Research library

Documentation, tradeoffs, and practical decisions for AI builders.

InferencekserveSep 83 min read

KServe: choosing the Kubernetes serving mode your models need

5.9Kstars

InferenceopenvinotoolkitSep 73 min read

OpenVINO: choosing a deployment path for your model and hardware

10.8Kstars

RAG & RetrievalVectifyAISep 63 min read

PageIndex: when document-tree retrieval is worth the tradeoff

35.5Kstars

EvaluationpromptfooSep 53 min read

Promptfoo: building evaluation checks that catch real regressions

24.8Kstars

EvaluationlangfuseSep 23 min read

Langfuse: turning an LLM trace into a useful debugging decision

34.1Kstars

InferencemaximhqSep 13 min read

Bifrost AI Gateway: what its latency numbers actually measure

7.7Kstars

RAG & RetrievalthedotmackAug 313 min read

Claude-Mem: what persists between sessions and what it costs

92.8Kstars

InferencespiceaiAug 303 min read

Spice: choosing between federated queries and local acceleration

3.1Kstars

Agent FrameworkQ00Aug 293 min read

Ouroboros: turning an agent request into an execution contract

5.7Kstars

Inferenceai-dynamoAug 283 min read

NVIDIA Dynamo: when inference needs cluster-level coordination

7.9Kstars

Agent Frameworklangchain-aiAug 273 min read

LangGraph: deciding when an agent needs persistent state

40.6Kstars

Developer ToolingvercelAug 263 min read

Vercel AI SDK: choosing provider access and handling tool results

26.4Kstars