Infrastructure

Deployment, observability, evaluation, and ops

All levelsBeginnerIntermediateAdvancedSort by starsSort by name

Ollama

⭐ 168.6k

The easiest way to run open-source LLMs locally.

beginner

localservingopen-source

vLLM

⭐ 76.2k

High-throughput LLM inference engine with PagedAttention for efficient GPU memory management.

advanced

servinginferencegpu

Qdrant

⭐ 30.3k

High-performance vector database written in Rust with advanced filtering capabilities.

intermediate

vector-databaserusthigh-performance

ChromaDB

⭐ 27.4k

Simple open-source vector database for AI applications.

beginner

vector-databaseembeddingsrag

LangFuse

⭐ 24.8k

Open-source LLM observability platform for tracing, evaluation, and prompt management.

intermediate

observabilitytracingevaluation

Weaviate

⭐ 16.0k

Open-source vector database with built-in vectorization and hybrid search.

intermediate

vector-databasesearchgraphql

Ragas

⭐ 13.3k

Framework for evaluating RAG pipeline quality with research-backed metrics.

intermediate

evaluationragmetrics

Text Generation Inference (TGI)

⭐ 10.8k

Hugging Face's production-ready inference server for LLMs.

advanced

servinginferencehuggingface

LangSmith

⭐ 843

LangChain's platform for debugging, testing, evaluating, and monitoring LLM applications.

intermediate

observabilitytracingevaluation

Pinecone

⭐ 429

Fully managed vector database designed for high-performance similarity search at scale.

beginner

vector-databasemanagedcloud

All Projects

• ChromaDB — Simple open-source vector database for AI applications.
• LangFuse — Open-source LLM observability platform for tracing, evaluation, and prompt management.
• LangSmith — LangChain's platform for debugging, testing, evaluating, and monitoring LLM applications.
• Ollama — The easiest way to run open-source LLMs locally.
• Pinecone — Fully managed vector database designed for high-performance similarity search at scale.
• Qdrant — High-performance vector database written in Rust with advanced filtering capabilities.
• Ragas — Framework for evaluating RAG pipeline quality with research-backed metrics.
• Text Generation Inference (TGI) — Hugging Face's production-ready inference server for LLMs.
• vLLM — High-throughput LLM inference engine with PagedAttention for efficient GPU memory management.
• Weaviate — Open-source vector database with built-in vectorization and hybrid search.