Results for “llm evals”

69 tools in this category · Updated 2 Nov 2026

“llm evals”CodingRuns on Command lineShowing 69 tools

vLLMby vLLMLLM inference and serving library.Free
LLM Compressorby IBMOpen-source Python library for quantizing and pruning LLMs to run faster in vLLMFree
DeepEvalby Confident AIYC W25Open-source LLM evaluation framework for testing AI agents and appsUnknown
Braintrustby BraintrustAgent observability and evals for engineering and product teamsFreemium
Langfuseby LangfuseYC W23Open-source platform for tracing, evaluating, and improving LLM and agent applicationsFreemium
Orq.aiby Orq.aiAI gateway and platform for routing, governing and observing LLM and agent traffic across 500+ models.Freemium
.txt APIby .txtStructured outputs API that enforces JSON Schema, regex, and grammar constraints on LLM responses.Pay as you go
Haystackby deepsetOpen-source Python framework for building RAG, agent, and multimodal LLM applicationsFreemium
Sakana AIby Sakana AISakana AI API for Fugu orchestration models and the Japanese-focused Sakana Namazu LLM.Pay as you go
Opikby CometOpen-source observability and evaluation for LLM and agent applicationsFreemium
LMCacheby LMCacheOpen-source KV-cache infrastructure for storing and reusing LLM inference cache.Free
AI SDKby VercelOpen-source TypeScript toolkit for adding LLMs and agents to apps through one provider-neutral API.Free
NVIDIA Dynamoby NVIDIAOpen-source framework for serving LLMs across multi-GPU, multi-node clustersFree
Red Hat AI Inferenceby IBMSelf-managed vLLM and llm-d inference stack for running open models on your own acceleratorsContact sales
Pydantic Logfireby PydanticFull-stack observability and evaluation for AI appsFreemium
Prime Intellectby Prime IntellectTrain, evaluate, and serve your own AI models on hosted RL infrastructureUnknown
HoneyHiveby HoneyhiveAgent observability and evaluation platform for tracing, scoring, and improving AI agents.Freemium
CodeHealth MCP Serverby CodeSceneLocal MCP server that gives AI coding agents CodeHealth feedbackPaidFree trial
NVIDIA Cosmosby NVIDIAOpen world foundation models, datasets and tools for building physical AI.Free
Bifrostby Maxim AIAI gateway and laptop-level AI traffic governance for enterprisesFreemium
Entireby EntireA Git forge for agent-human collaboration that stores intent alongside code.Pay as you go
Runware APIby RunwareModel APIs, serverless GPUs and reserved compute for AI workloadsPay as you go
Tesslby TesslAgent enablement platform for managing and optimizing agent skillsFreemium
Oumiby OumiA platform for evaluating, training, and deploying custom AI models.Freemium