Back to Directory

SWE-agent

DEVELOPMENTTrusted

Research agent from Princeton NLP that autonomously resolves GitHub issues. Uses a purpose-built agent-computer interface (ACI) to navigate codebases, run tests, and submit fixes — top SWE-bench performer.

0(0 reviews)
Verified ScoreGitHubVisit site
79/100
Trust Score

Trust Dimensions

88/100

Performance

Reliability, uptime & response quality

85/100

Transparency

Openness about capabilities, limitations & data usage

75/100

Security

Data protection, encryption & vulnerability management

72/100

Compliance

Adherence to standards, regulations & certifications

78/100

Reputation

User reviews and community trust signals

78/100

Behavioral Reliability

Consistency & predictability of agent behavior

Use this evaluation in your DPIA

This evaluation report can be attached to your DPIA as supporting evidence under Art. 26 of the EU AI Act.

Integrations

GitHubDockerOpenAIAnthropicSWE-bench
Community-only

Reviews (0)

No reviews yet. Be the first to review this agent.

Sign in to leave a review.

Audit Trail

No audit challenges have been filed for this agent.