gputaskman

vgpu is an open-source TypeScript library for WebGPU, developed by Vercel Labs, covering typed shaders, 3D scenes, GPU tensors, neural networks, and mathematical visualization. WGSL files can import and export declarations like TypeScript modules; reflection tracks binding names, types, and layouts so shader bindings do not require handwritten declarations. Its tiny GPU-first API uses a single context returned by init(), which is passed explicitly to rendering entry points. The same API runs in browsers, headless Node through a Dawn-backed device, and a deterministic software mock for tests and continuous integration. Explicit frame passes handle targets, effects, clears, and draws without hidden scene-graph state. The package includes a CLI for documentation, examples, and shader validation, and the video describes an MCP endpoint for agent access.

gpu-time is an experimental local neural parser for English date and time expressions. It converts text into ISO dates and time ranges, RFC 5545 recurrence rules, diagnostics, and source spans. The parser extracts token features without a word list, classifies tokens into time-related roles, detects expression boundaries, and uses TypeScript to build schedules from the predictions. It runs on CPU or WebGPU, with WebGPU processing parallel blocks and overlapping windows for long inputs; a calendar resolver applies the supplied reference instant, time zone, daylight-saving rules, and occurrence limit. The package provides parse, parseMany, and defineParser APIs, and does not send input to a server.

Gauge CLI is an open-source command-line tool for evaluating and improving how coding agents discover and use Skills, CLIs, SDKs, MCPs, APIs, and documentation. It runs real agent sessions, captures normalized transcripts and outcomes, identifies friction such as blocked interactive commands, deprecated usage, unused Skills, incorrect limitation claims, or unclear multi-command workflows, and supports comparing proposed fixes with a baseline. The local workflow runs in Docker using configured agent credentials or subscriptions. Users initialize a project, define evaluations or preference prompts with tasks and criteria, execute agents such as Claude Code, Codex, Pi, or OpenCode against working-tree inputs, and have an agent analyze the evidence into structured findings and judgments. The CLI supports rerunning evaluations against changed Skills, documentation, code, CLIs, or SDK artifacts and comparing batches; hosted Gauge adds managed execution, shared measurements, authenticated inputs, and automation. The package is distributed through npm as @withgauge/cli and requires Node.js 22.13 or later and Docker for local execution. The repository is licensed under MIT. Local measurements and analysis are stored in a private .gauge workspace backed by SQLite.

pgbot is a read-only PostgreSQL observability and health-diagnosis tool for AI agents, applications, and operators. A static binary connects to PostgreSQL, reads the database's own statistics views, and produces deterministic, findings-first health reports, including a health score, critical/warning/note findings, verified healthy subsystems, and change information from local baselines. It provides focused commands for indexes, queries, tables, and vacuum, along with versioned JSON output for agents and scripts and an MCP mode. Its optional ask and explain commands add an AI interpretation of the same findings; inspection and database queries otherwise require no model key or external service. The project is in beta and uses a read-only pg_monitor role with session-level read-only, statement, and lock timeouts as additional safeguards.

GuideLLM is an open-source platform for benchmarking and evaluating real-world LLM inference deployments. It simulates end-to-end interactions with OpenAI-compatible and vLLM-native servers, using real or synthetic text and multimodal datasets and configurable execution profiles such as synchronous, concurrent, throughput, constant-rate, Poisson, and sweep workloads. It measures SLO-oriented latency and token statistics, including time to first token, inter-token latency, and end-to-end behavior, then produces console, JSON, CSV, or HTML reports for deployment tuning, capacity planning, and regression tracking. The tool provides both a CLI and API, with multiprocessing, threading, asynchronous execution, and Hugging Face, file, synthetic, or custom data sources.