Cauval is an MIT-licensed Python package for building sovereign agents with deterministic output through causal grounding. It combines knowledge graphs, retrieval-augmented generation, SPARQL, and verification techniques for developers creating more auditable AI systems.
In the Frameworks & runtimes space, cauval takes a focused approach. It focuses on building AI agents that produce verifiable, deterministic outputs instead of relying solely on unconstrained language-model generation. cauval is an open-source project aimed at AI and Python developers building verifiable agent systems. cauval is open source under the MIT license. cauval is available on the command line and API, and it can be self-hosted.
It is developed by Brighk, and it first shipped in 2026. The project is developed in the open on GitHub with 21 commits in the last 90 days. Key capabilities include causal reasoning, knowledge graphs, and RAG grounding. 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