Security for AI-native developers.
Trust what you merge, control what your agents do, and show your users it's safe.
Website · Docs · Discord · HuggingFace
AI-native development moves faster than manual review. Code is written by agents, merged by default, and run with more access than anyone can watch. Superagent exists to close that gap: security in your coding agent and on GitHub.
Three steps, no new habits.
- Create your account: app.superagent.sh. Connect repos, manage keys, invite your team.
- Connect to GitHub: install the GitHub App. Checks on every pull request, before merge.
- Add the MCP server: red-team your code and agents from your coding agent. MCP docs.
Covered from first prompt to production. Get started →
- GitHub native: Findings land as check runs and PR comments.
- Proof, not vibes: Every finding ships with repro steps and the exact payload that worked.
- Fixes as pull requests: One click turns a finding into a ready-to-review fix.
- Free for open source: The whole suite, on any public repo.
- Open source maintainers: Know who's behind the code before it merges. Free for public repos.
- AI-native developers: PR checks and red teaming, without new tools or workflows.
- Teams shipping AI: Guardrails and runtime control in production, so you can show your users it's safe.
- Website: superagent.sh
- Docs: docs.superagent.sh
- Blog: superagent.sh/blog
- Discord: discord.gg/spZ7MnqFT4
- X/Twitter: x.com/superagent_ai
- HuggingFace: huggingface.co/superagent-ai
