# Capy — AI Coding Tool Review & Pricing

> Capy runs a fleet of cloud coding agents in parallel, taking each task from plan to merged PR. You can start work from the Capy desktop app, the web UI, Slack, Linear, GitHub, triggers or cron. Each agent runs in an isolated cloud VM. Captains coordinate crews of agent threads, and a built-in review agent checks every PR.

Source: https://ai.dosa.dev/tools/capy · Updated Nov 8, 2026 · Category: Autonomous & Async Agents · Published by dosa.dev

## At a glance

- **Tool**: Capy
- **Company**: Capy (YC F24, formerly Scrapybara)
- **Category**: [Autonomous & Async Agents](https://ai.dosa.dev/category/async-agents)
- **Pricing model**: Paid
- **Official website**: https://capy.ai/

## Key features

- Run hundreds of agents in parallel, each in an isolated cloud VM with snapshots and Docker-in-Docker
- Captains (GA in v0.7.0) direct crews of threads that pick up work from built-in Issues
- Built-in review agent runs on every PR, and you can create and review PRs inside Capy
- Computer use, browser use and annotated videos for end-to-end testing, plus iOS and Android builds tested on cloud phones (Pro and Max plans)
- Claude, GPT, Gemini and other models, with bring-your-own API keys or a ChatGPT (Codex), GitHub Copilot or SuperGrok subscription
- Slack, Linear, GitHub and Sentry integrations, plus scheduled and triggered automations
- Dock CLI (`capy dock`) runs threads headless on any macOS, Linux or Windows machine

## Pricing

**Model**: Paid

Every plan includes unlimited members, and the plan sets your monthly credits and cloud machine limits. Lite costs $20/mo ($16/mo billed annually) with $20 of credits, and your first 7 days cost $1 with a verified card. Pro costs $100/mo ($80/mo annually) with $105 of credits and adds mobile builds and devices. Max runs from $200 to $1,000/mo in $100 steps with 10% bonus credits. Enterprise is custom and adds SSO/SAML and audit logging. You can bring your own API keys, or a ChatGPT (Codex), GitHub Copilot or SuperGrok subscription, on every plan.

## Who it is for

- **Best for**: Engineering teams that want to hand off backlogs, migrations, bug triage, PR review and E2E testing to many cloud agents at once, starting work from Slack or Linear.
- **Not ideal for**: Developers who want a free or local-only tool, or who prefer working with one agent inside their editor instead of managing a fleet of cloud agents.

## Verdict

A capable platform for running many cloud agents in parallel, with strong team integrations, model flexibility and unlimited members. Usage is billed in credits, so costs grow with agent activity.

## Recent updates

Capy 0.7.2 (Nov 1, 2026) made the Dock CLI installable on macOS, Linux and Windows. Capy 0.7.0 (Oct 31, 2026) made Captains and Issues GA, added the Dock CLI and added a context breakdown view. On Oct 28, 2026 Capy announced iOS and Android app testing on cloud phones.

## Frequently asked questions

### Is Capy free?

Capy is Paid. Every plan includes unlimited members, and the plan sets your monthly credits and cloud machine limits. Lite costs $20/mo ($16/mo billed annually) with $20 of credits, and your first 7 days cost $1 with a verified card. Pro costs $100/mo ($80/mo annually) with $105 of credits and adds mobile builds and devices. Max runs from $200 to $1,000/mo in $100 steps with 10% bonus credits. Enterprise is custom and adds SSO/SAML and audit logging. You can bring your own API keys, or a ChatGPT (Codex), GitHub Copilot or SuperGrok subscription, on every plan. Check the official site for current plans.

### Is Capy open source?

Capy is not listed as open source on ai.dosa.dev - it is Paid.

### How much does Capy cost?

Every plan includes unlimited members, and the plan sets your monthly credits and cloud machine limits. Lite costs $20/mo ($16/mo billed annually) with $20 of credits, and your first 7 days cost $1 with a verified card. Pro costs $100/mo ($80/mo annually) with $105 of credits and adds mobile builds and devices. Max runs from $200 to $1,000/mo in $100 steps with 10% bonus credits. Enterprise is custom and adds SSO/SAML and audit logging. You can bring your own API keys, or a ChatGPT (Codex), GitHub Copilot or SuperGrok subscription, on every plan. Pricing changes often - verify on the official site.

### Who is Capy best for?

Engineering teams that want to hand off backlogs, migrations, bug triage, PR review and E2E testing to many cloud agents at once, starting work from Slack or Linear.

### Who is Capy not ideal for?

Developers who want a free or local-only tool, or who prefer working with one agent inside their editor instead of managing a fleet of cloud agents.

### What are the best Capy alternatives?

The closest Capy alternatives on ai.dosa.dev are Jules by Google, OpenHands, SWE-agent - all listed under Autonomous & Async Agents.

### Who makes Capy?

Capy is developed by Capy (YC F24, formerly Scrapybara). It is listed in the Autonomous & Async Agents category on ai.dosa.dev.

## Top alternatives

- [Jules by Google](https://ai.dosa.dev/tools/jules) (Freemium) — Developers who want to offload repetitive, non-urgent tasks like dependency version bumps, lint fixes, test scaffolding, and resolving CI failures in GitHub-hosted projects.
- [OpenHands](https://ai.dosa.dev/tools/openhands) (Freemium) — Individual developers and software teams looking to automate repetitive coding tasks, repository maintenance, and issue resolution through autonomous agents.
- [SWE-agent](https://ai.dosa.dev/tools/swe-agent) (Open Source) — Autonomous resolution of software engineering issues in real GitHub repositories and performing custom developer tasks using language models.
- [mini-swe-agent](https://ai.dosa.dev/tools/mini-swe-agent) (Open Source) — Researchers and engineers who want a small, transparent coding agent baseline for benchmarks, fine-tuning or sandboxed batch runs, and developers who want a simple bash-only agent in the terminal.
- [Sweep](https://ai.dosa.dev/tools/sweep) (Freemium) — Individual developers and teams working primarily in JetBrains IDEs who want a native-feeling assistant for routine coding tasks, bug fixes, and autocompletions.
- [Ellipsis](https://ai.dosa.dev/tools/ellipsis) (Freemium) — Teams looking to centralize and govern AI coding agents across repositories with secure, non-personal credentials and persistent cloud-based execution.
- Full alternatives guide: https://ai.dosa.dev/tools/capy/alternatives