NeuroSquad vs Paperclip:work with your agents, live
Paperclip runs an “AI company” on a server you host: agents wake on heartbeats and work tickets headless. NeuroSquad is a desktop app where every agent is a real, live terminal on a canvas — you watch it, answer it and steer it. 22 CLIs, native on Windows and macOS, nothing to host.
servers, databases or ports to run. Install the app and open a folder
0
idle wake-ups: an agent spends tokens only when you or a lead agent prompt it
Cost of running
Both are free to download. Running them is not the same
The real cost is what comes after the download: the hours you spend on infrastructure and the tokens your agents spend when nobody asked.
NeuroSquad
$0desktop app, nothing to host
Install and open — no Node version, database or ports
Agents run when prompted, never on an idle timer
SHA-256-verified auto-update, no migrations to plan
Paperclip
$0+ a server you run yourself
Node 24.11+ and an embedded Postgres
Deployment modes, ports and database migrations; each of their last four feature releases lists “Breaking Changes”
Heartbeats wake agents on a schedule — their own issue #3401 calls it “architecturally heavyweight”
A hosted version is waitlist-only, with no public pricing
Paperclip’s own blog calls it “unnecessary overhead for a solo developer who only wants to watch a few Claude sessions”. That developer is exactly who NeuroSquad is built for.
Where we win
Twelve places where NeuroSquad is clearly ahead
All of them come from one choice: the human stays at the keyboard, with every agent live in front of them.
A real terminal for every agent
Each card is the CLI’s own interactive interface. Watch the diff appear, interrupt with Escape, type a correction mid-turn.
NeuroSquad
Live TUI you can type into
Paperclip
Headless runs; you steer through ticket comments
Permission prompts stay on
When Claude Code asks before a risky command, you answer in its own terminal. The card tells you exactly what it is asking. Dangerous mode is your explicit choice per card.
NeuroSquad
Prompts answered in place
Paperclip
Headless Claude runs skip permissions by default
22 agent CLIs, all first-class
Claude Code, Codex, Antigravity CLI, OpenCode, Qwen, Copilot CLI, Kilo, Goose, Cline, Crush, aider, Amp, Auggie, omp and more — each resumes its session and reports its exact status.
NeuroSquad
22 CLIs at the same depth
Paperclip
10 built-in adapters, Gemini experimental
Native on Windows — and on macOS
Built and tested on Windows first: a native installer, winget and Scoop, hardened ConPTY terminals, Git Bash, WSL workspaces. On a Mac: Apple silicon and Intel, Homebrew or one line in Terminal, its own updates.
NeuroSquad
A desktop app for Windows and macOS
Paperclip
Install scripts target Linux and macOS; open Windows issues such as #10012 and #14066
Zero ops
No server to keep alive, no database to back up before an upgrade, no ports or tunnels to configure. Updates install themselves.
NeuroSquad
Install and open
Paperclip
Node 24.11+, Postgres, deployment modes
No tokens burned while idle
An agent works when you or its lead agent send a prompt. A quiet weekend costs exactly nothing.
NeuroSquad
Work only on real prompts
Paperclip
Heartbeat wake-ups on a schedule
Permissions you can see
Draw an arrow from an agent to a browser, a terminal or another agent — only then does it get those tools. Every call lights up its arrow.
NeuroSquad
Visible, auditable wiring on a canvas
Paperclip
Roles and settings in an org chart
Card mode that really removes tools
Switch an agent to canvas mode and its own shell and web tools are removed or denied at the CLI level — and stay off even in dangerous mode.
NeuroSquad
Enforced per CLI, checked live
Paperclip
Their docs: connector gates don’t constrain shell git or gh
Usage from the CLIs’ own logs
Tokens and cost are read from each CLI’s logs — subscriptions included — to the last token and picodollar, cross-checked by an independent recount.
NeuroSquad
Exact, per card, model and account
Paperclip
Cost as reported by each adapter
A browser any agent can drive, and dictation
A real Chrome card that any MCP-capable agent can control, and local speech-to-text (Parakeet, Whisper) that never leaves your machine.
NeuroSquad
Built into the app
Paperclip
Not built in
Your phone, without a VPN
Scan a QR code: the whole app opens in the phone browser over Wi-Fi or over the internet through a tunnel. The desktop always shows who is connected.
NeuroSquad
LAN or internet, no setup
Paperclip
The server must be reachable: Tailscale, VPN or a public deploy
English, Russian and Chinese
The app, the site and the docs in three languages, switched live without a restart.
NeuroSquad
en / ru / zh
Paperclip
English only
Side by side
The full comparison
Including the rows where Paperclip is ahead — they are real, and they matter for some teams.
Capability
NeuroSquad
Paperclip
Price
Yes: Free
Yes: Free, MIT; hosted version waitlist-only
What you install
Yes: A desktop app
Partly: A server: Node 24.11+, embedded Postgres
Live, interactive terminal per agent
Yes: Yes, the CLI’s own interface
No: Headless runs
Permission prompts during a run
Yes: Answered in place
Partly: Skipped by default for headless Claude
Agent CLIs
Yes: 22
Partly: 10 built-in adapters
Windows
Yes: Native, Windows-first
Partly: Works, with open Windows issues
Grid of live agent terminals
Yes: Grid mode next to the canvas, same terminals
No: Run transcripts in a web UI
Tokens spent while idle
Yes: None
Partly: Heartbeat wake-ups
Permissions as visible arrows
Yes: Tools per arrow
No: Org chart and settings
Card mode enforced at the CLI level
Yes: Survives dangerous mode
No: —
Usage from the CLIs’ own logs
Yes: Exact, subscriptions included
Partly: Adapter-reported cost
Budget caps
Partly: Per workspace brake
Yes: Company, agent and project, 80% warning
Plan-limit meters for Claude and Codex
Yes: Yes, plus several CLI accounts
Yes: Yes
Token-saving plugins
Yes: RTK-AI Token Saver and Caveman, live by arrow
Partly: A plugin system; no token saver in their README
Your own model servers (Ollama, LM Studio, vLLM…)
Yes: Offered to every CLI that can use them
Partly: Through each CLI’s own config (e.g. OpenCode provider/model)
MCP servers and skills
Yes: MCP Registry (35k) and skills.sh (20k) searchable in the app
Yes: Skills catalog, MCP, plugins
Browser any agent can drive
Yes: Yes
No: —
Local dictation
Yes: Parakeet / Whisper
No: —
Phone access
Yes: Whole app, LAN or tunnel, no VPN
Partly: Web UI; server must be reachable
Interface languages
Yes: English, Russian, Chinese
No: English
Unattended schedules (cron, webhooks)
Partly: A daily prompt per agent
Yes: Routines and heartbeats
Approval gates and a decisions queue
No: —
Yes: Yes
Agents on remote machines
Partly: WSL and SSH workspaces: Claude Code and shells so far
Yes: SSH targets and sandbox providers
Several users with roles
No: Single user
Yes: Owner, admin, operator, viewer
Open source, no account
No: Closed source, free account
Yes: MIT, no account
macOS and Linux
Partly: Windows and macOS (Apple silicon and Intel); Linux later
Yes: Anywhere Node runs
Price
NeuroSquad
Yes: Free
Paperclip
Yes: Free, MIT; hosted version waitlist-only
What you install
NeuroSquad
Yes: A desktop app
Paperclip
Partly: A server: Node 24.11+, embedded Postgres
Live, interactive terminal per agent
NeuroSquad
Yes: Yes, the CLI’s own interface
Paperclip
No: Headless runs
Permission prompts during a run
NeuroSquad
Yes: Answered in place
Paperclip
Partly: Skipped by default for headless Claude
Agent CLIs
NeuroSquad
Yes: 22
Paperclip
Partly: 10 built-in adapters
Windows
NeuroSquad
Yes: Native, Windows-first
Paperclip
Partly: Works, with open Windows issues
Grid of live agent terminals
NeuroSquad
Yes: Grid mode next to the canvas, same terminals
Paperclip
No: Run transcripts in a web UI
Tokens spent while idle
NeuroSquad
Yes: None
Paperclip
Partly: Heartbeat wake-ups
Permissions as visible arrows
NeuroSquad
Yes: Tools per arrow
Paperclip
No: Org chart and settings
Card mode enforced at the CLI level
NeuroSquad
Yes: Survives dangerous mode
Paperclip
No: —
Usage from the CLIs’ own logs
NeuroSquad
Yes: Exact, subscriptions included
Paperclip
Partly: Adapter-reported cost
Budget caps
NeuroSquad
Partly: Per workspace brake
Paperclip
Yes: Company, agent and project, 80% warning
Plan-limit meters for Claude and Codex
NeuroSquad
Yes: Yes, plus several CLI accounts
Paperclip
Yes: Yes
Token-saving plugins
NeuroSquad
Yes: RTK-AI Token Saver and Caveman, live by arrow
Paperclip
Partly: A plugin system; no token saver in their README
Your own model servers (Ollama, LM Studio, vLLM…)
NeuroSquad
Yes: Offered to every CLI that can use them
Paperclip
Partly: Through each CLI’s own config (e.g. OpenCode provider/model)
MCP servers and skills
NeuroSquad
Yes: MCP Registry (35k) and skills.sh (20k) searchable in the app
Paperclip
