# Agent tools: multiplexers, desktop environments, sandboxes, gateways and more

URL: https://developertoolkit.ai/en/ecosystem/agent-tools/
Description: Third-party tools around Claude Code, Codex and Cursor: six shelves, the built-ins to try first, license traps, and a checklist for adding a tool.

Agent tools are third-party software around Claude Code, Codex and Cursor: terminal multiplexers, desktop agent environments, remote clients, sandboxes, review bots and model gateways. The agents now ship worktrees, agent views and remote control themselves, so a third-party tool earns its place only with cross-agent state, a review GUI, or isolation beyond files.

Use this page when someone proposes a fourth app to manage your three agents: check the built-ins, place the tool on a shelf, and decide within a week.

## What the agents already do before you install anything

Checked against Claude Code 2.1.283 and codex-cli 0.157.1 on 2026-09-26. On 2026-10-12 the commands and flags named in the Claude Code and Codex columns for worktrees, `--tmux`, `claude agents`, `codex agents`, remote control and diff review were still present in Claude Code 2.1.296 and codex-cli 0.162.1. The Cursor column comes from Cursor's documentation and changelog as read on 2026-10-12.

| Job | Claude Code | Codex | Cursor |
| --- | --- | --- | --- |
| A git worktree per task | `claude --worktree NAME`; `.worktreeinclude` copies gitignored files | `codex --worktree` or `/worktree` | Worktrees (Agents Window, IDE and CLI) |
| A terminal session per worktree | `--tmux` (`--tmux=classic` for plain tmux) | — | — |
| One screen for all agents | `claude agents` (agent view, research preview) | `codex agents` | Agents Window |
| Agents cooperating | Agent teams (experimental, off by default) | Subagents | Subagents |
| Steering from another device | `claude --remote-control` | `codex remote-control` (experimental) | Cursor iOS app (remote control for local agents, changelog 2026-10-06) |
| Diff review | `/code-review` | `codex review` | Bugbot (on pull requests) |

Cursor: the Agents Window and remote control for local agents are documented as of 2026-10-12. The dash in the terminal-session row means this page found no documented equivalent.

## Try the native worktree workflow first

Start two agents on two tasks, each in its own checkout.

**Claude Code**

    In two terminals, from the repository root:

    ```bash
    claude --worktree feature-auth --tmux
    claude --worktree fix-invoice-rounding --tmux
    ```

    Each session gets its own worktree and branch; `--tmux` opens it in its own tmux session (iTerm2 native panes when available), so it survives a closed terminal. List `.env` in `.worktreeinclude` to copy it into new worktrees; watch both with `claude agents`.

**Codex**

    In each terminal, from the repository root:

    ```bash
    codex --worktree
    ```

    Codex starts the session in a new managed worktree; `/worktree` does the same inside a session. `codex agents` lists the sessions on the local app-server daemon.

**Cursor**

    `.cursor/worktrees.json` customises worktree setup in the Agents Window, the IDE and the CLI (Cursor docs, checked 2026-10-12). The control that starts an agent in a worktree moves between releases, so follow [Cursor's worktrees documentation](https://cursor.com/docs/configuration/worktrees).

Then prove the isolation:

```bash
git worktree list
```

Expect the main checkout plus one line per agent, each on its own branch. A single line means an agent is editing your main checkout: stop it.

**Copy-paste prompt: a worktree task that proves itself**

```text
You are working in a dedicated git worktree on one task: fix the rounding
error in invoice totals (round half-even to 2 decimals).
1. Before changing code, write a failing test that reproduces the bug and
   show me the failing output.
2. Make the smallest fix that turns it green. Touch only src/billing/ and
   tests/billing/.
3. Run the full test suite, the type checker and the linter. Paste the
   summary line of each.
4. If a server or test needs a port, do not assume the default; tell me
   which port you used.
5. End with: branch name, files changed, commands run, and anything you
   could not verify.
```

The agent hands back evidence, not a claim: a red-then-green test, three gate results and a scope you confirm with `git diff --stat main`.

## The six shelves of agent tools

| Shelf | What it adds over the built-ins | Go deeper |
| --- | --- | --- |
| **Agent-aware multiplexers** | Working, blocked or idle state across *different* agents; sessions that survive SSH drops; worktree managers such as Worktrunk | [herdr](/en/ecosystem/agent-tools/herdr-agent-multiplexer/), [tmux for agent fleets](/en/ecosystem/agent-tools/tmux-for-agent-fleets/) |
| **Desktop agent environments** | A GUI diff and review board over a worktree per task | [desktop environments compared](/en/ecosystem/agent-tools/agent-shells/) |
| **Remote and mobile clients** | Approvals and steering from a phone, for mixed agents | [agents from your phone](/en/ecosystem/agent-tools/remote-mobile/) |
| **Isolation runtimes** | A container, VM or cloud sandbox per agent: ports, databases and credentials isolated, not only files | [sandboxes compared](/en/ecosystem/agent-tools/sandboxes/) |
| **Review bots** | A second model on every pull request | [AI code review bots](/en/ecosystem/observability/ai-code-review-bots/) |
| **Gateways and local models** | Provider switching or local inference; you lose Remote Control and `/voice` | [gateways and local models](/en/ecosystem/agent-tools/gateways-local-models/) |

## Which agent tools are worth knowing in September 2026?

One or two picks per shelf; the shelf pages hold the rest and the install lines. Stars are GitHub stars read on 2026-09-26: attention, not use.

| Tool | Shelf | Pick it when | License | ★ |
| --- | --- | --- | --- | --- |
| herdr | Multiplexer | Mixed agents in one terminal | Apache-2.0 | 40.8k |
| tmux | Multiplexer | No new dependency allowed | ISC | 49.5k |
| Orca | Desktop | Free, cross-platform, best-of-N | MIT | 78.4k |
| Conductor | Desktop | Mac team, review board (secondary sources) | closed | — |
| Happy | Remote | End-to-end-encrypted phone client | MIT | 23.9k |
| container-use | Isolation | Container plus branch per agent over MCP (experimental) | Apache-2.0 | 4.0k |
| CC Switch | Gateway | Switch providers across agents (site: ccswitch.io) | MIT | 136.9k |
| Ollama | Gateway | Code must stay on the machine | MIT | 181.7k |

Clear the license with legal before a tool becomes a team standard: AGPL-3.0 (Claude Squad, Coder) and GPL-3.0 (cmux) bite when you embed, host or distribute; ELv2 (Superset) forbids hosting as a service; closed-source Conductor needs a SaaS review.

## Which agent tools should you not recommend?

As of 2026-09-26, keep these out of a team standard: Vibe Kanban (sunsetting), Uzi (dormant since 2025-06-04), Crystal (continues as Nimbalyst), Roo Code and `coder/agentapi` (archived), Continue (read-only), and subscription-resale proxies such as CLIProxyAPI and sub2api (terms compliance unverified).

## When should you add a third-party agent tool?

A tech lead runs this before a tool enters the team setup.

1. **Name the gap in one sentence**, such as "we cannot see which agent waits for approval." If a built-in covers it, configure that instead.

2. **Place it on a shelf.** A multiplexer does not isolate ports; a sandbox has no review board.

3. **Install from the vendor's README only.** On npm, `herdr` is a placeholder, `claude-squad`, `conductor` and `oh-my-claudecode` belong to unrelated authors, and `coderabbit` is a security holding package. Compare `npm view TOOL repository` with the README.

4. **Check health and license**: last release, archive flag, `LICENSE`. Pin and hash Python gateways: LiteLLM 1.82.7 and 1.82.8 on PyPI were malicious (2026-03-24).

5. **List what you lose.** A gateway (`ANTHROPIC_BASE_URL` other than `api.anthropic.com`) or an API key removes Claude Code's Remote Control, so phone steering needs a third-party client; `/voice` needs a claude.ai login.

6. **Pilot for one week**: two people, one backlog slice, unchanged CI gates. Record agent wait time, first-push CI result and review time per task.

7. **Keep it only if the gap closes and the gates stay green.** Native worktrees stay the fallback: this category churns fast.

**Copy-paste prompt: vet a third-party agent tool (replace OWNER/REPO)**

```text
Evaluate the agent tool at https://github.com/OWNER/REPO for a team of
eight that uses Claude Code and Codex. Read the repository itself (README,
LICENSE, latest release, archive status, open security issues), not blog
posts. Report as a table:
- License, and whether it allows local use, embedding, hosting for others
- Official install command, and whether the npm/PyPI package lists the
  same repository in its registry metadata
- Last release date; archived or sunsetting?
- What it adds over the Claude Code/Codex built-ins: cross-agent state,
  GUI diff review, isolation of ports/DB/credentials, remote control
- What it switches off (Remote Control, voice, auth mode)
- Where prompts, code and credentials are stored; does data leave the machine?
End with one line: adopt, pilot or reject, and why.
```

## How do you verify work that agent tools multiply?

An agent tool multiplies code; it checks none of it. CI gates decide merges, a review bot reads first and a named human owns the merge ([agent pull request review](/en/workflows/ship/agent-pr-review/)). `git worktree list` proves file isolation only, so run `--dangerously-skip-permissions` only in a disposable sandbox with restricted network access ([permissions and sandboxing](/en/workflows/harness/permissions-and-sandboxing/)).

## What goes wrong with agent tools, and how to recover

| Symptom | Cause | Recovery |
| --- | --- | --- |
| Two agents test against one dev server | Worktrees isolate files, not ports | A port block per worktree, or a sandbox |
| An agent in a new worktree lacks secrets | `.env` is gitignored | List it in `.worktreeinclude` |
| The standard tool stops shipping | Category churn | Fall back to native worktrees |

## Where to go next with agent tools

- [Running many agents at once](/en/ecosystem/agent-tools/parallel-agents/) — Worktrees, ports, merge train.
- [herdr: the agent multiplexer](/en/ecosystem/agent-tools/herdr-agent-multiplexer/) — Cross-agent state in a terminal.
- [Desktop agent environments compared](/en/ecosystem/agent-tools/agent-shells/) — Review GUIs and their licenses.
- [Agent sandboxes compared](/en/ecosystem/agent-tools/sandboxes/) — Containers, VMs, cloud sandboxes.
- [Gateways and local models](/en/ecosystem/agent-tools/gateways-local-models/) — LiteLLM, CC Switch and Ollama.
- [Headless agents in CI](/en/ecosystem/agent-tools/headless-agents-ci/) — Agents in your pipeline.
- [Other coding agents](/en/ecosystem/agent-tools/other-coding-agents/) — Cline, Goose, Aider and others.
- [Voice input](/en/ecosystem/agent-tools/voice-input/) — Dictating prompts to agents.

For skills, MCP servers and plugins, see [the ecosystem overview](/en/ecosystem/); for built-in supervisors, [Claude Code agent view](/en/claude-code/automate/agent-view/) and [Codex worktrees](/en/codex/automate/worktrees/).
