Add Adrian to resources/tools.md (runtime agent security)#14
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
Adds a new tool entry for Adrian to the repository’s resources/tools.md catalogue, extending the runtime monitoring/control coverage within the tools index using the local metadata format.
Changes:
- Adds a new
### Adriansection with standard metadata fields (type, producer, source, relevance, coverage, maturity, last checked, limitations). - Positions the entry between “Lakera Agent Breaker” and “Lakera Guard And Lakera Red”.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| - Source link: <https://github.com/secureagentics/Adrian>. | ||
| - Relevance to agentic execution security: Observes an agent's tool calls and reasoning traces at runtime and can intervene before an action executes, supporting detection and control of misaligned, out-of-remit, or injected behaviour during execution. | ||
| - Coverage: Runtime monitoring, reasoning-trace analysis, prompt-injection and out-of-remit action detection, in-flight intervention (audit or block mode), LangChain/LangGraph and OpenAI Agents SDK integration, self-hosted/offline deployment. | ||
| - Evidence quality and maturity level: Actively maintained open-source project (Apache-2.0); AARM-aligned. Suitable for evaluation and internal deployment; independent benchmarking still maturing. |
| - Coverage: Runtime monitoring, reasoning-trace analysis, prompt-injection and out-of-remit action detection, in-flight intervention (audit or block mode), LangChain/LangGraph and OpenAI Agents SDK integration, self-hosted/offline deployment. | ||
| - Evidence quality and maturity level: Actively maintained open-source project (Apache-2.0); AARM-aligned. Suitable for evaluation and internal deployment; independent benchmarking still maturing. | ||
| - Last checked: 2026-07-01. | ||
| - Limitations or caveats: A runtime detection-and-control layer, not a complete governance stack. Reasoning-trace analysis depends on the agent exposing its reasoning, and detection is a bounded signal rather than proof that the full execution system is secure. |
Owner
|
@gladstomych-sa Thank you for contributing Adrian, an open-source (Apache-2.0), AARM-aligned runtime security monitoring and control engine for AI agents. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds Adrian to
resources/tools.mdusing the repository metadata format (resource type, producer, source, relevance, coverage, maturity, last checked, limitations), with honest limitations noted.Adrian is an open-source (Apache-2.0), AARM-aligned runtime security monitoring and control engine for AI agents: it observes an agent's tool calls and reasoning traces at runtime and can intervene before an action executes (audit or block mode). Placed with the runtime controls, ahead of the commercial Lakera entry.
Disclosure: I work with Secure Agentics, the maintainers of Adrian. If you'd prefer this go through an issue-template suggestion first per CONTRIBUTING, happy to do that instead.