Research library

Documentation, tradeoffs, and practical decisions for AI builders.

RAG & RetrievaldoobidooSep 274 min read

mcp-memory-service Explained: Persistent AI Agent Memory

2Kstars

Evaluationcomet-mlSep 264 min read

Opik Overview: LLM Tracing, Evaluation and Guardrails

22.2Kstars

Agent FrameworkmixpeekSep 176 min read

amux Explained: Running Parallel AI Coding Agents

458stars

Agent FrameworktriggerdotdevSep 164 min read

Trigger.dev Explained: Durable AI Agent Workflows

16.3Kstars

Inferencemilvus-ioSep 155 min read

Milvus Explained: Vector Search and Storage Separation

46.1Kstars

Developer ToolingTanStackSep 145 min read

TanStack AI Explained: Streaming and Type-Safe Tool Calls

3.1Kstars

Evaluationconfident-aiSep 135 min read

DeepEval for LLM Testing: Pytest and G-Eval Explained

18.2Kstars

EvaluationmlflowSep 125 min read

MLflow for AI Agents: Tracing and Evaluation Explained

27.9Kstars

RAG & RetrievalHelixDBSep 115 min read

HelixDB Explained: Graph, Vector and Full-Text Search

5.9Kstars

InferenceSemiAnalysisAISep 103 min read

InferenceX Explained: Comparing LLM Inference Benchmarks

1.7Kstars

Agent Frameworkdeepset-aiSep 95 min read

Haystack for RAG: How Pipelines Expose Retrieval Failures

26.5Kstars

InferencekserveSep 84 min read

KServe Explained: Choosing a Kubernetes Serving Mode

5.9Kstars