Assevra provides release evidence tooling for AI agents. It converts test runs into cryptographically signed, statistically defensible scorecards that can automatically gate releases. Built as a Python package with an MIT license, it supports LLM-as-judge evaluations, safety checks, and governance requirements for production AI systems.
assevra sits in PulseGate's LLM eval & observability category. It focuses on lacking statistically valid, tamper-proof evidence to confidently gate AI agent releases to production. It is built as an open-source project for AI engineers and platform teams. assevra is open source under the MIT license. It runs on the web, the command line, and API, and it can be self-hosted.
It is developed by Assevra, and it first shipped in 2026. The project is developed in the open on GitHub with 30 commits in the last 90 days. Among its 5 catalogued features are Signed Scorecards, Statistical Evaluation, and Release Gating. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match