clearai-dsh

Overview of clearai-dsh

What it is

ClearAI is an ontology discovery and exploration platform built on two core concepts: a domain ontology and an epistemic loop. The domain ontology is the project's own vocabulary, knowledge entries established through the loop, and their graphs. The epistemic loop is the process of question → ontology → candidate hypotheses with predictions → test → evidence → bounded conclusion → ontology growth. Every edge in the knowledge graph is tested by evidence and independent evaluation, not by extraction or assertion.

Key features

• Domain ontology that grows as you research, including vocabulary, established entries with boundaries and evidence chains, ontology graph and entity graph.
• Epistemic loop that tracks what makes a conclusion trustworthy, with separate verdict, kept refuted hypotheses, and explicit open points.
• Conflict readings: contradictory conclusions surface automatically; the system reports them, and retracting or keeping is a human decision.
• Answers delivered per question in four parts: conclusion, basis, open points, and for you to decide.
• State derived from the session record with no second store; tools contain no field to declare a step complete.
• Prebuilt npm package with no build step and no allowBuilds prompt.

Use cases

Research projects that need to build a continuously growing, evidence-checked domain ontology. Use cases include any scenario where conclusions must be grounded in tested evidence, contradictions must be surfaced, and knowledge must be retrievable by concept across sessions.

Getting started

bashdsh plugin --profile web add [email protected]Or in the app: Plugins → Add plugin → [email protected]. Restart dsh web, then pick ClearAI in the preset picker at the top of a new session. Requirements: DSH ≥ 0.2.0-rc.2.

License and pricing

License: Apache-2.0. Pricing: open source (not stated otherwise).

Based on the project's public README and repository metadata.