Developer Tools / AI/ML Performance Testing
A 30-second WebGPU benchmark that measures a device’s memory-bandwidth ceiling for local AI and checks for a WebGPU subgroup correctness bug, with receipts, projections, and comparison data.
The page is clearly an AI-adjacent developer tool with a concrete purpose: benchmarking GPU bandwidth and estimating local-LLM throughput. The crawl shows the tool’s workflow, outputs, methodology, receipts, and example comparisons across devices and engines, which is enough evidence for a useful public listing. It also has a distinct angle beyond a generic benchmark by pairing performance measurements with a WebGPU canary for a correctness bug.
The snapshot does not show a simple quick-start, API, or install path for builders who want to integrate it elsewhere. It also doesn’t make the underlying code/repo status, release cadence, or browser/device support boundaries fully explicit beyond the visible WebGPU and Chrome-related notes.
Last evaluated 6 hours ago. Current rank #94. Down 3 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.
