by superagent-ai · AI Tool · ★ 6.5k
Superagent SDK Make your AI apps safe. Website · Docs · Discord · HuggingFace An open-source SDK for AI agent safety. Block prompt injections, redact PII and secrets, scan repositories for threats, and run red team scenarios against your agent. Features Guard Detect and block prompt injections, malicious instructions, and unsafe tool calls at runtime. TypeScript: Python: python from safetyagent import createclient client = createclient() result = await client.guard(input=usermessage) if result.classification == "block": print("Blocked:", resu
| Stars | 6,530 |
| Forks | 960 |
| Language | TypeScript |
| Category | AI Tool |
| License | MIT |
| Quality Score | 50.932/100 |
| Open Issues | 6 |
| Last Updated | 2026-04-11 |
| Created | 2023-05-10 |
| Platforms | node |
| Est. Tokens | ~6244k |
Explore other popular ai tool tools:
superagent is 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.. It is categorized as a AI Tool with 6.5k GitHub stars.
superagent is primarily written in TypeScript. It covers topics such as ai, anthropic, guardrails.
You can find installation instructions and usage details in the superagent GitHub repository at github.com/superagent-ai/superagent. The project has 6.5k stars and 960 forks, indicating an active community.
superagent is released under the MIT license, making it free to use and modify according to the license terms.