Skip to content

Add Adrian to resources/tools.md (runtime agent security)#14

Merged
natnew merged 2 commits into
natnew:mainfrom
gladstomych-sa:add-adrian-tools
Jul 24, 2026
Merged

Add Adrian to resources/tools.md (runtime agent security)#14
natnew merged 2 commits into
natnew:mainfrom
gladstomych-sa:add-adrian-tools

Conversation

@gladstomych-sa

Copy link
Copy Markdown
Contributor

Adds Adrian to resources/tools.md using 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.

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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 ### Adrian section 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.

Comment thread resources/tools.md
- 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.
Comment thread resources/tools.md
- 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.
@natnew
natnew merged commit c042cb0 into natnew:main Jul 24, 2026
3 checks passed
@natnew

natnew commented Jul 24, 2026

Copy link
Copy Markdown
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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants