agentproto vs Claude Squad, Conductor, Agent Farm

The honest framing first: these four tools are not really competitors. Claude Squad, Conductor and Agent Farm are interactive tools a human sits inside of to run several coding-agent sessions at once — and they are good at that. agentproto is a daemon with a programmatic lifecycle you call from code, from another agent, or from cron. The supervision primitives it adds — durable policy gates, multiplexed fan-in monitoring, nested orchestration — do not exist in the other three.

DimensionagentprotoClaude SquadConductorAgent Farm
Agents supportedClaude Code, Codex, Hermes, opencode, Mastra (Code + Agent), claude-sdk (Anthropic/Moonshot/OpenRouter), OpenClaw, browser-as-agent — uniform AIP-45 manifestsClaude Code, Codex, Gemini, Aider, other local agentsClaude Code, Codex, CursorClaude Code only (by design)
InterfaceDaemon with CLI + HTTP + MCP surfaces; scriptable from code, another agent, or cron — no terminal requiredInteractive terminal TUI (human sits in it)Mac desktop app (human sits in it)Python script / batch CLI
IsolationDaemon-tracked sessions; git-worktree isolation; sandbox provider family landing (local shipped, e2b microVM in progress)tmux session per agent + git worktree per branchIsolated workspace per agenttmux panes + lock-based file coordination
Programmatic APIYes — spawn/prompt/monitor/kill/export over MCP or HTTP; fan-in monitor; usage/cost introspectionNo — TUI appNo — desktop appPartial — configurable script, not a long-lived API
Durable supervision / policy gatesYes — shell or LLM-judge gate on turn-end, event bus, commit gated on human ack; survives client disconnectNo — human watches the TUINo — human reviews in the appPartial — workload watchdog (auto-restart), not per-turn gates
Nested orchestrationYes — scoped sub-gateways, executor/supervisor role gating, depth/children capsNoNoPartial — fans one workload across N agents
MCP surfaceYes — the daemon is an MCP server (~90 tools); agents can mount external MCP serversNoNoNo
License / platformMIT — cross-platform daemon + CLI (macOS + Linux verified)AGPL-3.0 — cross-platform TUI (requires tmux + gh)Closed source — macOS onlyMIT — cross-platform (Python 3.13+, tmux, Claude Code)

Facts sourced from each project's own page, 2026-07-07. Corrections welcome — file an issue.

When to use which

  • Claude Squad — you want a terminal cockpit for a handful of parallel sessions with git worktrees, reviewing each by hand.
  • Conductor — same workflow, polished Mac app, across Claude Code, Codex and Cursor.
  • Agent Farm — you have a lint/type-fix queue and want to throw ~50 Claude Code instances at it and get an HTML report.
  • agentproto — you want to drive coding agents from code or cron, with gates that survive a client disconnect, fan-in monitoring over N sessions, and children that can be granted their own scoped orchestration gateway.

They can compose

agentproto does not replace the cockpits. A tool like Claude Squad or Conductor could mount the agentproto MCP server and get durable policy gates and multiplexed monitoring for free, instead of hand-rolling a tmux + Redis watchdog around its panes. Interactive cockpit on top, supervised daemon underneath, any adapter either side wants to drive.