Comparison
browser-use vs agent-skills-eval
Verdict
Pick browser-use when browser-use is primarily Python; agent-skills-eval is TypeScript; pick agent-skills-eval when agent-skills-eval is primarily TypeScript; browser-use is Python.
Markdown twin · browser-use alternatives · agent-skills-eval alternatives
GraphCanon updated today
vs
Trust & integrity
| Signal | browser-use | agent-skills-eval |
|---|---|---|
| Maintenance | Very active (0d since push) As of today · github_public_v1 | Very active (2d since push) As of today · github_public_v1 |
| Provenance | Not a fork · Organization account As of today · github_public_v1 | Not a fork · Personal account As of today · github_public_v1 |
| Security (OSV) | No lockfile As of today · none | No lockfile As of today · none |
Tagline
- browser-use
- Make websites accessible for AI agents. Automate tasks online with ease.
- agent-skills-eval
- A test runner for agentskills.io-style AI agent skills
Stars
- browser-use
- 104k
- agent-skills-eval
- 618
Forks
- browser-use
- 11k
- agent-skills-eval
- 33
Open issues
- browser-use
- 296
- agent-skills-eval
- 8
Language
- browser-use
- Python
- agent-skills-eval
- TypeScript
Adopt for
- browser-use
- browser-use is a Python-based toolset that facilitates web task automation and enhances website interaction accessibility for AI agents using browser automation techniques.
- agent-skills-eval
- -
Persona
- browser-use
- -
- agent-skills-eval
- -
Runtime
- browser-use
- -
- agent-skills-eval
- -
License
- browser-use
- The MIT License provides great flexibility and permissiveness for both open-source and proprietary software projects.
- agent-skills-eval
- MIT
Last pushed
- browser-use
- Jul 11, 2026
- agent-skills-eval
- Jul 8, 2026
Categories
- browser-use
- AI Agents, Developer Tools
- agent-skills-eval
- AI Agents, LLM Frameworks, Developer Tools
Trust and health
Days since push
- browser-use
- 0d
- agent-skills-eval
- 2d
Open issues (now)
- browser-use
- 296
- agent-skills-eval
- 8
Owner type
- browser-use
- Organization
- agent-skills-eval
- User
Full report
- browser-use
- Trust report
- agent-skills-eval
- Trust report
Choose browser-use if…
- browser-use is primarily Python; agent-skills-eval is TypeScript.
- Pricing: This tool is provided under the MIT license which means you can use it freely but there are no guarantees or formal support unless included in separate agreements..
- Requirements: Min 2 GB RAM; Requires Docker; Playwright installation and configuration needed for full functionality..
- Tags unique to browser-use: llm, python, browser-automation, playwright.
- When you need to automate interactions with websites in a straightforward manner, especially if your use case already leverages Playwright under the hood.
When NOT to use browser-use
- Avoid using browser-use if your automation workflow requires features that are exclusive to a different framework or library, such as specific functionalities only available in Selenium, as browseruse
Choose agent-skills-eval if…
- agent-skills-eval is primarily TypeScript; browser-use is Python.
- Tags unique to agent-skills-eval: agent-skills, agentskills, agent-evals, llm-evals.
- Also covers LLM Frameworks.
When NOT to use agent-skills-eval
- AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism.
- LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
- Developer Tools: A gateway is overkill when you're pinned to a single provider and model.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (browser-use/browser-use) · observed Jul 11, 2026
- GitHub forks (browser-use/browser-use) · observed Jul 11, 2026
- Last push (browser-use/browser-use) · observed Jul 11, 2026
- License file (MIT) · observed Jul 11, 2026
- Decision facts (enrichment) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (darkrishabh/agent-skills-eval) · observed Jul 11, 2026
- GitHub forks (darkrishabh/agent-skills-eval) · observed Jul 11, 2026
- Last push (darkrishabh/agent-skills-eval) · observed Jul 8, 2026
- License file (MIT) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: browser-use 104k · agent-skills-eval 618 (synced Jul 11, 2026).
Common questions
- What is the difference between browser-use and agent-skills-eval?
- browser-use: Make websites accessible for AI agents. Automate tasks online with ease.. agent-skills-eval: A test runner for agentskills.io-style AI agent skills. See the comparison table for live GitHub stats and shared categories.
- When should I choose browser-use over agent-skills-eval?
- Choose browser-use over agent-skills-eval when browser-use is primarily Python; agent-skills-eval is TypeScript; Pricing: This tool is provided under the MIT license which means you can use it freely but there are no guarantees or formal support unless included in separate agreements.; Requirements: Min 2 GB RAM; Requires Docker; Playwright installation and configuration needed for full functionality.; Tags unique to browser-use: llm, python, browser-automation, playwright; When you need to automate interactions with websites in a straightforward manner, especially if your use case already leverages Playwright under the hood.
- When should I choose agent-skills-eval over browser-use?
- Choose agent-skills-eval over browser-use when agent-skills-eval is primarily TypeScript; browser-use is Python; Tags unique to agent-skills-eval: agent-skills, agentskills, agent-evals, llm-evals; Also covers LLM Frameworks.
- When should I avoid browser-use?
- Avoid using browser-use if your automation workflow requires features that are exclusive to a different framework or library, such as specific functionalities only available in Selenium, as browseruse
- When should I avoid agent-skills-eval?
- AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Developer Tools: A gateway is overkill when you're pinned to a single provider and model.
- Is browser-use or agent-skills-eval more popular on GitHub?
- browser-use has more GitHub stars (104,191 vs 618). Stars measure visibility, not whether either tool fits your constraints.
- Are browser-use and agent-skills-eval open source?
- Yes - both are open-source projects on GitHub (browser-use: MIT, agent-skills-eval: MIT).
- Where can I find alternatives to browser-use or agent-skills-eval?
- GraphCanon lists graph-backed alternatives at browser-use alternatives and agent-skills-eval alternatives (browser-use markdown twin, agent-skills-eval markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, browser-use or agent-skills-eval?
- browser-use: Very active. agent-skills-eval: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for browser-use and agent-skills-eval?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: browser-use trust report; agent-skills-eval trust report.