Yes: Skills catalog, MCP, plugins
Browser any agent can drive
NeuroSquad
Yes: Yes
Paperclip
No: —
Local dictation
NeuroSquad
Yes: Parakeet / Whisper
Paperclip
No: —
Phone access
NeuroSquad
Yes: Whole app, LAN or tunnel, no VPN
Paperclip
Partly: Web UI; server must be reachable
Interface languages
NeuroSquad
Yes: English, Russian, Chinese
Paperclip
No: English
Unattended schedules (cron, webhooks)
NeuroSquad
Partly: A daily prompt per agent
Paperclip
Yes: Routines and heartbeats
Approval gates and a decisions queue
NeuroSquad
No: —
Paperclip
Yes: Yes
Agents on remote machines
NeuroSquad
Partly: WSL and SSH workspaces: Claude Code and shells so far
Paperclip
Yes: SSH targets and sandbox providers
Several users with roles
NeuroSquad
No: Single user
Paperclip
Yes: Owner, admin, operator, viewer
Open source, no account
NeuroSquad
No: Closed source, free account
Paperclip
Yes: MIT, no account
macOS and Linux
NeuroSquad
Partly: Windows and macOS (Apple silicon and Intel); Linux later
Paperclip
Yes: Anywhere Node runs
In practice
Where the difference shows up
Everyday moments of working with agents, and what each tool gives you in them.
01
Claude asks before deleting a folder
The card turns “needs you” and says “permission for Bash — rm -rf dist”. You read it and answer in Claude’s own terminal.
The question is asked, not skipped.
02
Five sessions before lunch, on Windows
Install, open the project folder, add Claude Code, Codex and three helpers. No WSL, no bash wrappers, no server to start.
Working in minutes, not after an afternoon of setup.
03
A squad beyond the usual two
Qwen writes tests, Copilot CLI reviews, Kilo refactors, Goose runs the docs — each with resume, statuses and MCP tools.
None of these four is a built-in Paperclip adapter.
04
A quiet weekend
You are away, nobody prompts the agents, and nothing wakes them up to “check in”.
Zero tokens spent on Monday’s bill.
05
Catching a wrong turn mid-task
You see the agent open the wrong file. Escape, one line of correction, and it carries on — in the same session.
Steer in seconds instead of waiting for the next run.
06
Answering from the train
An agent needs you. The whole canvas opens in the phone browser over the internet — no Tailscale, no VPN, no public server.
One QR scan, done.
To be fair
When Paperclip may suit you better
The two tools solve different problems. Pick by the job, not the logo.
You want agents to run unattended as a “company”: on schedules and webhooks, with approval gates and an audit log per ticket.
Several people manage the same agents, with roles and per-user secrets.
You need open source you can self-host without any account, on Linux, or any agent CLI on remote machines and in sandboxes — NeuroSquad runs Claude Code and shells in WSL and over SSH so far.
If you are the one at the keyboard with five to twenty agent sessions — and want to see, answer and steer each of them — NeuroSquad is built for you.
FAQ
Questions about choosing
Yes. The plan is free and unlimited. You need a free NeuroSquad account to sign in; you pay only for the agent CLIs you already use.
Yes. They do different jobs: Paperclip runs agents for you while you are away, NeuroSquad is where you work with them live. Both run the same CLIs with your own logins.
No. Code, prompts, terminal output and keys stay on your machine. The account stores your email and usage counts — never content. The full list is on the privacy page.
Mac — yes: NeuroSquad runs on Windows 10 and 11 and on macOS 12 or newer, on Apple silicon and Intel. Install it with Homebrew, one line in Terminal or a .dmg. Linux is coming later.
Yes, for Claude Code and shells: open a workspace in a WSL distro or in a folder on an SSH host, and they run there live, with statuses, MCP tools by arrow and transcripts. The other agent CLIs don’t run in WSL or over SSH yet.
From Paperclip’s public site, documentation, source code and issue tracker, read on 1 October 2026 — the links are at the bottom of this page. Both projects move fast; if something here is out of date, tell us and we will fix it.
Every agent live, in front of you — free
22 agent CLIs as real terminals on one canvas, with arrows as permissions and nothing to host.