analysis tool for LLM streaming traffic from PCAP files

llmspend

Know where your AI money goes. Track LLM API costs per feature, per model, per user.

llmstudio-tracker

LLMstudio Tracker is the module of LLMstudio that allows monitoring and logging your LLM calls. By leveraging LLMstudio Tracker, users can gain insights on model performance and streamline development workflows with actionable analytics.

llmtask

LLM Downstream Task Evaluation Tool.

llmtaskgrader

LLM任务难度评分工具,支持百炼、OpenRouter和Gemini等大模型

llmtest

llmtest package

llmtest-anthropic

Anthropic provider for llmtest

llmtest-cli

CLI for llmtest

llmtest-core

Core library for llmtest — Pydantic models, assertions, runners

llmtest-framework

pytest for LLM apps - test for grounding failures, prompt injection, safety, and regressions

llmtest-ollama

Ollama provider for llmtest

llmtest-openai

OpenAI provider for llmtest

llmtest-perf

Production-quality performance validation and regression testing for LLM inference systems

llmtest-pytest

pytest plugin for llmtest

llmtestr

A new package that helps developers integration-test AI and LLM applications by validating structured outputs. It takes a user's test scenario or prompt as input, sends it to an LLM, and uses pattern

llmtests

LLM Tests

llmthinkbench

A framework for evaluating overthinking and basic reasoning capabilities of Large Language Models

llmtokens

Count tokens and explore chat templates using HuggingFace tokenizers or OpenAI tiktoken

llmtop

LLM-powered system monitoring with real-time performance insights

llmtrace

A lightweight LLM observability and evaluation framework.

llmtrace-lite

Zero-config decorator for tracing LLM calls

llmtrace-python

Python bindings for LLMTrace — security-aware LLM observability

llmtrace-sdk

Lightweight structured tracing for LLM applications

llmtracer

LLMTracer: A tool to trace the execution of a program that uses LLMs and visualize the results.

llmtracer-sdk

Auto-track LLM cost, latency, and usage. Two lines of code, every provider.

llmtraces

End-to-end observability with built-in security guardrails.

llmtraceviewer

A tool to view LLM call traces from JSONL log files.

llmtracex

Lightweight LLM observability. SQLite-based tracing with zero infrastructure.

llmtracing

Python bindings for LLMTrace — security-aware LLM observability

llmtrack

A concise description of your package.

llmuses

Eval-Scope: Lightweight LLMs Evaluation Framework

llmvalidate

Oncoshot LLM validation framework

llmvcr

Record and replay LLM API responses for fast, free, deterministic tests

llmverify

LLM Hallucination & Drift Detection — Verify LLM outputs for accuracy, consistency, and reliability

More in Agent frameworks & infrastructure