superagent-ai/superagent

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

64
/ 100
Established

Provides runtime guard detection with classification of violation types, PII/secret redaction using LLM-powered analysis, and repository scanning for agent-targeted attacks. Offers both API-based safety checks and open-weight models (0.6B-4B parameters) deployable on-premises for low-latency inference without data egress. Supports TypeScript, Python, CLI, and MCP Server integrations across any LLM provider.

6,461 stars. Actively maintained with 3 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

6,461

Forks

955

Language

TypeScript

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/superagent-ai/superagent"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.