Paperclip vs squad.so: Who Must Ask Before Acting?
Paperclip and squad.so both route work to people, but their documented approval controls differ. Compare review, hosting and costs.
Founder, Task Machine
Paperclip and squad.so both bring agent work back to a person, but who decides that an action needs approval? Paperclip documents connection-level action permissions. squad.so collects blocked work in Needs you, while its documentation leaves the choice to ask a question with the teammate.
For a small software team delegating customer-facing work, that difference can decide the purchase. A draft email awaiting your review and a configurable requirement to ask before sending are separate controls. Evaluate the point where an agent must stop, alongside the interface where you answer it.
Paperclip organizes delegation and review stages
Paperclip's product reference describes an organization of agents with goals, tasks and budgets. People can own tasks alongside agents, and a task retains plans, files, conversations, blockers and run history. Manager agents delegate to their reports, while a CEO agent can create and assign issues.
The execution-policy guide adds ordered review and approval stages with human or agent participants. Reviewers can send changes back to the executor. A team can use that route to separate producing a report from accepting its result.
Those stages are review stages, not general branching workflow steps. Paperclip's bundled QA skill describes acceptance criteria and a manual validation plan, but its checked material does not establish automatic checks against every task requirement. Keep that distinction visible if your acceptance process includes checks beyond a reviewer's judgment.
squad.so coordinates hosted teammates
squad.so, formerly MissionControlHQ, describes a chief of staff and teammates. The chief of staff hires and coordinates them, and teammates can route work to one another. A hiring flow asks questions and presents a plan for approval before creating a teammate.
Its task documentation supports steps, comments and ownership by a teammate or person. It also says teammates cannot currently assign a task to you, although older assignments remain visible. If your process depends on an agent handing execution back to a developer, check that constraint before adopting the board.
Shared memories can be reviewed, corrected or cleared, and teammates maintain their own notes. This is useful for recurring work that depends on company context. The documentation does not describe the same separate agent, project, goal, team and workspace scopes with restoration that some teams may require.
A waiting queue and an action boundary differ
Paperclip's action-permission documentation defines Allowed, Ask first or Off per connection. Its Decisions queue collects approvals, questions and proposals. These settings are per connection, so do not assume they establish separate rules for every action of each agent.
squad.so's control guide describes app permissions and teammates asking for help. Needs you gathers questions, approvals and other blocked work. The documentation does not describe a configurable approval requirement before selected actions, and says draft-first email depends on instructions and the teammate following them. A teammate can send an email without first producing a draft.
For an evaluation, choose an outward-facing action that you would not want taken on a guess. Record whether the requirement is an instruction to the agent or a configured permission. Then check where a waiting action appears and what lets the work continue after you answer.
Neither a central queue nor a review stage proves that every external action stops for approval. Paperclip publishes a connection permission boundary, and squad.so publishes app permissions plus a judgment-based decision to ask. Your choice depends on which boundary matches the account and action you intend to delegate.
Scheduled instructions or ordered review
Paperclip's routines can create tasks on schedules or from signed webhooks. Agents also wake on heartbeats. The docs do not describe a stable root task retaining a separate history for each occurrence.
squad.so's scheduled routines start a teammate with instructions, while triggers can start runs from webhooks and connected-app events. Skills supply written instructions and tasks can be split into steps. Its public documentation does not describe a repeatable multi-step process that follows the same route each time.
For a weekly customer report, Paperclip's execution policy offers a documented ordered review route. squad.so provides scheduled teammate instructions that people can steer through task comments. Its correctness documentation does not describe checking results against defined criteria, so include a concrete incorrect report in your evaluation of the human review process.
A further context check matters with squad.so. Its memory guide says routines start with less context than chat and, depending on the model, may not load a teammate's Notes. Required context should go in the routine instructions or in a named document for the teammate to read.
Hosting and the bill you operate
Paperclip's homepage makes its self-hosted software available under the MIT license. You arrange the hosting and AI services. The homepage offers a waitlist, while Cloud organizations appear in its documentation, leaving general hosted availability and a Cloud price unestablished.
squad.so's cost documentation lists $99 per month plus your AI provider's charges. Optional teammate inboxes cost $10 per month each, and human seats cost $9 each. Research gets 1,000 free credits a month, then costs $5 per 5,000 credits.
squad.so teammates execute on a cloud computer. Squad for Mac can grant approved access to local files, browser-tab details and screen pictures, but that does not move teammate execution onto your computer. Paperclip supports local and self-hosted deployments, which suits a different operating responsibility from a hosted squad.
