# Vitna | Documentation > The record of what AI infrastructure costs, and the engine that decides when a change is worth making. Every read endpoint is public and needs no key. ## Machine-readable discovery - [Full documentation corpus (llms-full.txt)](https://vitna.ai/llms-full.txt): All documentation pages concatenated into one Markdown file. - [Site OpenAPI 3.1 (openapi.json)](https://vitna.ai/openapi.json): Machine-readable OpenAPI schema for /api/v1 plus links to Vitna Web, Search, and Unblocker APIs. - [Web APIs OpenAPI 3.1 (web.vitna.ai/openapi.json)](https://web.vitna.ai/openapi.json): Read, batch, extract, crawl, monitors (diffMode), /v1/diff, /v1/parse, /v1/verify, /v1/entity, /v1/grid, /v1/ir, /v1/firehose/events, /v1/pdf (pageRanges, scale, printBackground), and 16 official sources. - [Search API OpenAPI 3.1 (search.vitna.ai/openapi.json)](https://search.vitna.ai/openapi.json): Web index search, similar pages, SERP retrieval, and grounded research. - [Unblocker API OpenAPI 3.1 (unblock.vitna.ai/openapi.json)](https://unblock.vitna.ai/openapi.json): Adaptive Chromium and Camoufox page rendering. - [Unified MCP Directory (.well-known/mcp.json)](https://vitna.ai/.well-known/mcp.json): Keyless Market MCP (/api/v1/mcp) and 25-tool Bearer Web API MCP (web.vitna.ai/v1/mcp). - [Agent Card (.well-known/agent-card.json)](https://vitna.ai/.well-known/agent-card.json): A2A capability card across all Vitna platform interfaces. - [Interactive Web API Playground (/apis)](https://vitna.ai/apis): Try live requests, copy cURL/Node/Python snippets, and connect MCP agents. - [Vitna MCP Landing Page (/mcp)](https://vitna.ai/mcp): Live verified market tools and Streamable HTTP client setup. ## Start here - [Cite a figure](https://vitna.ai/docs/citing-a-figure.md): Every price on every board carries a permanent, dated citation. This page is what that citation is, how to get one, and how long it will keep resolving, which is a promise rather than an intention and is written here because it has to exist before the first citation is minted rather than after. - [One key for the hosted APIs](https://vitna.ai/docs/one-key.md): An org holds one key for Vitna's hosted APIs. Search, the Web APIs and the Unblocker each accept it as `Authorization: Bearer vitna_key_...`, and each checks it with vitna.ai, where the key lives as a hash beside the org's other keys. During the beta an operator mints it. - [Quickstart](https://vitna.ai/docs/quickstart.md): Every read endpoint on `vitna.ai` is public and needs no key. There is no signup, no token, and no rate limit to negotiate. If you can reach the host you can read the record. - [Vitna documentation](https://vitna.ai/docs/README.md): The written surface of Vitna: what the record holds, what the words mean, and how to read it over HTTP without a key. - [Verify a figure yourself](https://vitna.ai/docs/verify-a-figure.md): The whole claim of this record is that you do not have to trust it. This page is that claim carried out, end to end, with nothing taken on faith. ## Concepts - [The model](https://vitna.ai/docs/concepts/overview.md): Vitna is a record of what AI infrastructure costs, and an engine that decides when a change to a production stack is worth making. Two systems, one repository, one database with a schema each. - [Attestation](https://vitna.ai/docs/concepts/attestation.md): Each day's observations hashed into a Merkle root and signed with Ed25519, so that an edit made afterwards has to contradict something already published. - [Component class](https://vitna.ai/docs/concepts/component-class.md): The top-level division of the market. A class is a kind of thing you buy, with one unit it is ultimately bought in. - [Workloads, triggers and decisions](https://vitna.ai/docs/concepts/decision.md): Aperture, the engine half. Witness records what things cost; Aperture decides whether a change is worth making, and records that nobody has acted on it yet. - [Dimension](https://vitna.ai/docs/concepts/dimension.md): What a price is charged by. A sku does not have "a price"; it has a price per dimension, and most skus carry several. - [Evidence](https://vitna.ai/docs/concepts/evidence.md): The archived document a figure was read from, addressed by the sha256 of its bytes. - [Market event](https://vitna.ai/docs/concepts/market-event.md): A published statement that something happened in the market. The rows the market log renders and the feed carries. - [Observation](https://vitna.ai/docs/concepts/observation.md): One figure, parsed out of one document, at one moment. The atom of the record. - [Price period](https://vitna.ai/docs/concepts/price-period.md): One stretch during which a