Evarness provides tools to prove an AI agent harness before it interacts with real data. It generates canonical traces, enforces invariant contracts, creates portable proof bundles, and supports offline verification. Built for developers who need deterministic guarantees and provenance for autonomous agents.
In the LLM eval & observability space, evarness takes a focused approach. It focuses on proving an AI agent's behavior and invariants before granting it access to real data or production systems. It is built as an open-source project for developers. evarness is open source under the Apache-2.0 license. The product ships for the command line.
evarness first shipped in 2026. Development happens publicly on GitHub with 99 commits in the last 90 days. Key capabilities include Canonical Traces, Invariant Contracts, and Portable Proofs. It exposes integrations via a public API.
Latest indexed changes and source events
Other apps tracked under the same category.