Paperclip and squad.so, point by point
Both products answer the same questions in the table below. Sources and check dates accompany each answer, including capabilities whose published scope is narrower than the question.
Both columns answer the same questions from each company's public pages. Yes means the company publishes the capability the question asks about, Partly means something narrower, No means it says it does not offer it, and Not published means its public pages do not describe it. Every answer links to its source and shows when we last checked it. The oldest check on this page was November 13, 2026.
| What you compare | Paperclip | squad.so |
|---|---|---|
| Goals |
Paperclip
Partly
Goals can contain measurable targets, link to projects and have sub-goals. The docs do not describe linked metric values and trends that automatically trigger a goal lead's review. |
squad.so
Partly
A teammate can produce a recurring report on metrics you name. Its documentation does not describe a goal owned by an agent or named owner with a tracked metric or target. |
| Leads |
Paperclip
Yes
A CEO agent creates and assigns issues, while manager agents delegate to their reports. The docs do not describe distinct goal and project leads that review outcomes and propose gaps for approval. |
squad.so
Yes
The chief of staff hires and coordinates teammates, and teammates can route work to one another. The documentation does not describe separate goal and project leads that review and propose gaps. |
| Tasks |
Paperclip
Yes
Tasks can be assigned to an agent or a person, and their threads keep conversations, plans, blockers, files and run history. |
squad.so
Yes
Tasks hold steps and comments, and can be owned by a teammate or a person. Teammates cannot currently assign a task to you, although older assignments remain visible. |
| Recurring work |
Paperclip
Yes
Agents wake on heartbeats, and routines create tasks on schedules or from signed webhooks. The docs do not describe a stable root task with separate occurrence histories. |
squad.so
Yes
Routines start a teammate on a schedule, while triggers start a run from a webhook or connected app event. The documentation does not describe a stable root task with a separate task history for each occurrence. |
| Workflows |
Paperclip
Yes
Execution policies provide ordered review and approval stages with human or agent participants, and reviewers can request changes. These are review stages rather than general branching workflow steps. |
squad.so
Partly
Skills give teammates written instructions and tasks can be broken into steps. The documentation does not describe a repeatable multi-step process that runs the same way each time. |
| Autonomy |
Paperclip
Yes
The Decisions queue contains approvals, questions and agent proposals. Connector actions can be Allowed, Ask first or Off per connection, rather than a per-agent rule for every action. |
squad.so
Partly
Needs you collects questions, approvals and other blocked work, and app permissions limit what teammates can do. The choice to ask a question is the teammate's. The documentation does not describe a configurable requirement for approval before selected actions. |
| Learned autonomy |
Paperclip
Partly
People can capture decision examples with notes and export them for a training pipeline. The docs do not describe automatic proposals to change an agent's autonomy based on approval history. |
squad.so
Not published
Teammates draft outward-facing work for approval until you trust them. Its documentation does not describe proposals to change autonomy based on approval history. |
| Memory |
Paperclip
Partly
Experimental memory connectors let agents save and retrieve context through providers including Mem0 and Zep. Paperclip has no separate memory page or automatic background memory sync, and the checked docs do not establish that users can inspect or correct the saved memories. |
squad.so
Yes
Shared memories learn from conversations and can be reviewed, corrected or cleared. Teammates also have their own notes. The documentation does not describe the same separate agent, project, goal, team and workspace memory scopes with restore. |
| Planning |
Paperclip
Yes
Experimental Agent Chat can research and draft a plan with you, then create tasks with the agreed plan and what done looks like. Plan mode gives you a plan to review before implementation. |
squad.so
Yes
A ready-made job brief asks the chief of staff to plan the job with you and start in draft-for-review mode. When hiring a teammate, you answer questions and approve a plan before creation. The documentation does not describe reviewing acceptance criteria before every task starts. |
| Intake |
Paperclip
Yes
A routine webhook can create a task and assign it to an agent, and a CEO agent can create and assign issues. The docs do not describe the same project-token intake with an optional proposal first. |
squad.so
Yes
Webhook and connected-app triggers start a chosen teammate with instructions, and tasks can be assigned to a teammate. The documentation does not describe project-token intake routed through a team lead's approval queue. |
| Connectors |
Paperclip
Yes
Paperclip lists service connectors and supports custom MCP servers. Routines can also start work through webhooks. |
squad.so
Yes
The app catalog, custom API-key integrations and hosted MCP servers give teammates tools, and triggers accept webhooks or connected-app events. The custom MCP setup does not accept SSE server URLs, and the documentation does not describe a general custom command-line connector. |
