Research library

Documentation, tradeoffs, and practical decisions for AI builders.

InferenceopenvinotoolkitSep 74 min read

OpenVINO Deployment Overview: Conversion and Device Support

10.8Kstars

RAG & RetrievalVectifyAISep 64 min read

PageIndex for RAG: Document-Tree Retrieval Overview

35.5Kstars

EvaluationpromptfooSep 54 min read

Promptfoo for LLM Evaluation: Regression Checks Explained

24.8Kstars

EvaluationlangfuseSep 24 min read

Langfuse for LLM Debugging: Traces, Prompts and Evals

34.1Kstars

InferencemaximhqSep 14 min read

Bifrost AI Gateway Explained: Latency and Fallbacks

7.7Kstars

RAG & RetrievalthedotmackAug 314 min read

Claude-Mem Explained: Persistent Memory for Claude Code

92.8Kstars

InferencespiceaiAug 304 min read

Spice Explained: Federated Queries vs Local Acceleration

3.1Kstars

Agent FrameworkQ00Aug 294 min read

Ouroboros Explained: From Agent Request to Specification

5.7Kstars

Inferenceai-dynamoAug 284 min read

NVIDIA Dynamo Overview: Multi-GPU LLM Serving

7.9Kstars

Agent Frameworklangchain-aiAug 274 min read

LangGraph Persistent State: When Agents Need Checkpoints

40.6Kstars

Developer ToolingvercelAug 264 min read

Vercel AI SDK Explained: Providers, Streaming and Tools

26.4Kstars

Agent FrameworkvercelAug 254 min read

Vercel Workflow for Durable TypeScript Jobs: An Overview

2.3Kstars