Guidance for Claude Code (and other agent tools) working in this repository. Microsoft Entra Agent ID sample agents that demonstrate the sidecar identity pattern: the Microsoft Entra SDK for Agent ID runs as a companion container and handles token acquisition (client credentials, federated identity credential, on-behalf-of) so the agent code never touches secrets. Variants: - sidecar/dev/ — local-LLM (Ollama + LangChain) - sidecar/aws/ — AWS Bedrock (Claude + Azure→AWS OIDC) - sidecar/weather-api/ — shared downstream API - deploy/azure/container-apps/ — Azure…
127mo agoReviewMountCreate a free account to mount
Connect Four game demo showcasing PydanticAI and Pydantic Logfire capabilities. Features human vs AI and AI vs AI gameplay with multiple LLM model support. Live at https://logfire.run. IMPORTANT: ALWAYS USE…
1212mo agoReviewMountCreate a free account to mount
When modifying Vale rules in this repo, use the --no-global flag to ensure Vale uses the local styles/ directory instead of the globally installed rules: Without this flag, Vale may load rules from ~/Library/Application Support/vale/styles/Elastic/ (macOS) instead of your local changes. Vale rules use YAML. Key rule types in this repo: Releases can be created in two ways: The workflow will create the tag and release automatically. The GitHub Actions workflow creates a release with the elastic-vale.zip package.
1111mo agoReviewMountCreate a free account to mount
LangSmith Data Migration Tool - A Python CLI for migrating datasets, experiments, annotation queues, project rules, prompts, charts, and Fleet resources between LangSmith instances. Built with Click CLI, Textual TUI, and the LangSmith SDK.
1131d agoReviewMountCreate a free account to mount
"The Cheat Code" is an internal Microsoft newsletter (ABS Tech Strategy) publishing weekly reusable agentic patterns for Copilot Chat. Each issue exists in parallel formats: HTML email, PDF, Viva Amplify content, architecture diagram, and interactive portal page. The PRODUCTION_PLAYBOOK.md is the authoritative reference for all production processes — read it first.
115mo agoReviewMountCreate a free account to mount
DALI_deps provides the build scripts and source snapshots (as git submodules) for all third-party C/C++ dependencies required for a bare-metal NVIDIA DALI build. It has no DALI source code itself. Dependencies managed here are outlined in README.rst Use shallow submodule clones to avoid fetching full upstream histories: Do not run as sudo — use a user-writable prefix instead. Key env vars for build_deps.sh: - HOST_INSTALL_PREFIX / INSTALL_PREFIX — installation prefix (default /usr/local) - CC_COMP / CXX_COMP — compiler selection (default…
1157d agoReviewMountCreate a free account to mount
Start here, then read the linked docs — this file is an index, not a manual. - CONTRIBUTING.md — build/test commands, the PR workflow, and the documentation requirement (docs must be updated in the same PR; see its Documentation section for the change-→-page map, the GitHub Pages site, and the diagram workflow). - **TESTING_PLAN.md** — the tiered test strategy. - README.md — what the project is and the three ways to use it. - User docs — docs/, published as…
104mo agoReviewMountCreate a free account to mount
This file gives AI agents (Claude Code, Cursor, Codex, etc.) the project-specific context they need to use the GISTBench dataset and modify this codebase. Human-facing documentation lives in README.md and…
106mo agoReviewMountCreate a free account to mount
This repository uses AGENTS.md files for agent instructions. Before doing anything else, find and index all AGENTS.md files in this repository. Read them before working on any adjacent code or systems. All instructions in AGENTS.md files take precedence over any defaults. Follow them exactly.
1017d agoReviewMountCreate a free account to mount
This is an MCP (Model Context Protocol) server that enables AI assistants to diagnose Microsoft Purview Data Lifecycle Management (DLM) issues in Exchange Online. It provides five tools—run_powershell, get_execution_log, ask_learn, create_issue, and submit_feedback—that let an AI run read-only PowerShell commands against Exchange Online and Security & Compliance sessions, review the diagnostic trail, look up Microsoft Learn documentation, report issues with the MCP server to GitHub, and collect structured diagnostic session feedback. Built with TypeScript and the official MCP SDK (@modelcontextprotocol/sdk).…
kvpress is a library for efficiently compressing the key-value (KV) cache of pretrained transformers during long-context inference. It implements multiple training-free KV cache compression methods and provides benchmarking tools using 🤗 transformers. The repository contains: - kvpress/ - Core library implementing compression methods ("presses") - evaluation/ - Benchmarking framework and datasets - tests/ - Unit and integration tests - notebooks/ - Example notebooks and tutorials All compression methods inherit from BasePress (kvpress/presses/base_press.py): KVPressTextGenerationPipeline (kvpress/pipeline.py) is the main interface: runtime.py ([evaluation/runtime.py](evaluation/run
Guidance for agents working in this repo. (The hedgehog is watching. Be cool.) hedgehog-mode is the bouncy, physics-driven hedgehog that scurries around PostHog. It's a Pixi.js (rendering) + Matter.js (physics)…
This is a Smart Office Dashboard for Dewey, Cheatham & Howe Law Firm - a comprehensive conference room utilization and analytics platform built with Next.js 15 and Supabase. The application…
914mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
MicrosoftCLAUDE.md
