Version updated for https://github.com/Snehgabani/aegis-kernel to version core@vv1.10.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Aegis is a deterministic safety verification tool that intercepts and analyzes AI agent tool calls, ensuring they comply with invariants by parsing SQL queries into ASTs, applying tautology detection, enforcing numeric bounds, and masking secrets. It operates in-process, typically under 1.5ms for single-statement queries, without external API calls or LLM dependencies.

Version updated for https://github.com/Snehgabani/aegis-kernel to version diagnostics@vv1.2.1. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Aegis is an open-source safety kernel that verifies AI agent tool calls against deterministic invariants before execution. It parses SQL into abstract syntax trees, applies tautology detection via constant folding, enforces numeric bounds, and masks secrets through salted token vaults. The core observation behind Aegis is that structural violations can be caught deterministically rather than probabilistically through AST analysis.