Research library

Documentation, tradeoffs, and practical decisions for AI builders.

RAG & Retrievalpipeshub-aiOct 176 min read

PipesHub for AI Agents: Permission-Aware Retrieval Overview

3.8Kstars

Inferenceaurelio-labsOct 154 min read

Semantic Router for LLM Apps: Embeddings and Intent Routing

3.9Kstars

ModelQwenOct 125 min read

Qwen3.8-27B Explained: Memory and Thinking Controls

6.9Mdownloads

InferenceraullenchaiOct 106 min read

Rapid-MLX for Coding Agents: Apple Silicon Inference

4Kstars

Agent Frameworkcaura-aiOct 95 min read

Caura Explained: Shared Memory for AI Agent Fleets

545stars

RAG & RetrievalThe-Vibe-CompanyOct 86 min read

Quivr V2 Explained: Durable Ingestion and Vector Search

39.6Kstars

Inferenceovg-projectOct 57 min read

kvcached GPU Memory Sharing: How Elastic KV Caching Works

1.5Kstars

InferencecarloslfuOct 45 min read

Slotstream Explained: Running MoE Models on a Mac

412stars

EvaluationArize-aiOct 35 min read

Phoenix for LLM Evaluation: Traces to Regression Cases

11.7Kstars

Developer ToolingIBMOct 25 min read

IBM ContextForge Explained: An MCP and A2A Gateway

4.6Kstars

RAG & Retrievalvespa-engineSep 306 min read

Vespa Vector Search: In-Engine Ranking vs Separate Retrieval

7.1Kstars

InferencegpustackSep 284 min read

GPUStack for Multi-GPU Inference: Server and Worker Roles

5.8Kstars