A developer released Pi Herdsman, an open-source coordination layer that keeps a lead coding agent's context small while parallel workers handle investigation and implementation in separate Pi sessions. It separates conversation state (Pi), session ownership (Herdr), and orchestration, routing questions and results back through an ownership tree instead of accumulating every tool call in the lead's context.
A developer released an update to Pi Herdsman, an open-source extension for coordinating multiple coding agents. The new setup uses a Manager → Lead → Agent hierarchy where each agent runs in its own Git worktree with an independent context, keeping implementation history out of the orchestrator. The demo and source are public on GitHub.
A developer released an update to Pi Herdsman, an open-source extension for coordinating multiple coding agents. The new setup uses a Manager → Lead → Agent hierarchy where each agent runs in its own Git worktree with an independent context, keeping implementation history out of the orchestrator. The demo and source are public on GitHub.
Dax Shepherd is a macOS tool for orchestrating multiple coding agents (Claude Code, Codex) across projects, extending the Herdr concept. Agents' sessions stay running while developers browse and navigate the server filesystem through a GUI. It targets developers running herds of coding agents who need visibility and organization.
Dax Shepherd is a macOS tool for orchestrating multiple coding agents (Claude Code, Codex) across projects, extending the Herdr concept. Agents' sessions stay running while developers browse and navigate the server filesystem through a GUI. It targets developers running herds of coding agents who need visibility and organization.
Guide walks through running parallel AI coding agents with Herdr
Guide walks through running parallel AI coding agents with Herdr
Agent Mesh is a shared memory system for coordinating multiple AI agents in coding workflows. It formalizes human decisions and stores coordination logs to reduce agent drift. Users can install it via pip and point their agents to it, which then review docs, prompt for input, and provide a dashboard UI for monitoring.
Agent Mesh is a shared memory system for coordinating multiple AI agents in coding workflows. It formalizes human decisions and stores coordination logs to reduce agent drift. Users can install it via pip and point their agents to it, which then review docs, prompt for input, and provide a dashboard UI for monitoring.
Concord is an MCP and CLI tool that lets coding agents like Claude Code, Codex, and Cursor communicate and coordinate. It allows agents to claim work, see what others are doing, and message each other live, preventing duplicated or conflicting changes. It solves the problem of parallel agents lacking task context, similar to giving a team a shared communication channel.
Concord is an MCP and CLI tool that lets coding agents like Claude Code, Codex, and Cursor communicate and coordinate. It allows agents to claim work, see what others are doing, and message each other live, preventing duplicated or conflicting changes. It solves the problem of parallel agents lacking task context, similar to giving a team a shared communication channel.