humanbound / humanbound
Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.
Why this job: topics: security-tools, ai-security, llm-security, pentesting, guardrails, prompt-injection, cybersecurity, ai-safety
What it does
AI agents hold conversations, call tools and keep state, so many security failures appear only as a conversation unfolds, never in a single prompt.
Get started
pip install 'humanbound[engine]'
export HB_PROVIDER=openai HB_API_KEY=sk-...
# the model that attacks and judges- Maintenance
- Active
- Last commit today
- Stars
- 235
- +9 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v2.14.0
- Released 10 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 9
- Last 90 days
- Issues
- 96% closed
- 1 still open
- Pull requests
- 165 merged
- 0 waiting
- Releases
- 22
- 22 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Tencent / AI-Infra-Guard | 7,441 | 4 days ago | Apache-2.0 | No downloads |
| gy15901580825 / Argus | 206 | today | Apache-2.0 | No downloads |
| dodoguardai / dodoguard | 276 | 56 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- HTML 1%
- Go Template <1%
- Dockerfile <1%
Topics
- ai-agents
- ai-red-teaming
- ai-security
- llm-security
- adversarial-testing
- cli
- owasp
- pentesting
- prompt-injection
- security-testing
- ai-safety
- aisecops
Project record
- JobAI security
- StatusListed
- Commits290
- Forks22
- Watching0
- Stars in 28 days+48
- CreatedFeb 8, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026