| Models |
Paperclip
Partly
You choose models and runtimes per agent. Experimental pools route accounts for new tasks and pin later runs, rather than automatically choosing a model for each work stage. |
squad.so
Partly
You choose a squad or teammate model and an ordered fallback list. The documentation describes fallback on failure or rate limits, not automatic model choice by task or step. |
| Cloud or your own computer |
Paperclip
Partly
Paperclip supports local and self-hosted deployments, and its docs describe Paperclip Cloud organizations. Its homepage offers a waitlist. General hosted availability is not established. |
squad.so
Partly
Squad teammates run on a cloud computer. Squad for Mac adds approved access to local files, browser-tab details and screen pictures. Mac access does not move teammate execution onto your computer. |
| Your own subscription |
Paperclip
Yes
Paperclip lets agents use your Claude or ChatGPT subscription, or an Anthropic or OpenAI API key. Connect the provider during agent setup and select the model on the agent. |
squad.so
Yes
Squad teammates use your ChatGPT, Claude Code or GitHub Copilot subscription, or supported provider API keys, for model usage. Your provider bills you under your own plan or key. |
| Pricing |
Paperclip
Partly
Paperclip's self-hosted software is open source under the MIT license. You arrange AI access. Its homepage offers a waitlist, and the checked Cloud documentation does not publish a price. |
squad.so
Partly
The squad costs $99 per month plus your AI provider's charges. Optional teammate inboxes cost $10 per month each, human seats $9 each, and research gets 1,000 free credits a month, then costs $5 per 5,000 credits. The required squad plan is flat-priced. |
| Correctness |
Paperclip
Yes
Execution policies route work through review and approval stages, with change requests returned to the executor. A bundled QA skill describes acceptance criteria and a manual validation plan rather than automatic checks on every task requirement. |
squad.so
Partly
You can describe what done looks like and correct a task through comments. The documentation does not describe results being checked against defined criteria. |
For software work
| What you compare | Paperclip | squad.so |
|---|---|---|
| Code review rules |
Paperclip
Yes
An experimental GitHub review bot accepts your own code-review guidance for pull requests. Its docs do not describe discovering repository rules and screening suggested rules against examples. |
squad.so
Partly
The GitHub integration can work with code, branches, pull requests and reviews. Its documentation does not describe reviewing changes against repository rules. |
| Adversarial review |
Paperclip
Yes
Execution policies can route an issue to an independent reviewer, and low-trust review can contain work on external pull requests. The docs do not describe two independent adversarial reviewers automatically examining high-risk changes together. |
squad.so
Not published
The GitHub integration can work with pull requests and reviews. Its documentation does not describe an independent second review of risky changes. |
| Risk rating |
Paperclip
Partly
A bundled GitHub pull request skill instructs an agent to include risk and rollback information in the pull request. It does not describe a revision-specific Low, Moderate or High merge-risk rating. |
squad.so
Not published
The GitHub integration can read pull requests and repository information. Its documentation does not describe a risk rating of a change before merge. |
| Pull requests |
Paperclip
Yes
Agents can create pull requests and push fixes after review. Experimental review bots publish a check on the reviewed commit, which GitHub repository rules can require before merging. |
squad.so
Partly
The GitHub integration supports code, branches, pull requests and reviews. The documentation does not establish agents addressing pull request review feedback. |
A fact we cannot find or cannot check is left out, and prices can change after the date shown. Task Machine publishes this comparison and is an interested party. Paperclip and squad.so are named only to identify them, and there is no relationship between the companies. Has something changed? Tell us.
Who each one suits
Pick Paperclip if you want self-hosted task ownership, connection-level action permissions and ordered review stages. Its experimental memory connectors require provider setup, and its checked documentation does not establish automatic validation of every task requirement.
Pick squad.so if you want a hosted chief of staff, shared memories and scheduled teammates using your AI account. Its documentation does not describe configurable approval requirements for selected actions, and says teammates cannot currently assign a task to you.
Where Task Machine fits
Task Machine addresses the stopping rule through per-agent Ask first or Automatic action settings. Its autonomy documentation describes decisions arriving in the Inbox with context, while Workflows can include human approvals and verifier checks. A recurring job can keep one stable root Task with separate occurrence histories, giving you another way to review repeated work.
Task Machine is the wrong choice if your requirement is Paperclip's self-hosted MIT-licensed software, or if a hosted chief of staff with squad.so's judgment-based delegation already meets your needs. Read Task Machine vs Paperclip and Task Machine vs squad.so, then map one customer-facing action to the exact approval setting you would use.