OpenMerit

OpenMerit is being built to help applications make better inference decisions using evidence about their models, workloads, quality, cost, and latency.

Version 0.1.6 starts with visibility: the Inference Terminal gives you a local view of the inference your application declares and records. It is a starting point for OpenMerit, not the full product vision. This release brings the existing npm preview into the default installation.

Install and run

Requires Node.js 22.19 or newer. In your application's directory:

npm install -g openmerit
openmerit dash

The terminal opens in your browser while collection starts. It runs locally, bound to 127.0.0.1, and prints its URL. Keep the command running while using it; press Ctrl+C to stop. Pi and model-provider credentials are not required for the terminal.

You can also point it at a project explicitly:

openmerit dash /path/to/your/project

To update from an earlier release or openmerit@preview, run npm install -g openmerit, stop the old terminal process, and launch it again. To pin this release, use npm install -g openmerit@0.1.6. Remove it with npm uninstall -g openmerit.

What you can see today

• Models and services: application declarations from supported code and configuration, recorded provider connections, and supported project-linked runtime inventory.
• Inference activity: requests, tokens, latency, costs, and agent/task identifiers where supported application logs or explicit exports provide them.
• Code and configuration evidence: file-and-line references, indexing progress, unresolved references, and source coverage.
• Compute and deployments: explicitly linked hosts, model residency, and supplied hardware or capacity measurements, with their freshness and scope shown.

The terminal keeps declarations, runtime inventory, and recorded usage separate. Missing evidence stays unknown. Code alone cannot reconstruct request history, usage, costs, or running agents. Discovery supports specific source formats and syntax; it is not complete coverage of every application or provider.

Local and read-only

The terminal reads supported project files, logs, exports, and authorized loopback runtime inventory endpoints. It does not execute your application code, call models, route inference, run evaluations, or change your model configuration. It does not retain prompts, responses, or credential values in its snapshots. Closing it leaves your workloads running.

Repository indexing runs in the background and reuses unchanged metadata in memory. Request history and runtime readers have documented limits. The local API can be reached by other processes or users on the same machine, so treat its model names, endpoint identifiers, and file paths as project data.

Useful commands

openmerit dash --no-open       # Print the local URL without opening a browser
openmerit dash --json          # Print one collected snapshot, then exit
openmerit dash --diagnostics   # Print repository-index coverage counts only
openmerit dash --demo          # Explore fictional data without local collection
openmerit dash --help

See the Inference Terminal guide for supported sources, setup, options, data handling, and limitations. You can also explore the hosted fictional sample without installing anything; it does not inspect your environment.

Optional Pi integration

The package also retains the Pi extension, reusable coordinator, and protocol. These are separate from the terminal. Pi can gather application evidence and carry out user-authorized model comparisons and changes; OpenMerit coordinates typed outcomes and validates the returned structure and frontier evidence.

For Pi 0.87 with a supported model provider configured:

pi install npm:openmerit

Then use /openmerit doctor inside Pi. See Pi setup, commands, budgets and permissions, and current limitations. The terminal itself does not perform this evaluation or routing work.

The existing openmerit/core, openmerit/protocol, and openmerit/pi exports remain available for integrations.

Documentation

• Inference Terminal
• Security and data handling
• Project files and logs
• Architecture and integrations
• Testing and validation
• Changelog

The bundled Inference Terminal guide follows this package version. The separately deployed documentation website may reflect a different release.