SPARSEUP Is a 149M Open Sparse Retriever Built for Inspectable RAG Search
The SPARSEUP sparse retriever maps queries and documents to weighted vocabulary terms. See its 149M design, benchmarks, failure modes and RAG test plan.
Read more
The SPARSEUP sparse retriever maps queries and documents to weighted vocabulary terms. See its 149M design, benchmarks, failure modes and RAG test plan.
Read more
The Unity agent plugin adds official Unity 6 workflow guidance to Claude Code and Codex. Learn installation, verification, license and safe testing steps.
Read more
Claude Code AGENTS.md support adds a fallback for project instructions, while version 2.1.278 moves eligible auto mode checks to an unbilled server path.
Read more
Google MilleMiglia generates privacy-preserving middle-mile logistics instances with schedules, capacity and synchronization constraints for reproducible research.
Read more
Tencent EVIE open-sources 4.5B and 8B visual document retrieval models. Learn how Prefix-MRL and HAC trade index size against retrieval quality.
Read more
Tools directory
Editorial shortlist from the tools directory, with tools worth opening twice.
From the newsroom
TensorRT Edge-LLM completed an MLPerf edge-agent run 6.4x faster than NVIDIA's llama.cpp reference. The exact cache, quantization and stream settings matter.
Open storyThree evergreen guides plus the tools directory: the fastest way into Musthave.AI.