price did not move. The history unit. - [Provider term](https://vitna.ai/docs/concepts/provider-term.md): What a provider published about **how** it handles the work, beside what it charges for it. - [Reference rate](https://vitna.ai/docs/concepts/reference-rate.md): One number per product per day: the median list price among the providers publishing one, by a rule with no judgement in it. - [Sku](https://vitna.ai/docs/concepts/sku.md): The unit Vitna prices: one thing, sold by one provider, that you could buy. - [Source](https://vitna.ai/docs/concepts/source.md): One fetchable document, and the adapter that knows how to read it. ## API v1 - [API v1](https://vitna.ai/docs/api/v1/overview.md): JSON over HTTP. Reading the public record takes no key, no signup and no quota. Base URL `https://vitna.ai/api/v1`. ### Prices - [Catalog, benchmarks and capability](https://vitna.ai/docs/api/v1/prices/catalog.md): Mirrored model metadata, Hugging Face weight licences, route speed measurements, multi-seller endpoint offers, openly licensed benchmark boards, and Vitna's IRT capability scale. Kept separate from `/api/v1/markets` so `meta.provenance` always distinguishes mirrored third-party data from Witness first-party provider observations. - [Historical data exports](https://vitna.ai/docs/api/v1/prices/exports.md): Paginated bulk export of Witness first-party datasets (`price-periods`, `observations`, `rates`, `events`, and `provider-terms`) in JSON, JSONL (`application/x-ndjson`), or CSV (`text/csv`) for Deploy and Enterprise organisations. - [LiteLLM cost map](https://vitna.ai/docs/api/v1/prices/litellm-cost-map.md): Witness's attested language-model and retrieval rates rendered in the JSON dictionary format LiteLLM's `--model_cost_map_url` (`LITELLM_MODEL_COST_MAP_URL`) loads directly, with a `vitna` provenance block on every entry. - [Markets](https://vitna.ai/docs/api/v1/prices/markets.md): Every component class Vitna prices, with counts and freshness. The index of the record. - [Providers](https://vitna.ai/docs/api/v1/prices/providers.md): Every company whose own pages Vitna reads a price from, with the pages read, the markets each sells into, and any registered products no longer on the board. - [Quote Check](https://vitna.ai/docs/api/v1/prices/quote-check.md): Evaluate a vendor quote in memory against historical published list prices, peer spreads, and reference rates. - [Reference rates](https://vitna.ai/docs/api/v1/prices/rates.md): The published reference rates: one number per product per day, the median list price among providers publishing one. - [Sku history](https://vitna.ai/docs/api/v1/prices/sku-history.md): Every price period recorded for one sku. - [Snapshot](https://vitna.ai/docs/api/v1/prices/snapshot.md): All ten board documents in exactly the shape `app/data/` holds them: the model board, the GPU board, and the eight meter boards. - [Spreads](https://vitna.ai/docs/api/v1/prices/spreads.md): What several providers charge for the same product, cheapest first, with the percentage between the low and the high. - [Tape](https://vitna.ai/docs/api/v1/prices/tape.md): Every current price in one class, flattened to one row per priced cell. - [Provider terms](https://vitna.ai/docs/api/v1/prices/terms.md): What providers have published on their own domains about how they handle customer work: retention, training use, processing regions, and bring-your-own-key support. The read surface for provider terms. ### The log - [Events](https://vitna.ai/docs/api/v1/log/events.md): The market log as data. Curated and detected rows merged, newest first. - [Feed](https://vitna.ai/docs/api/v1/log/feed.md): JSON Feed 1.1. The market log plus the triggers that fired and the decisions the engine proposed, in something a reader, a bot or a chat channel can subscribe to. ### Verification - [Attestations](https://vitna.ai/docs/api/v1/verification/attestations.md): The signed daily Merkle roots, newest first, with everything a check needs. - [Citations](https://vitna.ai/docs/api/v1/verification/citations.md): One observation in the three paste-ready citation forms `/cite/{id}` prints (`reference`, `footnote`, `schedule`), alongside the figure's provenance fields and signed-day status. See citing a figure for the permanence rules that govern these URLs. - [Evidence](https://vitna.ai/docs/api/v1/verification/evidence.md): The record of one archived document, and behind a token, the document itself. - [Signing keys](https://vitna.ai/docs/api/v1/verification/keys.md): Every key the record acknowledges, what each one is for, whether it has been retired, and how much it provably signed. - [Observation