SantanderAI / autoguardrails
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
Why this job: topics: security, red-teaming, guardrails, prompt-injection, jailbreak, ai-safety, guardrails
What it does
Part of Santander AI Open Source — open source AI projects from Banco Santander (santander.com).
Get started
python -m autoguardrails baseline --reset --repeat 2 --notes "initial baseline"You need: Python 3.10+; No third-party runtime dependencies — the harness is built entirely on the Python standard library and runs offline by default.; Optional, for development only: ruff, black, mypy, pytest, pytest-cov (see CONTRIBUTING.md).
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 129
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.0
- Released 4 months ago
- Built with
- Python
- 98% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 7 merged
- 1 waiting
- Releases
- 1
- 1 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| superagent-ai / superagent | 6,856 | 2 months ago | MIT | Mac, Windows, Linux |
| yueliu1999 / FlipAttack | 182 | 3 months ago | MIT | No downloads |
| dodoguardai / dodoguard | 276 | 57 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 98%
- Shell 2%
Topics
- ai
- ai-safety
- alignment
- autoresearch
- benchmark
- content-moderation
- evaluation
- guardrails
- jailbreak
- llm
- llm-safety
- machine-learning
Project record
- JobAI security
- StatusListed
- Commits14
- Forks36
- Watching5
- Stars in 28 days0
- CreatedJun 15, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026