Browser Use vs BrowserSkill
Browser Use (Browser Use) and BrowserSkill (Tencent) side by side on public data, as of Oct 10, 2026.
Browser Use has 13.8x the GitHub stars of BrowserSkill (117K against 8,521). Browser Use shipped 7 stable releases in the past 90 days. BrowserSkill shipped 18 stable releases in the past 90 days.
Side-by-side numbers
| Metric | Browser Use | BrowserSkill |
|---|---|---|
| Gid Score | 60 | 46 |
| Overall rank | #25 | #79 |
| Downloads, last 7 days | 2.2M | — |
| Downloads, 7-day change | down 3.2% | — |
| Downloads, 30-day change | — | — |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 117K | 8,521 |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 8 | 0 |
| Latest stable release | 0.13.11 · 3d ago | 0.3.2 · 10d ago |
| Stable releases, 90 days | 7 | 18 |
| Terminal-Bench (best run) | — | — |
| Price | Free | Free (OSS) |
| License | MIT | MIT |
| First released | November 2024 | June 2026 |
| Interfaces | API, CLI | — |
| Models | Any LLM of your choice (OpenAI, Anthropic, Google and others) plus its own BU2 model via the cloud |
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 BU2 model option.
Pricing: Open-source library is free (MIT). Cloud is pay-as-you-go with no subscription: credits from a $5 top-up, browsers $0.02/hour, residential proxies $5/GB, hosted agents billed at model cost plus 20%; the pricing page lists $1 in free credits for eligible signups (the README mentions $15).
Latest release 0.13.11:
- chore: pin publish workflow toolchain
- filesystem: writefile can create tiny binary images (png/gif/jpg/webp) for upload flows
- fix(agent): redact sensitive data nested below list boundaries in saved history
- fix(anthropic): treat data URL scheme and media type case-insensitively
BrowserSkill
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
Pricing: Open source under the MIT licence; check the website for any paid hosted plans.
Latest release 0.3.2:
- fix(geometry): unify cross-frame coordinates and screenshot conversion | 统一跨 frame 坐标与截图转换
- refactor(observation): decouple DOM processing from capture orchestration | 解耦 DOM 处理与采集流程
- refactor(observation): unify cross-frame capture coordination and data ownership | 统一跨 frame 采集协调与数据归属
- fix(observation): validate DOM identity across capture phases | 校验跨采集阶段的 DOM 身份一致性