AGENTS.md
This is a LiveKit Agents project. LiveKit Agents is a Python SDK for building voice AI agents. See @README.md for more details on the application itself.
Explore
10,439 skills indexed with the new KISS metadata standard.
This is a LiveKit Agents project. LiveKit Agents is a Python SDK for building voice AI agents. See @README.md for more details on the application itself.
The n8n-copilot-shim is an **orchestration agent** that manages multiple specialized subagents, each configured to handle specific domains and tasks. This document describes the agent system architecture and how to work with agents.
> **Note:** This file provides a quick reference. For comprehensive guidance, see [`.github/copilot-instructions.md`](.github/copilot-instructions.md) (single source of truth, GitHub standard filename).
This is a .NET 10 Clean Architecture template using Domain-Driven Design (DDD) tactical patterns, CQRS with MediatR, and .NET Aspire for orchestration.
generic skill
generic skill
The call intelligence system uses a multi-agent orchestration architecture where 6 specialized AI agents process call transcripts in parallel, each producing domain-specific artifacts. The orchestration layer coordinates agent execution, deduplicates outputs, and routes artifacts through approval wo
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
**Read [`.llm/context.md`](.llm/context.md)** — the canonical source of truth for all project context, development policies, testing guidelines, and coding standards.
This document provides essential information for agentic coding assistants.
- `app/` — Next.js App Router routes, layouts, and API handlers (`app/api/**`).
Ax is a TypeScript framework for building LLM-powered agents with end-to-end streaming, multi-modal DSPy capabilities, and typed signatures. It provides a standard interface across all top LLMs with features like prompt compilation, native streaming, agent orchestration, RAG, vector databases, and a
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
**Core is the only brain.** `@zodsidian/core` is surface-agnostic — returns structured data (typed objects, arrays, maps), never formatted strings. CLI wraps with Commander + chalk. Plugin wraps with Obsidian UI. Same contracts everywhere.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
This file is read by Claude Code automatically. It provides project context for working on this codebase.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
This project uses **Agentic QE v3** - a Domain-Driven Quality Engineering platform with 13 bounded contexts, ReasoningBank learning, HNSW vector search, and Agent Teams coordination (ADR-064).
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
🚨 **Core principle: Do what you can, user does what you can't.** Never punt to user if you have the access/tools to try yourself first.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
> **FOR CLAUDE: Read the SESSION STATE, DESIGN PRINCIPLES, and DUAL-USE CONTEXT sections before doing anything.**
This directory contains a standalone zsh configuration designed with a literate programming approach. The configuration is organized in a modular fashion with separate files for different aspects of the shell environment.