Awesome Agent Orchestrators 
A curated list of tools and frameworks for orchestrating agents.
Everything here decides what an agent works on, when it runs, where it runs, or what happens to its output, and takes whatever task you point it at. Single-purpose bots, and things an agent merely consumes — memory backends, MCP servers, sandbox providers, skill libraries — are out of scope.
How to choose
- Run several agents at once and review each diff. Terminal if you live in tmux, Desktop & Web if you want a GUI or phone access.
- Keep an agent working while you're away. Autonomous Loop Runners drive one goal until it verifies. Autonomous Task Runners pull work from an issue tracker, board, or schedule.
- Have agents split a large job between themselves. Multi-Agent Swarms.
- Message an agent instead of opening a tool. Personal Assistants stay running, remember across sessions, and pick up work from a chat thread — general tasks, not only code.
- Build your own orchestrator. Agent Infrastructure & Primitives — control planes, coordination protocols, harness adapters, and runtimes.
Parallel Coding Agents — Terminal (TUI/CLI)
Run and supervise several agent sessions side by side from a terminal — tmux panes, git worktrees, and TUI dashboards.
- agent-console - Rust TUI that finds Codex and Claude Code sessions from the providers' own transcripts, including ones started elsewhere, and resumes their native UI rather than replacing it. No tmux or worktrees.
- agent-deck - One TUI covering sessions across Claude Code, Codex, Gemini, and OpenCode, with live status and resume for each.
- agent-manager - tmux TUI with live status, a prompt that lands in the pane without attaching, and in-terminal diff review that sends line comments back to the agent. Claude Code, Codex, OpenCode, Grok, Gemini CLI, Pi, Hermes.
- agent-of-empires - Pairs a TUI with a matching web view, so the same sessions stay reachable from a phone. Claude Code, Codex, OpenCode, Gemini, Mistral Vibe.
- agentbox - Gives each agent its own sandboxed VM — local Docker or cloud via Hetzner, Daytona, Vercel, or E2B — with sub-second checkpoint starts.
- agterm - Native macOS terminal with named workspaces, a live dashboard, attention states, and a scriptable control API.
- ai-devkit - CLI control plane that runs agent sessions in managed tmux, sends prompts and logs to running agents from the terminal or a TUI console, and gives every agent one setup with shared local memory, verification skills, and lifecycle workflows. Claude Code, Codex, Pi, and more.
- amux - Minimal TUI for spawning parallel coding agents in git worktrees.
- Calyx - Native macOS terminal built on libghostty with an approval inbox for permission prompts, a working/blocked/idle sidebar, and in-terminal diff review.
- claude-squad - Runs each agent as a detached background session with its own worktree, so work continues after you close the pane. Claude Code, Codex, OpenCode, Amp.
- cmux - Ghostty-based macOS terminal with vertical tabs and per-agent notifications, built for keeping many concurrent sessions legible.
- Cyclops - Coordinates coding agents running in tmux through a durable mailbox with guarded terminal notifications, FIFO delivery per recipient, and fail-closed human-composer protection, with an optional workspace UI for overseeing the team. Codex CLI, Claude Code, Antigravity, Cursor Agent.
- dmux - Dev agent multiplexer pairing coding agents with git worktrees over tmux.
- herdr - Background runtime that owns your agents' terminals: sessions survive reboot and reattach from any terminal or SSH, panes are marked working/blocked/idle, and agents themselves spawn panes and prompt each other over a CLI and socket API. One Rust binary.
- openkanban - Kanban board for orchestrating coding agents, rendered entirely in the terminal.
- pappardelle - TUI that turns a description into a Linear, Jira, or beads issue, a git worktree, a PR, and a Claude Code session beside a companion pane, wired together in a 3-pane tmux layout.
- repomon - Rust TUI that supervises a fleet across many repositories at once, in durable tmux sessions you can approve from your phone.
- termany - Terminal that keeps many agent sessions in one window, tagging each pane working/done/needs-attention from the running job rather than the shell prompt, with diffs, worktrees, port handling, remote hosts, and token cost in the same place. Claude, Codex, Gemini, Grok Build, OpenClaw, Hermes, OpenCode, Cursor, Kimi, OMP.
- thurbox - TUI orchestrator with remote SSH sessions, inter-session messaging, and a native code-review view. Works with any CLI agent you define.
- tmux-ide - Turns any project into a tmux IDE from a checked-in
ide.yml, including preset agent-team layouts. - Vigil - Native macOS terminal where a manager agent runs the tree — spawning workers and sub-managers, detail flowing down, summaries rolling up — while every node stays the CLI's own TUI you can take over. Claude Code, Codex, OpenCode.
- YYLO - Command-line orchestrator for coding agents with typed task, validation, merge, and release-readiness boundaries: each task runs in a dedicated branch and worktree, and a risk-based merge queue reviews the result with receipt-backed changes. Pi and Codex subagents.
Parallel Coding Agents — Desktop & Web
The same parallel-sessions workflow as a desktop app or browser/mobile dashboard, with diff review and merge.
- agent-orchestrator - Agent IDE for fleets that plans the work, spawns the agents, then fixes CI failures and merge conflicts without being asked.
- agent-squid - Browser UI organized into named lanes (
#topic@agent), with context shared across agents and a realtime quota gauge. - AGX - Wake-work-sleep checkpointing keeps a persistent agent team on long objectives, with human gates between cycles.
- ai-maestro - Dashboard spanning multiple machines, adding memory search, code-graph queries, and agent-to-agent messaging. Claude, Aider, Cursor.
- AI4Kanban - AI project manager that turns rough ideas into actionable tasks, coordinates coding agents through planning and implementation, and builds shared project memory from decisions. Humans steer priorities and make key decisions through a desktop and web interface.
- aizen - macOS workspace that organizes worktrees, environments, and agent sessions per project.
- alas - Native macOS workspace for the whole agent loop: libghostty terminals or native chat panes across every worktree, on your Mac or over SSH, with comment-based review, in-app merge, and pickup from your phone.
- Alethe - Local-first desktop workspace where agents and shells run as real PTYs in split panes and custom grids across projects, surviving pane close and app restart. Suspend idle groups to reclaim memory and resume with scrollback intact. Claude Code, Codex, OpenCode.
- Aperant - Runs up to 12 agent terminals with a self-validating QA loop and automatic conflict resolution when merging back to main.
- ateam - macOS and iPhone app orchestrating Claude Code, OpenCode, and Codex crews, each isolated in its own git worktree.
- automaker - Describe features on a Kanban board and agents implement them in isolated worktrees, running tests and committing as they go.
- bb - Self-controlling agentic IDE that orchestrates multiple coding agents in live threads you can follow, steer, or hand off, driven from a desktop app, web app, CLI, or HTTP API.
- Berd - Block's open-source desktop app for working with AI agents: project chats with per-folder worktree behavior over the Goose backend, with agents, skills, connections, and agent sharing in one place.
- Better Agent - Local web workspace with persistent state, approvals, and restart recovery for native Claude, Codex, and Gemini sessions.
- Claude Command Center (CCC) - Local dashboard for spawning, monitoring, and resuming sessions across Claude Code, Codex, Cursor, Antigravity, and Kilo Code.
- clave - Native macOS app with split and grid layouts, session groups, SSH remote sessions, and usage analytics for Claude Code.
- [clideck](https://github.com/rusty