SuperAgent
Superagent’s open-source SDK helps protect AI applications from prompt injection, data leaks, and harmful outputs.
About SuperAgent
SuperAgent is an open-source SDK for adding safety checks to AI applications. It can guard runtime inputs for prompt injections and unsafe tool calls, redact PII, PHI and secrets from text, and scan repositories for agent-targeted attacks such as repo poisoning. It is available through TypeScript and Python SDKs, a CLI, and an MCP Server. Use requires an API key from superagent.sh, scans report usage cost, and red-team testing against production agents is listed as coming soon.
Key features
- Detect and block prompt injections and unsafe tool calls at runtime
- Redact PII, PHI and secrets from text automatically
- Analyze repositories for repo poisoning and malicious instructions
- Run red-team scenarios against production agent endpoint (coming soon)
- TypeScript and Python SDKs for embedding checks in apps
- CLI and MCP Server for automation and Claude tools
Best for: Developers building AI agents who need code-level checks for injections, redaction, and repository scanning.
Good for
- Open source under MIT license
- Offers TypeScript, Python, CLI, and MCP Server integration options
- Works with models from OpenAI, Anthropic, Google, Groq, Bedrock, and more
Watch out for
- Red-team testing is listed as coming soon
- Requires signing up at superagent.sh for an API key
- Repository scans report usage cost
SuperAgent at a glance
- Website
- github.com/homanp/superagent
- Category
- Privacy & Security › Security Tools
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Guides for Security Tools
SuperAgent alternatives
Tools and sites you could use instead, ranked by how closely they match.
Check open-source dependencies for vulnerabilities and license compliance with OpenSCA-CLI.
Open source
24 alternatives
ClawMoat helps guard AI agents against data leaks, unsafe tool use, and poisoned dependencies through an open-source firewall.
Open source
24 alternatives
QWED verifies LLM outputs, tool calls, code, schemas, and agent state before production execution.
Open source
24 alternatives
Plexiglass helps detect and protect against vulnerabilities in large language models.
Open source
24 alternatives
git-hound searches public GitHub repositories for exposed secrets and credentials.
Open sourcePick
24 alternatives
Use reference sheets for reverse engineering, binary analysis, and assembly programming tools.
Open source
24 alternativesPopular in Security Tools
Well-known listings from the same topic.
Online Password Hash Crackonlinehashcrack.comOTP Authapps.apple.com/app/otp-auth/id659877384MD5 reverse lookupmd5.gromweb.comMozilla SSLssl-config.mozilla.orgchallenges.rechallenges.reGoPlus Locker V3gopluslabs.io
SuperAgent FAQ
How do I start using SuperAgent?
Sign up at superagent.sh for an API key, install the safety-agent package with npm or uv, then set SUPERAGENT_API_KEY.
What integration options are available?
TypeScript SDK, Python SDK, CLI for testing and automation, and MCP Server for use with Claude Code and Claude Desktop.
What does Scan check?
It analyzes repositories for AI agent-targeted attacks such as repo poisoning and malicious instructions and returns a security report.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.