PulseGate's liveness check found it on 8 Sep 2026; it is registered on GitHub and has been in the index since 26 Aug 2026. How this is checked
Agent Eval Planner is a Ruby command-line tool that reads an agent contract and produces a structured evaluation pack. It generates attack prompts with pass/fail criteria, executable JSONL cases, and remediation guidance for prompt, policy-gate, and evaluator layers.
Agent Eval Planner sits in PulseGate's Agent evaluation & testing category. It focuses on testing AI agents for scope violations, prompt injection, unsafe tool use, and other guardrail failures. Agent Eval Planner is an open-source project aimed at AI engineering and application security teams. The project is open source (MIT). It ships for the web and the command line, and it can be self-hosted.
Behind Agent Eval Planner is Saulo Filho, and it first shipped in 2026. The project is developed in the open on GitHub with 4 commits in the last 90 days. Among its 10 catalogued features are contract analysis, attack prompts, and pass/fail criteria.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do