nexart.io

    NexArt Product Stack

    Four pieces. They compose. You adopt the ones you need.

    What NexArt is

    • NexArt is verifiable execution infrastructure for AI systems. It produces tamper-evident records of what your AI actually ran.
    • A lightweight integration captures inputs, outputs, and execution context at runtime and seals them into a single record locally.
    • An independent attestation node certifies each record so that no single party controls the proof.
    • Certification adds a third-party signature. The record can then be verified by anyone without trusting the operator.
    • verify.nexart.io is a public verification surface. Anyone can check a record there with no account, no login, and no dependency on NexArt.
    • A Project Bundle groups multiple execution steps into one verifiable artifact, covering entire workflows or agent sessions.
    • NexArt proves what executed. It does not prove that the output is correct or that the model behaved well.

    NexArt ships four products. They compose: each one adds value on its own, and they work together when combined. Start with the certification engine; add context, workflow helpers, and field verification as your needs grow.

    Without these pieces, every AI execution in your stack is a transient event. If a decision is questioned later, logs are not proof. Most systems rely on internal records that cannot be verified externally. The record you need does not exist until you create it.

    @nexart/ai-execution

    The certification engine

    What it isThe core SDK. Drop it into any Node.js codebase and start producing Certified Execution Records in under five minutes. Handles sealing, verification, attestation, project bundles, and redaction.
    What it unlocks
    • Every AI call your product makes can produce a tamper-evident record.
    • Records verify offline, with no NexArt service dependency.
    • Optional attestation by a NexArt node adds an independent third-party signature.
    Adoption shapeOne function call per model inference. No middleware, no proxy, no infrastructure change.
    When to add: Day one. This is the entry point.
    See how the certification engine works
    @nexart/signals

    Context capture

    What it isA small, framework-agnostic SDK that captures the evidence that fed a model run: the tools the model called, the documents it retrieved, the upstream decisions, the inputs from your pipeline.
    What it unlocks
    • CERs go from "model said X" to "model said X, having seen exactly Y, Z, and W."
    • The upstream evidence is hashed into the same certificateHash, so the whole chain is one tamper-evident unit.
    Adoption shapeAdd a few lines around your tools and retrievals. Pass the resulting signals[] to your CER call.
    When to add: As soon as your product has tool use, retrieval, or any non-trivial upstream pipeline. Often immediately after ai-execution.
    See how context capture works
    @nexart/agent-kit

    Workflow helpers

    What it isConvenience layer for multi-step workflows. wrapTool per tool, startWorkflow per session, project bundles per run.
    What it unlocks
    • One verifiable artifact per agent run, instead of scattered individual records.
    • Automatic project bundle registration with a NexArt node in a single call.
    • Project bundles record which orchestrator was used (LangChain, n8n, custom) so verifiers can identify the source.
    Adoption shapeWrap your tools and pipeline steps. The CERs and project bundle are emitted automatically.
    When to add: When your product runs multi-step agents and you want one record per session.
    See how workflow helpers works
    @nexart/cli

    Command-line verifier

    What it isA nexart command-line tool. Verify, certify, project-verify, with file or pipe input and machine-readable JSON output.
    What it unlocks
    • CI gates: fail the pipeline if any CER from this build does not verify.
    • Auditor self-service: hand over a folder of bundles plus a CLI binary; auditors verify on their own machines, no NexArt account.
    • Ops scripts: bulk-verify, batch-certify, project-verify across an export.
    • Customer self-service: ship CERs to a customer plus a one-line install command they can verify with.
    Adoption shapenpm install -g @nexart/cli. Use in CI, ops scripts, or hand to compliance.
    When to add: As soon as you have CERs you want to verify outside of your application code path.
    See how command-line verifier works

    First-party integrations

    NexArt ships integration patterns for the most common ways teams build with AI today.

    • LangChain: every chain run becomes a verifiable record. Multi-step chains become project bundles.
    • n8n: make every LLM step in your business workflows defensible.

    How adoption typically works

    Most teams start with @nexart/ai-execution and add the other pieces as their needs grow. See the adoption journey for a stage-by-stage guide, or read how NexArt works for the end-to-end flow.

    Most teams assume their existing instrumentation is sufficient until they are challenged. This gap exists even in well-instrumented systems.

    View developer quickstart when you are ready to implement.

    As more decisions are automated, the window to instrument them narrows. Retroactively certifying past executions is not possible. The evidence starts when you start capturing it.

    Ready to start?

    See the 4-stage adoption path with time-to-value estimates for each step.

    Start with NexArt →

    Related