A developer released Rysh on GitHub under the Apache 2.0 license, an AI harness that lets graphs of Codex and Claude agents intercommunicate. It supports hierarchical agent fleets (CEO to managers to workers) and peer-to-peer Claude agent fleets that log progress to a slack-like Agent Board. It matters to practitioners building multi-agent orchestration without proprietary tooling.
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.
A developer released Workestrator, an open-source tool that dynamically assembles AI agent teams using local CLI sessions (Claude, Codex, GPT) instead of API keys. A coordinator agent selects the next agent step-by-step until task completion, with agents accessing real tools (Bash, read/write/edit) in a sandboxed workspace.
A developer released Workestrator, an open-source tool that dynamically assembles AI agent teams using local CLI sessions (Claude, Codex, GPT) instead of API keys. A coordinator agent selects the next agent step-by-step until task completion, with agents accessing real tools (Bash, read/write/edit) in a sandboxed workspace.
Runner is a local AI orchestrator that lets multiple agents work on one project from different angles and talk to each other. It targets the gap where agents built on different providers' models (e.g. Claude and Codex) can't collaborate, letting users exploit each model's strengths. Built by a developer for personal work efficiency.
Runner is a local AI orchestrator that lets multiple agents work on one project from different angles and talk to each other. It targets the gap where agents built on different providers' models (e.g. Claude and Codex) can't collaborate, letting users exploit each model's strengths. Built by a developer for personal work efficiency.
AgentHost is a persistent chat interface that lets users route tasks across Claude, Codex, and local models (e.g., Hermes) without rebuilding conversations. It solves the problem of fragmented agent workflows by providing a shared task board, live per-engine cost ledger, and autonomous run reporting. Built for developers managing multiple AI agents.
AgentHost is a persistent chat interface that lets users route tasks across Claude, Codex, and local models (e.g., Hermes) without rebuilding conversations. It solves the problem of fragmented agent workflows by providing a shared task board, live per-engine cost ledger, and autonomous run reporting. Built for developers managing multiple AI agents.
A chat-based orchestrator that coordinates multiple CLI coding agents (Claude Code, Codex, Cursor) running on local or remote machines. Users can watch, steer, and interact with all agents from a single chat interface, including via Telegram, solving the coordination pain of managing multiple coding agents manually.
A chat-based orchestrator that coordinates multiple CLI coding agents (Claude Code, Codex, Cursor) running on local or remote machines. Users can watch, steer, and interact with all agents from a single chat interface, including via Telegram, solving the coordination pain of managing multiple coding agents manually.