This is the simple-examples project within the Koog Framework repository. It contains executable examples demonstrating various AI agent patterns and capabilities, from basic calculator agents to advanced features like persistence, streaming, and agent-to-agent communication. Examples require API keys for LLM providers. Configure them via: Each example has a dedicated Gradle task: All available tasks follow the pattern runExample*. See build.gradle.kts for the complete list. This project uses Gradle composite build to depend on the parent Koog framework (settings.gradle.kts:). Changes in…
Personal Obsidian vault -- an external brain for work notes, decisions, performance tracking, and Claude context. This vault has obsidian-skills installed in .claude/skills/. Follow these skill conventions: The MCP server (.mcp.json → .claude/scripts/qmd-mcp.mjs), the CLI, and the SessionStart hook all read the same manifest field, so every surface scopes to the same store. On a fresh clone, run node --experimental-strip-types .scripts/qmd-bootstrap.ts once to build the index. Note: the MCP connect-time banner can read "0 documents" when the server registers before…
Pydantic Logfire is an observability platform built on OpenTelemetry. This repository contains the Python SDK for Logfire and documentation. The server application for recording and displaying data is closed source. Key aspects: - Opinionated wrapper around OpenTelemetry (traces, metrics, logs) - Extensive integrations with popular Python packages - SQL-based querying of telemetry data Pre-commit automatically runs ruff and pyright, but you can also run make format/lint/typecheck to run them explicitly, particularly to check files that haven't been changed. Docs are…
These guides must describe integrations that users can reproduce. Treat every code sample and support claim as product behavior, not illustrative pseudocode. - Use the framework's real agent abstraction and make it execute a real framework tool. A direct model call, prompt invocation, generation helper, chain, or query engine is not an agent example. - Do not add manual wrapper spans, synthetic agent spans, fake tool spans, or other telemetry solely to make the trace look complete. Show telemetry emitted…
IMPORTANT: Adhere to coding style in .embabel/coding-style.md for coding style guidance. NEVER execute git commit or push. You may use git tools for history, diffing or staging only. ALWAYS work test first. When making an enhancement or fixing a bug, write failing tests first, then implement the feature or fix the bug to make the tests pass. IMPORTANT: You should build the most relevant project (closest pom.xml) with Maven before presenting finished changes. Run the individual tests you have changed…
Macro is a document and collaboration app with a Rust backend and a web frontend. This file is the shared entry point: AGENTS.md symlinks to CLAUDE.md. Edit CLAUDE.md and preserve…
This is the Awesome Claude Agents repository - a collection of specialized AI agents that extend Claude Code's capabilities through intelligent orchestration and domain expertise. The agents work together as a development team, with each agent having specific expertise and delegation patterns. When creating or modifying agents: 1. Agents are Markdown files with YAML frontmatter 2. Most agents should omit the tools field to inherit all available tools 3. Use XML-style examples in descriptions for intelligent invocation 4. Agents return…
Unity-MCP bridges LLMs (Claude, Cursor, Copilot, etc.) with Unity Editor and Runtime via the Model Context Protocol. Sub-projects: Unity-MCP-Plugin/ (Unity Editor/Runtime plugin), cli/, Installer/, Unity-Tests/. The MCP server is NOT in this repo — the plugin consumes the shared GameDev-MCP-Server (binary gamedev-mcp-server, release assets gamedev-mcp-server-<rid>.zip, Docker aigamedeveloper/mcp-server) — one engine-agnostic server shared by Unity-MCP, Godot-MCP, and Unreal-MCP. The plugin downloads the release pinned by the ServerVersion constant in Unity-MCP-Plugin/Packages/com.ivanmurzak.unity.mcp/Editor/Scripts/McpServerManager.cs (decoupled from the plugin Version). Server version pin: bumping the consumed…
Unity-MCP Plugin — Unity Editor/Runtime side of the MCP bridge. Attribute-based framework that registers and executes MCP tools, prompts, and resources. Includes a self-hosted MCP server manager and auto-configuration for AI clients.
just-bash is a TypeScript implementation of a bash interpreter with an in-memory virtual filesystem. Designed for AI agents needing a secure, sandboxed bash environment. No WASM dependencies allowed. The just-bash…
The harness-specific tools system-prompt.md relies on, for when you are running inside Claude Code. The main prompt only names capabilities ("ask the user", "preview", "screenshot", "debug"); this doc gives the exact Claude Code tool, signature, and call pattern. Generic tools (Bash, Read/Write/Edit/Glob, gh) are the same everywhere and aren't covered here. The upstream prompt references Claude.ai web tools that do not exist in Claude Code. Substitute as follows everywhere — prose and code alike: Video export has no web-tool equivalent…
AGENTS.md is the single source of truth for this repository. Read it before any non-trivial change; it is imported below so it is always in context. This file intentionally holds no guidance of its own — do not add rules here, add them to AGENTS.md. The frontend has its own website/AGENTS.md.
website/AGENTS.md is the single source of truth for frontend work in website/. Read it before any UI change; it is imported below so it is always in context. This file intentionally holds no guidance of its own — do not add rules here, add them to website/AGENTS.md. The backend has its own AGENTS.md at the repo root.
kubefwd is a popular command-line utility for bulk Kubernetes port forwarding, featured in "essential k8s developer tools" lists. It forwards multiple services from one or more namespaces, adding corresponding entries to /etc/hosts for local development. Key Differentiator from kubectl port-forward: Each service gets its own unique loopback IP address (127.x.x.x), allowing multiple services to use the same port simultaneously (e.g., multiple databases on port 3306, or multiple web services on port 80). This mirrors how services work in the cluster,…
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.
JetBrainsCLAUDE.md
