autoguardrails
Alignment-research scaffold for LLM guardrails involving policy evaluation and content moderation
GraphCanon updated Oct 21, 2026 · GitHub synced Oct 21, 2026
Decision brief
Unverified catalog guidance: Autoguardrails is an evaluation and development framework for AI policy creation and review. It enables the iterative adjustment and testing of guardrail policies in alignment research through a controlled workflow.
Good fit when
- Unverified catalog guidance: When you are conducting alignment research that requires systematic iteration on LLM safeguard policies.
- Unverified catalog guidance: If your project operates with an open-source requirement, given its Apache-2.0 license agreement.
Avoid when
- Unverified catalog guidance: Autoguardrails may not suit needs requiring real-time or dynamic policy adjustments outside its autoresearch workflow.
- Unverified catalog guidance: Avoid using Autoguardrails if you cannot accept offline operation as it is built on the Python standard library and runs without third-party runtime dependencies.
- Requirements:
- Requires Python 3.10 or higher.; No third-party runtimes; it is built completely on the standard Python library.
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (20d since push)
- As of Oct 21, 2026
- Provenance
- Not a fork · Organization account
- As of Oct 21, 2026
- Security (OSV)
- No lockfile
- As of Oct 18, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
Package installation is not established from the available documentation. Check the source repository for setup instructions.
git clone https://github.com/santanderai/autoguardrailsSource repositorySimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Autoguardrails is scaffolding for alignment research to develop LLM safety mechanisms like guardrails through an autoresearch style workflow. It operates on a policy.md file to evaluate different policies against preset criteria, allowing for iterative adjustment and testing in a controlled environment.
Capability facts
- CLI
- Declared CLI entrypoint
Source: pyproject.toml:[project.scripts] · Oct 21, 2026
- MCP server
- Unknown; MCP server not established by this scan
Source: repo_scan · Oct 21, 2026
- Languages
- python
Source: github.language+pyproject.toml · Oct 21, 2026
Categories
Tags
README
Quick Start Run from the repository root. 1. Record a baseline. 2. Edit only . 3. Score the new candidate. 4. Inspect the current kept result. 5. Inspect the full log. If a candidate is rejected, the harness restores to the last accepted version automatically. Requirements Python...
For agents
This page has a .md twin and JSON over the API.