The Microsoft Agent 365 SDK extends the Microsoft 365 Agents SDK with enterprise-grade capabilities for building sophisticated AI agents. This Node.js/TypeScript monorepo provides comprehensive tooling across three core areas: Observability packages are retired here. Applications migrate to @microsoft/opentelemetry; see the migration guide. Do not restore retired implementations or add the distro to otherwise unaffected SDK packages. Never publish cached/wildcard-discovered tarballs. Release only receipt-listed artifacts from the approved commit; external publishers and old release branches need their own allowlist enforcement. See…
2413mo agoReviewMountCreate a free account to mount
This workspace may contain up to 6 related repositories. Not all teams have all repos. Always be aware of which repository you're in when making changes. What is omnichannel-sdk (@microsoft/ocsdk)? This is the lowest-level HTTP client in the Omnichannel frontend stack. It provides typed wrappers around the Omnichannel livechatconnector REST APIs, handling request construction, retry logic, timeout management, authentication headers, and telemetry logging. It does not manage WebSocket connections, message rendering, or conversation adapters — those are handled by higher-level…
2432d agoReviewMountCreate a free account to mount
Handlebars template engine for composing LLM prompts, built on Pydantic. Templates may be untrusted. All context data is serialized to JSON-safe types via pydantic_core.to_jsonable_python before rendering — the template engine only sees dicts, lists, strings, numbers, bools, and None. Enforce depth limits for nesting. Tests are ported from https://github.com/handlebars-lang/handlebars.js/tree/master/spec. When adding new features, find the corresponding JS spec tests and port them. Use assert render(template, context) == expected pattern. No test classes — standalone functions only.
249mo agoReviewMountCreate a free account to mount
In this repo we develop and maintain the core methodology and skills for PhysicsIntern, a framework for using AI agents to conduct physics research. When the user asks a "how…
235mo agoReviewMountCreate a free account to mount
This repository uses Spec-Driven Development for project development. Root SPEC.md and relevant module SPEC.md files are the grounding truth for project code and project logic. They do not define the SDD workflow. This file and .github/skills/ control agent write authorization and SDD phase transitions. Project SPEC.md files must not duplicate or override those workflow rules. Ordinary discussion, explanation, review, and planning are read-only. Do not automatically load or invoke repository workflow skills. Before creating, modifying, renaming, or deleting project development…
2333d agoReviewMountCreate a free account to mount
Why message filter, not handlers: McpServerHandlers and McpServerImpl are internal in the SDK. We can't register handlers for new JSON-RPC methods from outside. Instead we use McpServerOptions.Filters.Message.IncomingFilters to intercept interceptors/list and interceptor/invoke, handle them, send JsonRpcResponse via context.Server.SendMessageAsync(), and skip calling next. See InterceptorMessageFilter.cs. Chain execution is no longer a wire method — it's SDK orchestration in Client/InterceptorChainOrchestrator.cs. Why ServerCapabilities.Extensions: The SDK's intended mechanism for protocol extensions (stable since SDK 2.x — no experimental pragma needed). We advertise InterceptorsCapability {…
233mo agoReviewMountCreate a free account to mount
AutoHelix is an agent-powered iterative optimization tool. It runs AI agents in a loop — each iteration is isolated in a git worktree, validated, and only merged when it passes. See README.md for user-facing docs. For setting up training/eval (ML benchmark) cells, see docs/ml-experiments.md. Activate the virtual environment before running any commands: If the venv doesn't exist yet: - src/autohelix/harness.py - main iteration loop (start here) - src/autohelix/cli.py - CLI commands (init, run, clear, watch, report) - src/autohelix/config.py - configuration…
224mo agoReviewMountCreate a free account to mount
See the design.md for an overview of kperf's architecture and components. See the build.md for build instructions to compile and install kperf and runkperf. See setup.md for setup instructions on how to prepare your environment for running kperf and runkperf. See the kperf.md for instructions on how to test kperf end-to-end. See the runkperf.md for instructions how to test runkperf end-to-end.
2216mo agoReviewMountCreate a free account to mount
This repo is also worked on by Kiro, which may be running at the same time. The shared rules live in the Kiro steering files below and are imported, not copied, so the two tools cannot drift. Where an import disagrees with this file, this file wins (the imports have a few stale details, listed under Corrections). @.kiro/steering.md @.kiro/steering/derive-dont-hardcode.md
2017d agoReviewMountCreate a free account to mount
When preparing a package-spec release (e.g. user mentions releasing package-spec, prepare-release-*, or finalizing spec/changelog.yml for a version), follow docs/releasing-package-spec.md. It links to the canonical workflow under .cursor/skills/package-spec-release/references/workflow.md.
207mo agoReviewMountCreate a free account to mount
The ML Workload Debugging Wiki is a structured, LLM-executable knowledge base and diagnostic framework for ML training and inference workload issues (Cloud TPU, GPU, Pathways, JAX, XLA, GKE). - .claude/:…
2020d agoReviewMountCreate a free account to mount
This is the Microsoft Copilot Studio CAT team's technical blog, hosted at https://microsoft.github.io/mcscatblog/. It uses Jekyll with the Chirpy theme for static site generation on GitHub Pages. Posts go in _posts/ with filename format: YYYY-MM-DD-post-slug.md Add new authors to _data/authors.yml with: - name: Display name - email: Optional - avatar: GitHub avatar URL (e.g., https://github.com/username.png) - url: Optional link to profile/website Store post images in assets/posts/<post-slug>/. Reference in posts as /assets/posts/<post-slug>/image.png. See Chirpy documentation for advanced formatting: https://chirpy.cotes.page/posts/write-a-new-post/ Review instructions…
208mo agoReviewMountCreate a free account to mount
liquid-spec is a test suite and CLI for testing Liquid template implementations. Its purpose is to act as a harness for the gradual construction of a full, production-ready Liquid implementation: start with trivial passthrough specs, then progressively add variables, filters, control flow, partials, compatibility quirks, and finally production/theme recordings. It captures test cases from the reference Shopify/liquid implementation and can verify that any Liquid implementation produces correct output. The standard (liquid-spec run adapter.rb; shorthand liquid-spec adapter.rb still works) run prints…
2011mo agoReviewMountCreate a free account to mount
A declarative Infrastructure-as-Code (IaC) tool for managing ClickHouse schemas in Go. The active code path is HCL-first: schemas are written in HCL, layered for multi-environment setups, resolved into a flat desired state, and round-tripped against a live cluster via the hclexp binary. Terraform/Kubernetes-style state reconciliation; no sequential migrations. Execution model: generated DDL is run on each node of a cluster individually — never with ON CLUSTER (too fragile in operation). Heavy mutations (MATERIALIZE INDEX) are generated but marked manual and…
193mo agoReviewMountCreate a free account to mount
This file provides guidance to Claude Code when working with this repository. This is a Cloudflare Worker that acts as a GitHub webhook receiver for pull requests. Its purpose is to enforce "agentic development only" by evaluating code changes and determining whether they appear to be written by AI agents rather than humans. MANDATORY after ANY code changes: - Run pnpm run typecheck to verify TypeScript compilation - Run pnpm run lint to check code style - Run pnpm run…
1816mo agoReviewMountCreate a free account to mount
A comprehensive Lua development toolkit for Claude Code, providing memory files, build system templates, and development commands. This project creates efficient Lua development-focused resources optimized for Claude Code usage, enabling developers to build production-ready Lua packages with C/C++ extensions. @.claude/memories/ldk-index.md
1815mo 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