proof](https://vitna.ai/docs/api/v1/verification/proof.md): The path from one observation up to a signed root. The other half of the attestation. ### The engine - [Collecting a signed artifact](https://vitna.ai/docs/api/v1/engine/artifacts.md): `GET /api/v1/artifacts` lists what has been signed for your organisation, and `GET /api/v1/artifacts/{id}` hands over the bytes, exactly as they were signed. - [Stateless audit attestation pack](https://vitna.ai/docs/api/v1/engine/audit-pack.md): Verify a `vitna.audit-pack.v1` document across all six cryptographic and governance layers, or assemble an inline audit pack from a `vitna.stackfile.v1` payload in memory with no API key and zero retention. - [Stateless stack decision check](https://vitna.ai/docs/api/v1/engine/decide.md): Evaluate an inline workload, candidate model list and evaluation measurements against live Witness prices and provider compliance terms in memory, with no API key and zero retention. - [Decision pack](https://vitna.ai/docs/api/v1/engine/decision-pack.md): One accepted or recorded decision as a standalone, signed audit pack: the decision, the exact price periods and evidence it read, the observation leaves with their Merkle hashes, and the canonical digest of the whole, so the pack can be verified offline without the record. - [Model Context Protocol (MCP)](https://vitna.ai/docs/api/v1/engine/mcp.md): Keyless Streamable HTTP MCP endpoint (`2025-03-26` and `2024-11-05`) exposing ten read-only and zero-retention tools over Vitna's first-party Witness market record, provider compliance terms, three-provenance SKU capabilities, cryptographic citations, stack decision engine, rollout watchdog, compound pipeline analyzer, and offline audit pack verifier. - [Headless artifact signing requests](https://vitna.ai/docs/api/v1/engine/org-artifact-requests.md): Queue an asynchronous request for the isolated signer to rebuild and Ed25519-sign your organisation's standing routing policy or environment config, and poll until the artifact settles. - [Organisation audit attestation pack](https://vitna.ai/docs/api/v1/engine/org-audit-pack.md): Export a read-only `vitna.audit-pack.v1` procurement, FinOps, and model-governance attestation pack across an authenticated organisation's registered workloads, standing decisions, signed policy, and attested Witness prices. - [Workload counterfactual cost](https://vitna.ai/docs/api/v1/engine/org-counterfactual.md): Compute what a recorded usage window of one of your organisation's workloads would have cost at historical Witness list prices had it run on another SKU. - [CI evaluation evidence](https://vitna.ai/docs/api/v1/engine/org-evidence.md): Record evaluation measurements from CI pipelines and read back historical measurements for your organisation's workloads, with built-in normalization for Promptfoo, Braintrust and UK AISI Inspect AI outputs. - [Organisation dependency and deprecation exposure](https://vitna.ai/docs/api/v1/engine/org-exposure.md): Read your organisation's live workload-to-SKU-to-provider dependency graph, provider blast-radius concentration, stale standing decisions and upcoming model deprecations as structured JSON. - [Your organisation's feed](https://vitna.ai/docs/api/v1/engine/org-feed.md): The triggers that fired on your organisation's workloads and the decisions the engine proposed for them, newest first, as a feed a reader or a chat channel can subscribe to. It is private: the address is the permission, and an owner of the organisation gets it from the console. - [Organisation API keys](https://vitna.ai/docs/api/v1/engine/org-keys.md): List active and revoked organisation API keys without exposing key hashes, and soft-revoke compromised or retired keys with an audit reason. - [Organisation members](https://vitna.ai/docs/api/v1/engine/org-members.md): List active organisation members, add or re-admit GitHub accounts on any plan, and soft-remove members with last-owner protection. - [Organisation compound pipeline](https://vitna.ai/docs/api/v1/engine/org-pipeline.md): Inspect the cross-layer Bill of Materials, bottlenecks, decision-ready switches, and eligible class-peer exploratory levers across an authenticated organisation's registered workloads. - [Organisation Stackfile](https://vitna.ai/docs/api/v1/engine/org-stackfile.md): Export your organisation's live register as a canonical `vitna.stackfile.v1` JSON document, preview a deterministic reconciliation plan (`dryRun: true`), or apply declarative register updates over HTTP. - [Organisation rollout watchdog](https://vitna.ai/docs/api/v1/engine/org-watchdog.md): Inspect standing-decision drift, shadow rule promotion readiness, and routed canary health across