LOCAL-FIRST · BLIND · REPRODUCIBLE

A structured desktop workspace for AI Remote Viewing research.

AI RV Harness combines blind RV sessions, ordinary Conversations, structured Training, controlled Research, separate AI roles, target management, evidence-preserving Reveal flows, and reproducible evaluation tools.

Latest public release View source

Current public line: v0.7.13 Branch: main

WHAT IT IS

One environment, several deliberately separated roles.

Conversations and blind sessions

Keep ordinary Conversations separate from controlled RV Sessions while preserving the boundary between Viewer evidence and Reveal information.

Structured Training

Use bundled and user-provided targets, resumable checkpoints, Viewer self-review, Viewer Notes, and optional judging.

Controlled Research

Build locked, blinded studies with reproducible designs, frozen evidence, judging, unblinding, and experiment statistics.

AI Center

Keep AI Monitor history, AI identities, Viewer Notes, and versioned Viewer Learning resources in distinct profile-wide tools.

Local-first records

The desktop application stores project state locally with SQLite while remote providers are used only when selected.

Evidence boundaries

Viewer, Monitor, Judge, Research, and post-Reveal material are handled through explicit workflow boundaries rather than one blended chat.

CURRENT PUBLIC UI

v0.7.13 on the main branch

These screenshots show the current AI RV Harness interface after the transition to v0.7.13. The gallery reflects the current navigation and public project presentation.

AI RV Harness Home screen showing the welcome dashboard, recent workspace, recent RV sessions, and local-first status — Home · welcome dashboard, recent workspaces, and recent RV sessions

Profiles screen showing multiple profiles, separate Conversation Workspaces, and RV Workspaces — Profiles · identities with separate Conversation and RV workspaces

RV Sessions screen showing Automatic RV configuration with single session and AI Monitor options — RV Sessions · automatic and monitored blind session setup

AI Training screen with Viewer model, Use Viewer Notes, RV Lite variant, and recent training runs — Training · RV Lite training, Viewer Notes, and resumable runs

Research Tests screen showing seven blinded research templates including Viewer Notes Impact — Research · blinded research templates, including Viewer Notes Impact

AI Center · Viewer Learning, Field Guide, and Viewer Notes

PROJECT BOUNDARY

A research workflow, not a claim of proof.

AI RV Harness does not claim that Remote Viewing has been scientifically proven, that a particular model possesses anomalous perception, or that model-generated material is accurate.

The project provides controlled procedures, records, and evaluation tools. Interpretation remains the responsibility of the user and researcher.

PROJECT RESOURCES

Source, releases, documentation, and licensing.

RepositorySource code and project history Latest releaseStable public download location WikiUser and development documentation MIT LicenseApplication source license