# Licklider agent-readable documentation

> Run the public verifier directly or through local MCP, decide when a verification call applies, and interpret the returned evidence from one versioned documentation set.

nomue is Licklider's agent-callable scientific verification product. It moves important scientific decisions and numerical checks out of the research model and into a separate, inspectable capability.

## Available now

- Anyone can install the public @licklider/nomue-verifier package from npm and run nomue verify locally to check a conforming Release 1 Record for independent two-group continuous outcomes under the two-sided Welch two-sample t procedure. It recomputes the covered numerical quantities and returns a machine-readable report of the scoped checks without calling a nomue server after installation.
- [Run the verifier](https://www.licklider.ai/docs/record-verification.md)
- [Use nomue from an MCP client](https://www.licklider.ai/docs/mcp-verification.md): exact local stdio package, configuration, tool-selection boundary, result contract, and independent replay
- [Inspect the exact CLI](https://www.licklider.ai/docs/cli-reference.md)
- [Use machine-readable examples](https://www.licklider.ai/docs/examples.json)
- Release 1 publishes source code together with public fixtures, a signed source archive, checksums, a snapshot manifest, detached signatures, and the public release key.

## Product and roadmap

- Approved recipients can submit data and required scientific declarations for a supported Welch calculation, or submit a claimed result with structured evidence for checking, through authenticated MCP and HTTP. The service returns scoped outcomes, reasons, evidence, and next actions.
- Use the npm-published Release 1 verifier, the local stdio MCP server, the Protocol, and their machine-readable documentation today. The agent-facing Welch capability is now available in limited Release 1 to approved recipients through authenticated MCP and HTTP interfaces; public self-registration is not available. The hosted capability does not yet emit public Records for replay through the local verifier.
- [Making verification results more useful to research agents](https://www.licklider.ai/engineering/making-verification-results-useful-to-agents/): Since limited Release 1, nomue development has expanded candidate calculation range, improved completion of difficult calculations, clarified what was checked, and added historical-result handling. Development update: integrated candidates and completed internal milestones are not a new hosted release or an expansion of public verifier support.
- Record assembly and emission has entered development. The adopted initial invite-free release plan targets Welch, independent multi-group and paired two-condition capabilities; delivery and scientific activation remain future gates, with no promised date.
- [Hosted limited Release 1](https://www.licklider.ai/news/nomue-welch-limited-release-1/)
- The exact @licklider/nomue-verifier-mcp@0.2.0-rc.1 release candidate is public on npm and in the official MCP Registry as nomue Record Verifier. It exposes the method-neutral verify_nomue_record tool over local stdio; the current supported scientific scope remains Release 1 Welch Record verification. It delegates to @licklider/nomue-verifier@0.2.1-rc.1 and has passing package-path CI across Linux, macOS, and Windows. It requires no account, API key, environment variable, or Licklider-hosted service. The first npx launch may download npm dependencies; after installation, verification runs locally. This release candidate supports stdio only: it is not a hosted HTTP endpoint and does not add paired-t, Wilcoxon, Mann–Whitney, method selection, raw-sample calculation, or an overall scientific verdict.
- The Release 2 paired-t candidate now has an independently reviewed formal decision-readiness packet. It assembles the D1–D6 decision ledger, numerical and execution evidence, structural candidates, review dispositions, Release 1 safeguards, and the required coupled landing order. The Steward decisions, authoritative issuance, support activation, and release remain open.
- Release 3 public discussion is open on independent groups and multiple comparisons. The proposal makes design, comparison families, result meaning, and error-control questions explicit across 49 catalogued procedures. Its evidence scope is limited to supplied originals; method adoption and numerical support remain separate decisions.
- [Release 3 public discussion](https://github.com/licklider-ai/nomue-protocol/issues/274); [scope and evidence](https://www.licklider.ai/news/nomue-protocol-release-3-public-discussion/)
- Release 4 public discussion is open for a balanced two-by-two fixed-factor proposal. Its unissued numerical, report and controlled-execution candidate has reached independently reviewed final readiness, without establishing Protocol support. A separate amendment discussion covers strict binary64 comparison and completed indeterminate results; it changes neither the current verifier nor the original RFC clock.
- [Release 4 public discussion](https://github.com/licklider-ai/nomue-protocol/issues/261); [scope and evidence](https://www.licklider.ai/news/nomue-protocol-release-4-public-discussion/)
- Release 5 public discussion is open on a common evidence view for declared study design and selection timing across analysis families. The proposal covers versioned mappings, timing declarations, explicit limits on what a passing check means, and a shared report view. All three candidate families require separately accepted successors; no new verification capability is available.
- [Release 5 public discussion](https://github.com/licklider-ai/nomue-protocol/issues/346); [scope and evidence](https://www.licklider.ai/news/nomue-protocol-release-5-public-discussion/)
- The evaluation program examines nomue through decision quality, cost and time, and concrete cases, with explicit comparisons and linked reproduction materials. Current evidence includes two developer-led preprints on constructed Welch workflows and selected cases from the whole-submission study. Results remain specific to their tasks, models and configurations; public archives support reproducing disclosed results, not independently rerunning the private nomue implementations.
- Welch is the first working, publicly checkable vertical slice, not the product boundary. The adopted product sequence expands both the platform beneath each call and the scientific methods available through it.
- Planned method families: Independent multi-group; Paired two-group; Repeated measures; Factorial and interaction; Nonlinear and dose response; Nonparametric rank-based; Categorical outcomes; Correlation and linear models; Survival time-to-event; Count outcomes.
- [Full product roadmap](https://www.licklider.ai/roadmap/)

## Research finding for call selection

- A statistical method name is not a verification contract. A useful guarantee also depends on the comparison family, error criterion, assumptions, sidedness, balance conditions, and exact procedure variant.
- This source-bounded finding does not add or change Protocol support.

## Documentation

- [What a verification call is](https://www.licklider.ai/docs/verification-call.md): A shared model for asking a separate capability to check one bounded part of AI-assisted research.
- [Verify a Release 1 nomue Record](https://www.licklider.ai/docs/record-verification.md): When and how to use the public local verifier for the exact Release 1 Public Draft support target.
- [Use nomue Record verification over MCP](https://www.licklider.ai/docs/mcp-verification.md): Install the public local stdio server, decide when its method-neutral Record tool applies, and replay the current Release 1 Welch result with the independent verifier.
- [nomue CLI reference](https://www.licklider.ai/docs/cli-reference.md): The exact public command surface shipped by @licklider/nomue-verifier 0.2.1-rc.1, including current help and version boundaries.
- [Decision vocabulary](https://www.licklider.ai/docs/decision-vocabulary.md): Keep execution, clarification, unsupported scope, refusal, failed checks, and unasserted scientific validity separate.
- [Examples for agents and implementers](https://www.licklider.ai/docs/examples.md): Runnable verifier examples and selection examples showing execute, clarify, unsupported, and bounded interpretation behavior.
- [Current capability and boundaries](https://www.licklider.ai/docs/limits.md): What can be used now, what comes next, how the platform expands, and how to interpret a successful result.

## Machine-readable examples

- [Examples JSON](https://www.licklider.ai/docs/examples.json): normalized executable and call-selection examples