an authenticated organisation's active workloads. - [Policy drift webhooks](https://vitna.ai/docs/api/v1/engine/org-webhooks.md): Register, test and soft-disable HMAC-SHA256 signed webhook endpoints for policy drift, newly signed policy bundles and fired price watches on Deploy and agreement organisations. - [Organisation workloads](https://vitna.ai/docs/api/v1/engine/org-workloads.md): List, create, edit and transition workloads in your organisation's register over HTTP, including reversible pausing and permanent archiving that free active workload slots without erasing decision history. - [Stateless compound pipeline analysis](https://vitna.ai/docs/api/v1/engine/pipeline.md): Evaluate a multi-stage, multi-class AI pipeline Bill of Materials, per-run trace attribution, compound reliability, and cross-layer spend optimization in memory with no API key and zero retention. - [Proposals](https://vitna.ai/docs/api/v1/engine/proposals.md): The decision register: what the engine proposed, what a person ruled, and the exact rows each brief was derived from. - [Stateless invoice reconciliation](https://vitna.ai/docs/api/v1/engine/reconcile.md): Reconcile a usage window and optional stated vendor invoice lines against historical Witness list-price periods in memory, deriving exact list-cost bounds and implied enterprise discounts with zero retention. - [Relay spreads and Anchor manifests](https://vitna.ai/docs/api/v1/engine/relay-anchor.md): Keyless, ETag-cached registry feeds consumed by `vitna-relay` for wholesale cloud arbitrage and by `vitna-anchor` for verified 4KB DMA local checkpoints. - [Router challenge](https://vitna.ai/docs/api/v1/engine/router-challenge.md): Evaluate in memory whether handing model selection to a dynamic router (`openrouter/auto`, `martian/model-router`, `notdiamond/custom-router`, `routellm/mf`, or a custom router) beats naming a fixed SKU, with zero retention. The HTTP surface for Router Challenge (#72). - [Pushing usage](https://vitna.ai/docs/api/v1/engine/usage.md): The one write route this API mounts, and the only route a machine authenticates to. A runtime pushes what its own ledger says served each lane on a day that has ended, and each batch lands as readings on `/console`. - [Stateless rollout watchdog](https://vitna.ai/docs/api/v1/engine/watchdog.md): Evaluate standing-decision drift, shadow rule promotion readiness, and routed canary health in memory against Witness list prices, provider compliance terms, and three-provenance SKU capabilities, with no API key and zero retention. - [Watches](https://vitna.ai/docs/api/v1/engine/watches.md): What each workload is watching, and what has already fired. ### Status - [Health](https://vitna.ai/docs/api/v1/status/health.md): Whether this instance is up, and what it found when it reached for the database. - [Source health](https://vitna.ai/docs/api/v1/status/sources.md): Every source Vitna reads, and whether it is still answering. ## Routing - [Routing](https://vitna.ai/docs/routing/overview.md): How an accepted decision becomes a value a machine loads, and how the record finds out whether the change actually took. - [Rendering a policy for a gateway you already run](https://vitna.ai/docs/routing/adapters.md): A signed policy is a document a Vitna runtime executes. An adapter renders that same document as the configuration of a gateway you run instead, so one accepted decision configures whatever is already in your request path rather than asking you to adopt something new. - [Audit and procurement attestation packs](https://vitna.ai/docs/routing/audit-packs.md): Bundle an organisation's declarative Stackfile, standing routing decisions, signed runtime policy envelope, CI policy lock, RFC 6962 Witness price observation Merkle proofs, provider compliance terms, three-provenance SKU capabilities, rollout watchdog status, and compound pipeline Bill of Materials into one self-contained, offline-verifiable `vitna.audit-pack.v1` file. - [Three-provenance capability eligibility](https://vitna.ai/docs/routing/capabilities.md): Capabilities and runtime speed constraints narrow which candidates may serve a workload before cost per successful unit is weighed, and each constraint is bound to the provenance class that can honestly answer it. - [Emitting a routing config](https://vitna.ai/docs/routing/config.md): `aperture:config` renders an organisation's accepted decisions as a signed environment fragment. - [Connected accounts](https://vitna.ai/docs/routing/connected-accounts.md): An org connects its OpenRouter account to Vitna from `/console`, by OAuth PKCE. Vitna is never given a provider API key, and there is no field anywhere on this site