choose when you want a minimal-RAM harness instead of herdr's full server runtime.
The most RAM efficient harness
- 18.2k
- Rust
- MIT
AI coding agent orchestration / terminal multiplexing
herdr is a background terminal multiplexer/server that provides a persistent, agent-native runtime for managing AI coding agents (Claude Code, Codex, etc.) via CLI/socket API and TUI.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose when you want a minimal-RAM harness instead of herdr's full server runtime.
The most RAM efficient harness
choose when you need unified orchestration across Codex, Claude Code, and OpenClaw with workflow automation.
Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.
choose when you want a visible multi-agent CLI workspace that mixes many different coding CLIs.
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
choose when you want TUI and web access to manage many agents from mobile.
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.
choose when you prefer a Go/AGPL orchestration workflow.
Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode)
choose when you want a Rust/AGPL mission-control tool for agents.
Mission control for your AI agents
choose when you need an agent multiplexer with map-charting features.
Agent multiplexer with map-charting capabilities
choose when you want a dev-agent multiplexer built around git worktrees.
A dev agent multiplexer for git worktrees and coding agents.
choose when you need a Windows-native terminal multiplexer for agents.
The original Windows terminal multiplexer for AI agents.
choose when you want a self-hosted control plane with web/phone dashboards for parallel sessions.
Open-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Codex & Gemini sessions from one web dashboard or your phone. Self-healing, single-file, tmux-native.
choose when you want a Python/Apache-2.0 orchestrator that coordinates agents in isolated tmux sessions.
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
choose when you want a browser-native collaborative PTY protocol for CLI agents.
Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.
choose when you need a broader agent framework with policy/sandboxing and harness swapping.
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose when you already use tmux and want a lightweight sidebar overlay.
tmux sidebar for coding agents — Amp, Claude Code, Codex, OpenCode. Per-thread markers, local HTTP API, live session state.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
choose when you need a team-facing AI coding platform with web collaboration.
AI coding platform for teams
choose when you want a node/canvas GUI instead of a terminal TUI.
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.
choose when you want a browser-based workspace with session discovery and kanban.
Open-source workspace manager for AI coding CLIs: Claude Code and ChatGPT Codex in one browser app. Discovers every session on disk, embedded terminals, phone-ready, cost tracking, kanban, docs. Windows, macOS, Linux.
choose when you want a local GUI workbench for multi-agent development.
Open-source local workbench for multi-agent software development.
These projects were analysed and named herdr among their alternatives. The relationship is not symmetric — how herdr rates them is a separate judgement, made when herdr is analysed in its own right.
calls herdr “Choose it if you need a runtime/daemon layer for agents instead of a TUI harness.”
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
calls herdr “choose when you want a headless runtime/API for coding agents with separate UI clients instead of a self-hosted canvas”
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.