# agent-browser vs Airtop

> agent-browser scores 66.6 (B) on agent readiness against Airtop's 55.3 (C), and leads in 5 of 7 scored categories. Airtop leads on reliability. Both do browser automation. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/agent-browser-vs-airtop
- Markdown: https://www.anchorterminal.com/compare/agent-browser-vs-airtop.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/agent-browser-vs-airtop.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/agent-browser-vs-airtop.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

agent-browser scores 66.6 (B) on agent readiness against Airtop's 55.3 (C), and leads in 5 of 7 scored categories. Airtop leads on reliability. Both do browser automation.

- agent-browser: grade B, 66.6/100, rank #263 of 842. Markdown https://www.anchorterminal.com/tools/agent-browser.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-browser.json
- Airtop: grade C, 55.3/100, rank #592 of 842. Markdown https://www.anchorterminal.com/tools/airtop.md · JSON https://www.anchorterminal.com/api/v1/tools/airtop.json

## Which one, for what

### agent-browser (B)

Good for: Coding agents with a shell that want short commands and compact snapshots.

Ahead on:
- Schema & documentation, 84 against 76
- Agent ergonomics, 78 against 65
- Security & auth, 67 against 46
- Payments & pricing, 60 against 25
- Maintenance & community, 70 against 24

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source

Watch for: The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed

### Airtop (C)

Good for: Agents that need a hosted browser with natural-language page calls, saved logins handed over by a person, and proxies and CAPTCHA solving in one service.

Ahead on:
- Reliability, 69 against 48

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: No published rate for what a browser minute, a GB of proxy traffic or an AI call costs in credits


## Score by category

| Category | Weight | agent-browser | Airtop | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 48 | 69 | Airtop +21 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 84 | 76 | agent-browser +8 |
| Agent ergonomics | 13% (16.2 this run) | 78 | 65 | agent-browser +13 |
| Security & auth | 14% (17.5 this run) | 67 | 46 | agent-browser +21 |
| Payments & pricing | 10% (12.5 this run) | 60 | 25 | agent-browser +35 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 70 | 24 | agent-browser +46 |
| Transparency & trust | 7% (8.8 this run) | 61 | 61 | even |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **66.6 · B** | **55.3 · C** | |

## Facts side by side

| Fact | agent-browser | Airtop |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | Vercel Labs | Switchboard Visual Technologies, Inc. (dba Airtop) |
| Hosted endpoint | no (local only) | `https://api.airtop.ai/api` |
| Transports | stdio | HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 | Proprietary cloud service under Airtop's terms of use. The Node and Python SDKs are MIT per npm and PyPI |
| Tools exposed | 158 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-01 | 2026-07-01 |
| Terms last updated | no document linked | 2025-07-29 |
| Privacy policy last updated | no document linked | 2025-09-02 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | yes |
| Popularity | 44k stars, 2.1M npm/wk | 16 stars, 16k npm/wk, 246 PyPI/wk |

## Verdicts

**agent-browser.** Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.

**Airtop.** The cloud browser API has a public OpenAPI 3.1 document, Markdown docs, natural-language page calls with a per-call credit cap, and a status page with no incident in the last 90 days. Credit rates for browser time, proxy traffic and AI calls are not published, and the developer changelog's last entry is dated 3 September 2025.

## Before you call either

### agent-browser

1. Run `agent-browser install` once after `npm install -g agent-browser`. It downloads Chrome for Testing
2. Take a fresh `snapshot -i` after any navigation. Refs survive same-document changes only
3. Pass `--json` for machine-readable results and `--max-output` to cap page text
4. Set `--allowed-domains`, `--action-policy` and `--content-boundaries` for untrusted sites. None is on by default, and the allowlist rejects `--profile`, `--cdp` and `--restore`
5. Start MCP with `agent-browser mcp`, and add profiles such as `--tools core,network` only when needed

### Airtop

1. Terminate every session with `DELETE /v1/sessions/{id}`. Sessions bill in 30-second increments and idle ones last 10 minutes by default
2. Set `costThresholdCredits` on AI calls and read `meta.usage.credits` afterwards. Credit rates are not published, so measure them
3. Use `page-query` with `configuration.outputSchema` for structured output. `prompt-content` and `summarize-content` are deprecated
4. When calling REST without the SDK, poll session status until `running` before creating a window. Only the SDK waits for you
5. Airtop's integrated proxy cannot reach LinkedIn, ticketing sites and some banks and streaming services. Bring a custom proxy for those

## Questions

### Which is better for AI agents, agent-browser or Airtop?

agent-browser scores 66.6 (B) on agent readiness against Airtop's 55.3 (C), and leads in 5 of 7 scored categories. Airtop leads on reliability.

### Do agent-browser and Airtop need an API key?

agent-browser needs no key. Airtop needs an API key.

### Can an agent call agent-browser and Airtop without installing anything?

agent-browser runs on your own machine, with no hosted endpoint listed. Airtop has a hosted endpoint at https://api.airtop.ai/api.

### Are agent-browser and Airtop open source?

agent-browser is open source (Apache-2.0). No open-source release is listed for Airtop.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/agent-browser-vs-airtop.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-browser-vs-airtop.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "agent-browser", "b": "airtop"}`. From a terminal: `anchor compare agent-browser airtop`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-browser.json and https://www.anchorterminal.com/api/v1/tools/airtop.json

## Other comparisons with agent-browser or Airtop

- [agent-browser vs Anchor Browser](https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.md)
- [agent-browser vs Browser Use](https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.md)
- [agent-browser vs Browserbase](https://www.anchorterminal.com/compare/agent-browser-vs-browserbase.md)
- [agent-browser vs Browserless](https://www.anchorterminal.com/compare/agent-browser-vs-browserless.md)
- [agent-browser vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp.md)
- [agent-browser vs Hyperbrowser](https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser.md)
- [agent-browser vs Notte](https://www.anchorterminal.com/compare/agent-browser-vs-notte.md)
- [agent-browser vs Playwright MCP](https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.md)
- [agent-browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.md)
- [agent-browser vs Skyvern](https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.md)
- [agent-browser vs Steel](https://www.anchorterminal.com/compare/agent-browser-vs-steel.md)
- [agent-browser vs TinyFish](https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish.md)
- [Airtop vs Anchor Browser](https://www.anchorterminal.com/compare/airtop-vs-anchor-browser.md)
- [Airtop vs Browser Use](https://www.anchorterminal.com/compare/airtop-vs-browser-use.md)
- [Airtop vs Browserbase](https://www.anchorterminal.com/compare/airtop-vs-browserbase.md)
- [Airtop vs Browserless](https://www.anchorterminal.com/compare/airtop-vs-browserless.md)
- [Airtop vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/airtop-vs-chrome-devtools-mcp.md)
- [Airtop vs Hyperbrowser](https://www.anchorterminal.com/compare/airtop-vs-hyperbrowser.md)
- [Airtop vs Notte](https://www.anchorterminal.com/compare/airtop-vs-notte.md)
- [Airtop vs Playwright MCP](https://www.anchorterminal.com/compare/airtop-vs-playwright-mcp.md)
- [Airtop vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/airtop-vs-puppeteer-reference-server-archived.md)
- [Airtop vs Skyvern](https://www.anchorterminal.com/compare/airtop-vs-skyvern.md)
- [Airtop vs Steel](https://www.anchorterminal.com/compare/airtop-vs-steel.md)
- [Airtop vs TinyFish](https://www.anchorterminal.com/compare/airtop-vs-tinyfish.md)