that would accept one. - [Composing the register from the console](https://vitna.ai/docs/routing/console-composing.md): An owner of an org can enter a workload, put a sku in play, record a measurement and arm a watch at `/console`, instead of running the commands at a prompt on the box. - [Ruling from the console](https://vitna.ai/docs/routing/console-ruling.md): An owner of an org can accept or refuse an open proposal at `/console`, instead of running `aperture:accept` at a prompt on the box. - [Delivery targets](https://vitna.ai/docs/routing/delivery.md): Where a workload's accepted decision gets applied. Without one, a decision is only readable; with one, it is emittable. - [Fallback chains](https://vitna.ai/docs/routing/fallbacks.md): What may serve a lane when the model a decision named cannot. - [Running the hosted router](https://vitna.ai/docs/routing/hosted.md): `router:start` serves an OpenAI-compatible endpoint for several organisations at once, resolving each request against that organisation's own signed policy and paying for it with that organisation's own delegated OpenRouter key. - [Model ids](https://vitna.ai/docs/routing/model-ids.md): Three names exist for one model, and only two of them are the registry's. - [Did the decision do what it said](https://vitna.ai/docs/routing/outcome.md): A decision predicts. An imported usage export observes. This is the two of them side by side, which the record could always answer and never had to. - [Multi-class unit profiles and compound pipelines](https://vitna.ai/docs/routing/pipelines.md): Evaluate end-to-end AI workflows that fan out across multiple component classes, attribute runtime `x-vitna-run` trace volume back to each stage, and separate decision-ready migrations from exploratory class-peer levers. - [Emitting a routing policy](https://vitna.ai/docs/routing/policy.md): `aperture:policy` renders an organisation's accepted decisions as a signed policy document, which is what a Vitna runtime loads and resolves requests against. - [Router Challenge (#72)](https://vitna.ai/docs/routing/router-challenge.md): A router executes a routing policy per request. Vitna determines whether handing the choice to a router beats naming a model. - [Vitna router](https://vitna.ai/docs/routing/router.md): **Built on 2026-08-31, ahead of the preconditions this page sets out, on the owner's instruction.** The software exists: `npm run router:start` runs a multi-tenant router serving C1, and Running the hosted router is how. What does not exist is the product. Vitna operates no traffic for anybody, the three preconditions in `RUNTIME.md` phase R5 are still unmet, and this page remains the design to hand a reviewer rather than a description of a service somebody can buy. - [Rules within a lane](https://vitna.ai/docs/routing/rules.md): The per-request question, answered without an oracle: a declared predicate on an observable request attribute, routing to a named sku, shadow first. - [Rotating the seller, not the model](https://vitna.ai/docs/routing/sellers.md): A lane may name several hosts of the same weights and let a request go to the cheapest one that is up, without a new decision, because nobody decided to serve a different model. - [Signing an artifact without an operator](https://vitna.ai/docs/routing/signing.md): `aperture:sign` answers a queue of asks for signed artifacts, rebuilding each one from the record rather than signing what it was handed, so that a config or a policy can reach a customer without somebody standing at a prompt. - [Declarative Stackfile and CI policy lock](https://vitna.ai/docs/routing/stackfile.md): Check your organisation's workload register into git as `vitna.stack.json` (`vitna.stackfile.v1`), preview and apply register changes deterministically, and gate deployments in CI with `vitna-runtime-lock` and `vitna.lock.json`. - [Importing usage](https://vitna.ai/docs/routing/usage-import.md): `aperture:usage:import` reads a consumer's own usage export back into the record, so it can say what actually served a workload. - [Verifying a routing config](https://vitna.ai/docs/routing/verifying.md): Checking a file you were handed, without needing the database or the key that made it. - [Rollout and decision watchdog](https://vitna.ai/docs/routing/watchdog.md): Decision-oriented observability over live workloads and active lane rules: whether current prices, compliance terms, three-provenance capabilities, and runtime telemetry still support the standing decision, and where each `shadow` or `route` rule stands on the canary ladder. ## CLI - [The CLI](https://vitna.ai/docs/cli/overview.md): Everything an operator does to the record is a