Results for “optimization”

prompt-optimizer

linshenkx/prompt-optimizer

AI prompt optimizer

optimate

nebuly-ai/optimate

A legacy collection of libraries for optimizing AI model performance

optillm

algorithmicsuperintelligence/optillm

OptiLLM is an OpenAI API-compatible optimizing inference proxy that enhances LLM accuracy and performance on reasoning tasks without needing to train or fine-tune models.

ECC

affaan-m/ECC

The agent harness performance optimization system

ray

ray-project/ray

Unified framework for scaling AI and Python applications

textgrad

zou-group/textgrad

Automatic Differentiation via Text

owl

camel-ai/owl

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

parlant

emcie-co/parlant

An interaction control harness optimized for controlled, consistent, and predictable LLM interactions for building reliable customer-facing AI agents.

agent-lightning

microsoft/agent-lightning

The absolute trainer to light up AI agents.

Megatron-LM

NVIDIA/Megatron-LM

GPU-optimized library for training transformer models at scale

RagaAI-Catalyst

raga-ai-hub/RagaAI-Catalyst

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework

coze-loop

coze-dev/coze-loop

Next-generation AI Agent Optimization Platform

GenerativeAIExamples

NVIDIA/GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

endee

endee-io/endee

Endee.io – High-performance vector database optimized for up to 1B vectors on single node.

rtk

rtk-ai/rtk

CLI proxy reducing LLM token consumption by 60-90%

headroom

headroomlabs-ai/headroom

Context compression layer for AI agents

awesome-claude-code

hesreallyhim/awesome-claude-code

Repository for resources dedicated to Claude Code, an AI coding companion by Anthropic PBC.

mlflow

mlflow/mlflow

The open source AI engineering platform for agents, LLMs, and ML models

metaflow

Netflix/metaflow

Human-centric framework to build and manage AI/ML systems

OpenRLHF

OpenRLHF/OpenRLHF

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray

intellagent

plurai-ai/intellagent

Uncover Your Agent's Blind Spots

vllm

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

ponytail

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room.

qdrant

qdrant/qdrant

High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI.

heretic

p-e-w/heretic

Fully automatic censorship removal for language models

toon

toon-format/toon

Token-Oriented Object Notation (TOON)

mlc-llm

mlc-ai/mlc-llm

Universal LLM Deployment Engine with ML Compilation

airllm

lyogavin/airllm

Repository for running large language models with reduced memory usage on limited GPU hardware.

Qwen

QwenLM/Qwen

Official repo of Qwen, a large language model by Alibaba Cloud.

opik

comet-ml/opik

Comprehensive tracing, automated evaluations, and production-ready dashboards for LLM applications.

ggml

ggml-org/ggml

Tensor library for machine learning

ragas

vibrantlabsai/ragas

Supercharge Your LLM Application Evaluations

zvec

alibaba/zvec

A lightweight, lightning-fast, in-process vector database

lancedb

lancedb/lancedb

Developer-friendly embedded retrieval library for multimodal AI

PowerInfer

Tiiny-AI/PowerInfer

High-speed Large Language Model Serving for Local Deployment

deeplake

activeloopai/deeplake

Deeplake: AI Data Runtime for Agents

BentoML

bentoml/BentoML

The easiest way to serve AI apps and models

Qwen-VL

QwenLM/Qwen-VL

The official repository of Qwen-VL (通义千问-VL) – Large Vision-Language Model by Alibaba Cloud

Awesome-LLMOps

tensorchord/Awesome-LLMOps

Curated list of LLMOps tools for developers

infinity

infiniflow/infinity

AI-native database for LLM applications with fast hybrid search capabilities.