AI-powered development tools with comprehensive browser monitoring and skill-based agent guidance dev3000 is a TypeScript package that gives AI assistants deep visibility into local development workflows. It captures unified logs from servers, browsers, and user interactions, making debugging and development assistance dramatically more effective. All logs use unified timestamps with source prefixes: dev3000 is specifically designed to enhance AI-assisted development:
CLI for generating and managing appxmanifest.xml, image assets, certificates, Windows SDK projections, package identity, and MSIX packaging for any app framework targeting Windows. winapp helps developers add Windows-specific features (MSIX packaging, push notifications, native APIs) to apps built with any framework—Electron, Tauri, .NET, C++, Rust, or others. It handles the complexity of Windows app identity, code signing, and SDK integration. A single shared plugin at plugins/winapp/ serves both GitHub Copilot and Claude Code. It includes:
Kingfisher is an open source secret scanner and credential-response tool. It detects exposed credentials, validates which are active, maps blast radius, supports visual triage, and revokes supported secrets. Kingfisher is written in Rust and licensed under Apache-2.0. Use TOON output for LLM and agent workflows: kingfisher scan <target> --format toon --no-update-check.
CUDA-Q streamlines hybrid application development and promotes productivity and scalability in quantum computing. It offers a hybrid programming model designed for a setting where CPUs, GPUs, and QPUs work together. CUDA-Q contains support for programming in Python and in C++.
NVIDIA cuDNN Frontend (FE): a header-only C++ library and Python package (nvidia-cudnn-frontend, import cudnn) exposing the cuDNN Graph API, plus open-source CuTeDSL kernels (SDPA/Flash Attention, MoE grouped-GEMM fusions, fused normalizations) for Hopper and Blackwell GPUs. Published documentation: https://docs.nvidia.com/deeplearning/cudnn/latest/developer/overview.html
This repository contains the source code for lage, a task runner optimized for JavaScript/TypeScript monorepos. See CONTRIBUTING.mdx in the docs/docs directory for guidelines on contributing to the project. This file provides a high-level overview. For detailed information, please refer to the documentation and the source code within each package.
OpenAPI 3 and 3.1 schema generator and validator for Hono, itty-router, and Cloudflare Workers. Chanfana automatically generates OpenAPI specs from Zod v4 schemas, validates requests, and provides auto CRUD endpoints with built-in D1 database support. This package includes source code and documentation to help AI tools understand the library:
This skill helps you create and manage Microsoft Teams bots using the Teams CLI. Covers both bot application development (creating bot code) and infrastructure management (bot registration, SSO, credentials). IMPORTANT: Use information and guidance provided within this skill and its reference guides. You may also use external public documentation only when it is explicitly linked from this skill or those guides. Do NOT perform arbitrary web searches or rely on unlisted external sources. Based on the user's request, route to…
Agents that review your code. Locally or on every PR. Warden watches over your code by running skills against your changes. Skills are prompts that define what to look for:…
CUDA-Q Academic Use curriculum.json as the source of truth for all content discovery in this repository. What curriculum.json contains How to navigate it Important modeling rules Maintenance rules Recommended agent…
Slack bot runtime for Hono and Nitro apps. Junior runs as a Hono app, receives Slack events, processes turns through queue-backed runtime work, and posts finalized replies back to Slack threads. Plugins add provider capabilities, credentials, MCP surfaces, runtime dependencies, and bundled skills.
!!! tip "Prerequisites" This guide assumes familiarity with the following: The langchain-aws package provides comprehensive integration between LangChain and AWS services. This guide demonstrates how to leverage AWS's powerful AI and ML services for building production-ready applications with features like chat models, embeddings, retrievers, and graph databases. First, let's install the required packages and set up AWS credentials: !!! tip Configure your AWS credentials using any of these methods: - AWS CLI: aws configure - Environment variables (shown above) -…
Harness-backed AI evaluation tests on top of Vitest. vitest-evals lets teams write evals as ordinary Vitest tests while still capturing the AI-specific data needed for judges, replay, terminal reporting, and GitHub Actions reporting. The public API is harness-first and judge-first: bind one harness to a suite, call the explicit run(input) fixture inside each test, assert on the typed app output, and let normalized session data flow to judges and reporters. Canonical docs: The canonical documentation page routes readers to the…
Build TensorRT bundles from Python-first checkpoints and run them through a native C++ task API. Documentation: https://nvidia.github.io/TensorRT-Model-Connect/ Repository: https://github.com/NVIDIA/TensorRT-Model-Connect
Shared tooling for coding agents dotagents manages agent skills, MCP servers, hooks, subagents, and plugins declared in agents.toml, and handles symlinks and config generation so tools like Claude Code, Cursor, Codex, GitHub Copilot CLI, Grok, VS Code, and OpenCode are configured from a single source of truth. Install: npm install -g @sentry/dotagents Run without installing: npx @sentry/dotagents <command> These unqualified commands create and use ~/.agents/agents.toml, even when run inside a repository. To manage repository-local state, make project intent explicit: The…
Every time a layer of the work became infrastructure, the role didn't shrink. The scope kept expanding. AI is the next layer in that pattern. Developers are not being automated. They are being amplified. This is an editorial essay that makes one argument: the anxiety developers feel about AI replacing them is real but misplaced. The historical pattern is consistent — memory management became a language feature, bare metal became the cloud, deployments became CI/CD. The work never disappeared. It…
Open-source tools for AWS DevOps Agent that extend its capabilities for incident response, root cause analysis, and operational troubleshooting. This repository contains skills, custom agents, and MCP servers that can be used with AWS DevOps Agent, as well as templates for writing your own. Skills follow the open Agent Skills specification; MCP servers follow the Model Context Protocol. This is the primary open-source collection of tools for AWS DevOps Agent — the AI-powered operations agent from AWS that automates incident…
An open-source (Apache-2.0), unprivileged Kubernetes controller that generates CycloneDX 1.6 ML-BOM documents for AI workloads at runtime — inference services, agent stacks, RAG pipelines, training jobs, and evaluation harnesses — with evidence locators and a confidence tier on every attribute.
Vercelllms.txt