command, run from a checkout with the environment sourced. There is no admin UI, and that is a property of the design rather than a gap. - [Access commands](https://vitna.ai/docs/cli/access.md): Which orgs exist, who may read them at `/console`, and how a session is opened or revoked. - [npm run db:generate, npm run db:migrate](https://vitna.ai/docs/cli/database.md): Generating a migration from the schema and applying it, forward only, with the grants that carry the record's rules kept narrow. - [npm run event:add](https://vitna.ai/docs/cli/event-add.md): Add one curated market event. - [Push keys](https://vitna.ai/docs/cli/keys.md): Who may land a reading over the network, per org, minted and revoked at the prompt. The web process authenticates against these and cannot mint one. With console keys on, an owner can revoke one from the console, and can mint a platform key there through a separate minter (below). - [The standalone scripts](https://vitna.ai/docs/cli/scripts.md): The mirrors that write `app/data/`, the reconcilers that run behind them, and the rest of what is run with `node` rather than through npm. ### Witness - [npm run witness:attest](https://vitna.ai/docs/cli/witness/attest.md): Hash a day's observations into a Merkle root and sign it. - [npm run witness:collect](https://vitna.ai/docs/cli/witness/collect.md): One collector pass: fetch every enabled source, parse it, archive it, and write what changed. - [npm run witness:rates](https://vitna.ai/docs/cli/witness/rates.md): Publish yesterday's reference rates. - [npm run witness:rebuild-periods](https://vitna.ai/docs/cli/witness/rebuild-periods.md): Replay every observation into price periods. - [npm run witness:seed](https://vitna.ai/docs/cli/witness/seed.md): The registry: classes, providers, sources, dimensions, skus, and the curated market log. - [Recording a provider term](https://vitna.ai/docs/cli/witness/terms.md): Entering, by hand, what a provider published about how it handles the work: retention, training use, processing regions, whether a key you hold is accepted. Each reading is taken from a page on the provider's own domain. ### Skus and discovery - [npm run sku:candidates](https://vitna.ai/docs/cli/skus/candidates.md): The priced rows the collector saw that the registry does not track. - [npm run sku:link](https://vitna.ai/docs/cli/skus/link.md): Close a candidate against a sku the registry already holds. - [npm run sku:promote](https://vitna.ai/docs/cli/skus/promote.md): Register a candidate as a sku. - [npm run sku:reject](https://vitna.ai/docs/cli/skus/reject.md): Rule a candidate out. ### Aperture - [Audit attestation pack CLI](https://vitna.ai/docs/cli/aperture/audit-pack.md): Export, sign, and verify self-contained `vitna.audit-pack.v1` procurement, FinOps, and model-governance attestation packs from the register, from an offline Stackfile, or in an air-gapped CI runner. - [How much of a bill the record can price](https://vitna.ai/docs/cli/aperture/bill.md): One window of somebody's spend, bucketed by whether the record holds a figure for it. - [What it would have cost somewhere else](https://vitna.ai/docs/cli/aperture/counterfactual.md): One window of a workload, priced on a sku that did not serve it. - [Deciding](https://vitna.ai/docs/cli/aperture/decide.md): Running the engine, and ruling on what it proposes. - [Candidates and evidence](https://vitna.ai/docs/cli/aperture/evidence.md): Putting a sku in play, and recording what was measured about it. - [Compound pipeline CLI](https://vitna.ai/docs/cli/aperture/pipeline.md): Compute a multi-stage, multi-class AI pipeline Bill of Materials, attribute empirical `x-vitna-run` trace fan-out from a runtime ledger, discover eligible lower-cost Witness class peers, and enforce per-run or monthly spend budgets in CI. - [Your own infrastructure](https://vitna.ai/docs/cli/aperture/private.md): Registering something this organisation runs that no provider publishes a price for, and entering what it costs. - [Seeding and notification](https://vitna.ai/docs/cli/aperture/seed-notify.md): Loading the engine's reference data, and draining the outbox into the feed that stands in for email. - [Trigger commands](https://vitna.ai/docs/cli/aperture/triggers.md): Arming a watch on the record, and seeing what has fired. - [Rollout and decision watchdog CLI](https://vitna.ai/docs/cli/aperture/watchdog.md): Evaluate standing-decision drift, shadow rule promotion readiness, and routed canary health across an organisation's active workloads or offline against a checked-in Stackfile and runtime ledger. - [Workload commands](https://vitna.ai/docs/cli/aperture/workloads.md): Entering and correcting the