xlang-ai/OSWorld

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Use with caution. xlang-ai/OSWorld scores 78/100. Review security details before production use.
78
Trust Score
B
Grade
1
Security
N/A
Downloads

Package Details

Namexlang-ai/OSWorld
Authorxlang-ai
LicenseApache-2.0
LanguagePython
Sourcegithub — view
Categoryresearch
Stars2.6k
EU AI Actminimal

Security Analysis

Security Score1/100
Activity Score1/100
Documentation1/100
Popularity0/100

View full safety report →

Add to Your CI

Automatically check xlang-ai/OSWorld trust score in your CI pipeline:

# Check trust score before deploy
curl -s "https://nerq.ai/v1/preflight?target=xlang-ai/OSWorld" | jq '.trust_score'

Alternatives

#NameTrustGradeStars
1hiyouga/LlamaFactory80B67.8k
2OpenDCAI/Paper2Any80B1.7k
3inclusionAI/AReaL80B3.6k
4camel-ai/camel80B16.1k
5DLR-RM/rl-baselines3-zoo80B2.7k
6truera/trulens79B3.1k
7vamplabAI/sgr-agent-core78B1.0k
854yyyu/zotero-mcp78B1.5k

View all alternatives →

FAQ

Is xlang-ai/OSWorld safe?

Trust Score: 78/100, Grade: B. See the full safety report for details.

Does xlang-ai/OSWorld have vulnerabilities?

Security Score: 1/100. Check /is-xlang-ai-osworld-safe for current vulnerability data.

What license is xlang-ai/OSWorld?

License: Apache-2.0.

We use cookies for analytics and caching. Privacy Policy