# Checksum — card for AI agents

Generates Playwright end-to-end and API tests, runs them in CI and repairs failing tests automatically as the code changes.

Maker: Checksum · category: AI testing and QA agents

## Price
- Priced by the number of workflows and tests maintained, with no per-seat or per-run fees; no public prices.
- Pricing page: https://checksum.ai/
- Checked: 2026-10-06

## Install
- npm: `npm install -g @checksum-ai/runtime`

## Facts
- Interfaces: Web app, CLI, API, MCP server, Messaging apps

## Numbers (AgentGid data)
- Gid Score: 31 (rank #232); limited data: 2/4 score components have public numbers (public popularity and activity, not quality)
- Downloads last 7 days: 19,023

## Details (plan limits, live status, safety; from AgentGid's data)
Checksum by Checksum. Category: AI testing and QA agents. Type: AI test generation and maintenance (Playwright). Generates Playwright end-to-end and API tests, runs them in CI and repairs failing tests automatically as the code changes. Proprietary Pricing (checked 2026-10-06): Priced by the number of workflows and tests maintained, with no per-seat or per-run fees; no public prices. Interfaces: Web app, CLI, API, MCP server, Messaging apps Supports: headless Data: Gid Score 31/100, #232 overall; #4 in its category; usage +30% over 30 days.

## Alternatives in the same category
- Momentic: https://agentgid.com/agents/momentic/agent.md
- e2e: https://agentgid.com/agents/tester-army-e2e/agent.md
- mabl: https://agentgid.com/agents/mabl/agent.md
- KaneAI: https://agentgid.com/agents/kaneai/agent.md
- QA Wolf: https://agentgid.com/agents/qa-wolf/agent.md
- Ito: https://agentgid.com/agents/ito/agent.md

## Links
- AgentGid page: https://agentgid.com/agents/checksum/
- Source: https://checksum.ai/
- Source: https://registry.npmjs.org/@checksum-ai/runtime

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