things you run. ## Operations - [Operations](https://vitna.ai/docs/operations/overview.md): How the site is served, deployed, collected and backed up. One box, one Node process, no orchestration. - [Backups](https://vitna.ai/docs/operations/backups.md): A nightly unit dumps the database, keeps a fortnight locally, and mirrors both the dumps and the evidence tree off-box. - [Self-service checkout](https://vitna.ai/docs/operations/checkout.md): How somebody becomes a customer without anybody at Vitna doing anything, and what the box needs configured before they can. - [The collector](https://vitna.ai/docs/operations/collector.md): A oneshot unit fired hourly with jitter, running one collector pass out of the deployed checkout. - [Deploys](https://vitna.ai/docs/operations/deploys.md): Push-based. The box never talks to GitHub. - [Rotating a signing key](https://vitna.ai/docs/operations/key-rotation.md): Replacing the key that signs customers' policies without refusing a single running runtime, and what a compromise needs instead. - [Rolling back](https://vitna.ai/docs/operations/rolling-back.md): Most failures roll themselves back. One kind needs a person. - [Verifying a deploy](https://vitna.ai/docs/operations/verifying-a-deploy.md): A push that exits zero is not a deploy. Three checks say which commit is live. ## Search - [Vitna Search](https://vitna.ai/docs/search/overview.md): Private beta. A separate search API for agents with independent Google/Bing SERP retrieval and Vitna's own crawler and web index. SERP requests return actual search-engine organic listings; indexed search and cited research use successfully indexed pages. It includes a browser interface, dedicated client keys, and shared request limits. The private-key beta is hosted at `https://search.vitna.ai`, with an API reference at `/docs`. Its product page and a playground are at `/search` on vitna.ai. Keys are issued by invitation, requested at vitna.ai/start. Customer signup and search billing are not enabled. - [Run the general web beta](https://vitna.ai/docs/search/general-web.md): Vitna Search can grow its own index across public websites, keep a durable crawl queue, and serve authenticated searches without a paid search provider. This is a bounded beta with limited coverage. The API is deployed at `https://search.vitna.ai` on a reused Virginia OVH server, with private R2 backups. No additional OVH instance was purchased. - [Grounding check](https://vitna.ai/docs/search/grounding.md): `platform/search/grounding.mjs` decides, segment by segment, whether an answer a model wrote from Vitna Search evidence is supported by the verbatim passages it cites. It is deterministic and lexical: it uses no model and no network, and it checks that what a sentence states occurs in the cited passages, not what the sentence means. - [Vitna Search Vertical Indexes](https://vitna.ai/docs/search/indexes.md): Vitna Search exposes specialized vertical corpora alongside the default `web` index through a single `index` field on `/v1/search`, `/v1/similar`, and `/v1/extract`: - [Migrate Bright Data and Live/Hybrid clients](https://vitna.ai/docs/search/live-engine.md): Vitna retrieves actual Google and Bing organic SERPs through its own transport and parser at `POST /v1/serp`, with a URL-based compatibility path at `POST /request`. The former Bright Data search adapter has been removed. Native indexed search and cited research remain separate capabilities. This page keeps its existing URL to help older clients migrate. - [Run a focused search index](https://vitna.ai/docs/search/self-hosted.md): Vitna can crawl selected public AI documentation, keep an independent keyword index, and serve it through the search API. An OVHcloud Public Cloud instance can run the service and crawler; Cloudflare R2 can hold standalone snapshots. The deployment files are prepared locally. No cloud resources, DNS records, R2 uploads, or credit spending have been created by this implementation. For cross-site discovery, persistent crawl budgets, API quotas, and the Virginia deployment package, use the general web beta. - [Google and Bing SERP retrieval](https://vitna.ai/docs/search/serp.md): Vitna's SERP API retrieves actual Google or Bing search result pages through Vitna's own transport and parser. It returns parsed organic and rich SERP features (or the fetched HTML) without calling Bright Data, supporting web, news, images, videos, and shopping verticals alongside SerpApi-compatible query aliases and output shapes. ## Web APIs - [Vitna Web APIs](https://vitna.ai/docs/web/overview.md): Hosted pilot at `https://web.vitna.ai` (OpenAPI at `/openapi.json`, MCP manifest at `/.well-known/mcp.json`, Agent Card at `/.well-known/agent-card.json`), with keys by invitation while public signup is closed. Turn public web pages into Markdown, structured JSON, crawl datasets, change alerts (`diffMode`), structural redlines (`/v1/diff`), parsed PDF/Office documents (`/v1/parse`), company dossiers (`/v1/entity`, `/v1/ir`), cited enrichment matrices (`/v1/grid`), claim verifications (`/v1/verify`), structured registry firehose events (`/v1/firehose/events`), screenshots, and printable PDFs (`pageRanges`, `scale`, `printBackground`), alongside 16 official data sources (`courtlistener`, SEC EDGAR, Federal Register, CISA KEV, FRED, FINRA, Treasury, NY Fed, BLS, and more) and 25 MCP tools (`/v1/mcp`). Native retrieval, lexical reranking, observed field extraction, and bounded research analysis run in the Vitna process by default. The product page and request playground are at `/apis`. The native customer account console is at `/apis/account`. ## Unblocker - [Vitna Unblocker](https://vitna.ai/docs/unblocker/overview.md): Hosted alpha. Vitna Unblocker is a browser-backed web access API: send a public HTTPS URL and receive the rendered HTML, the readable text and the links, or a validated JSON feed, with a receipt of every attempt. It is hosted at https://unblock.vitna.ai, takes an alpha key issued on request, and is relayed at https://vitna.ai/api/v1/unblock. Billing is not active. ## runtime - [The runtime](https://vitna.ai/docs/runtime/overview.md): An optional process that applies an accepted decision per request, on your own infrastructure. It is the second way to consume a decision, beside the config a consumer loads into a variable it already reads. - [The response cache](https://vitna.ai/docs/runtime/cache.md): A repeat of a deterministic request, answered from memory rather than by a provider. Off unless you turn it on, and never a saving. - [Putting a coding harness on a lane](https://vitna.ai/docs/runtime/harness.md): *An operator note.* The launcher is not in the published package: it runs from a checkout of Vitna's private repository, as does the local lane it looks for. Outside Vitna, point the harness at a runtime you installed yourself, with the base URL Serving a lane gives. - [Installing the runtime](https://vitna.ai/docs/runtime/installing.md): Getting from nothing to a served lane, on your laptop, your box, or your own cloud account. - [The ledger](https://vitna.ai/docs/runtime/ledger.md): One line per request, appended to the file `VITNA_LEDGER` names. It is yours, on your disk, and it moves only when you move it. - [A lane on your own machine](https://vitna.ai/docs/runtime/local.md): An operator note: one command from a workload in the register to a runtime answering on the same machine, run from a checkout of Vitna's repository, which is private. It is for Vitna's own operators. Outside Vitna, the runtime is installed from npm with a policy the console signs, which is Installing the runtime. - [Measuring your unit profile](https://vitna.ai/docs/runtime/profile.md): A unit profile is how many tokens one call on a lane actually consumes. It is the bridge between a published price and a cost per unit: input tokens per unit, multiplied by a price per million input tokens, is what one unit of that work costs at list. - [Pushing the ledger](https://vitna.ai/docs/runtime/pushing.md): Sending a runtime's closed days to Vitna, deliberately, as a command of its own. - [Redaction](https://vitna.ai/docs/runtime/redaction.md): Known credential formats lifted out of a request before it leaves your machine, and put back into the answer, streams included. Off unless you turn it on, for the lanes you name or for traffic that names a model, except in Relay, which turns it on for you. - [Relay: the runtime with no policy](https://vitna.ai/docs/runtime/relay.md): Relay is `vitna-runtime` started with no policy at all, for a developer who wants a local gateway today and a register later, or never. Every request is served as exactly the model it names, on your own keys, and every one is a line in a ledger on your disk. - [Per-request auto-routing with vitna-route](https://vitna.ai/docs/runtime/route.md): `vitna-route` selects the model and reasoning effort for each request deterministically from structural counts of the prompt, preserves prompt caches across multi-turn conversations, and requires an Aperture-signed policy pinned by `VITNA_PUBLIC_KEY` before routing live traffic. - [Serving a lane](https://vitna.ai/docs/runtime/serving.md): Starting a runtime against a signed policy, the two request dialects it answers, and how a lane reaches its model, fails over and stays inside the provider allowlist.