Browser Use vs ARTEMIS
Browser Use (Browser Use) and ARTEMIS (Google) side by side on public data, as of Nov 21, 2026.
Browser Use has 6.8x the GitHub stars of ARTEMIS (122K against 17.8K). Browser Use shipped 14 stable releases in the past 90 days.
Which should you choose?
Choose Browser Use if
- you need to run local models
- you want to use your own model API key
- you want to switch between model providers (10 documented against 4)
- you want to run it unattended in scripts or CI
- you prefer the more widely used tool, with more docs and answers around (Gid Score 60 against 41)
Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.
Side-by-side numbers
| Metric | Browser Use | ARTEMIS |
|---|---|---|
| Gid Score | 60 | 41 |
| Usage data as of | Nov 21 | Nov 21 |
| Rank by Gid Score | #17 | #83 |
| Downloads, last 7 days | 2.1M | — |
| Downloads, 7-day change | down 2.4% | — |
| Downloads, 30-day change | down 6.7% | — |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 122K | 17.8K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 12 | 0 |
| Latest stable release | 1.0.7 · yesterday | — |
| Stable releases, 90 days | 14 | — |
| Terminal-Bench (best run) | — | — |
| Price | Free | Free (OSS) |
| License | MIT | Apache-2.0 |
| First released | November 2024 | August 2026 |
| Interfaces | API, CLI | CLI, SDK, MCP server, Web app |
| Models | Any LLM of your choice (OpenAI, Anthropic, Google and others) plus its own BU 2.0 model via the cloud | — |
A dash means there is no public data for that metric as of Nov 21, 2026.
Trends
Browser Use
Open-source Python library and hosted cloud that let LLM agents control a real browser to complete web tasks, with a CLI, a cloud API for hosted agents and browsers, and its own BU 2.0 model option.
Pricing: Open-source library is free (MIT). Cloud is pay-as-you-go with no subscription: $1 free signup credit, browsers $0.06/hour, home-IP proxies $5/GB, direct/custom proxies $0.20/GB. Agents start at $0.006/task (median). Token-based model pricing ranges from $0.12–$12/1M input tokens across 19+ models (GPT-6 Luna, Claude, Grok, etc.). Browser concurrency unlocked by cumulative spending: 50 browsers at $100 total paid, 250 at $1,000, 500 at $5,000, 1,000 at $25,000.
Latest release 1.0.7:
- MCP calls no longer time out at 60 s. A long browser_exec now replies within 50 s with the output so far, so Cursor and other clients with a 60 s limit get a result instead of Request timed out.
- README: Browser Use for enterprises, and the Cloud API key link is back in the Python quickstart.
- Skills, README, CLI and MCP ask coding agents for integration feedback.
ARTEMIS
An agent that takes natural-language instructions and carries out multi-step tasks and test workflows on Android devices or emulators through ADB using multimodal models, with an MCP server so coding assistants can drive devices.
Pricing: Free Apache-2.0 software; users supply their own multimodal model API keys.
Browser Use vs ARTEMIS: common questions
How do Browser Use and ARTEMIS prices compare?
Browser Use: Free. ARTEMIS: Free (OSS). Prices come from each vendor's pricing page.
Which is more popular, Browser Use or ARTEMIS?
Browser Use has a Gid Score of 60 against 41 for ARTEMIS. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do Browser Use and ARTEMIS support local models?
Browser Use documents support for local models; ARTEMIS's documentation does not.