GraphScope Blog

Andrej Karpathy’s LLM Wiki reshapes the knowledge-base paradigm: no chunking, no vector index. The LLM itself handles create / read / update / delete on the knowledge, and the wiki evolves dynamically with use.

146 open PRs. 83 of them clustered into conflict groups. Some modifying the same function across 5 different branches. This isn’t a hypothetical — it’s the real state of the qwen-code repository on a random Tuesday in May 2026. And qwen-code isn’t even the extreme case — projects like OpenClaw and Hermes routinely carry thousands of open PRs.

When you pick an open source project on GitHub, what do you look at first? For most people, the answer is Star count. But can Star count really tell you whether a project is healthy and worth relying on long-term?

We indexed 1,906 source files, 9,848 functions, and 22,678 call edges using CodeGraph — a code intelligence skill powered by NeuG, an open-source embedded graph database — to reveal what lies beneath the surface of one of the most ambitious AI coding tools ever built.

We are pleased to announce the open source release of NeuG (pronounced “new-gee”), a lightweight, high-performance embedded graph database designed for local analytics and real-time transaction processing.

The Linked Data Benchmark Council (LDBC) has released the latest results of its SNB Interactive Benchmark (via Declarative Queries), where GraphScope Flex achieved a historic breakthrough with a throughput exceeding 80,000 QPS (queries per second) – nearly twice the performance of the previous record holder!