Multi-agent Orchestration 3
OpenClaw plugin for scaffolding multi-agent teams with shared context and agile workflows.
ClawRecipes is a specialized plugin for OpenClaw designed to scaffold and manage multi-agent teams using a file-first workflow. Instead of manually configuring individual agents, users use Markdown-based 'recipes' to deploy complete teams (such as development, product, or marketing teams) with pre-defined roles, shared context, and agile workflows. It features 'The Pantry' for shared file-based context, 'The Timer' for automated cron-based loops, and 'The Pass' for a structured agile process (Backlog to Done). This approach ensures that agent interactions are repeatable, reviewable in Git, and highly organized.
Open-source Python/Rust rewrite of the Claude Code AI agent framework.
Claw Code is an open-source AI coding agent framework built as a clean-room rewrite of the Claude Code architecture. Developed using Python and Rust, it provides a terminal-native environment for autonomous AI development. The framework reimplements core architectural patterns revealed in the March 2026 source leak, such as multi-agent orchestration (swarms), a plugin-based tool system with over 40 capabilities, and a provider-agnostic LLM layer. It allows developers to use various AI models (Claude, OpenAI, or local models) to read codebases, edit files, execute shell commands, and manage Git operations autonomously without relying on proprietary Anthropic code.
A multitasking macOS terminal built for AI coding agents.
crystl is a native macOS terminal built specifically for AI coding agents such as Claude Code, Codex, and Antigravity CLI. It allows developers to orchestrate multi-agent workflows, run parallel terminal sessions without resource conflicts via isolated git worktrees, and monitor agent actions through a unified frosted-glass interface. It helps developers avoid getting lost in a sea of windows and tabs by providing tools like a shared backlog, session autosave, history navigation, and an approval panel for agent actions.
