# Rei - Docs

## Docs

- [Spatial Vision endpoint](https://docs.reilabs.org/POST /api/v1/vision/spatial.md): Run non-LLM spatial VQA and grounded object-relative pointing.
- [Agent Cloning](https://docs.reilabs.org/api-reference/agent-management/agent-cloning.md): Clone an existing Rei Agent using the user's secret token.
- [Agent Creation](https://docs.reilabs.org/api-reference/agent-management/agent-creation.md): Create a Rei Agent using the user's secret token.
- [Agent Deletion](https://docs.reilabs.org/api-reference/agent-management/agent-deletion.md): Delete a Rei Agent using the user's secret token.
- [Agent Update](https://docs.reilabs.org/api-reference/agent-management/agent-update.md): Update an existing Rei Agent using the user's secret token.
- [Get Reigent](https://docs.reilabs.org/api-reference/agent/get-reigent.md): Retrieve a Reigent Unit.
- [Get Reigent Unit's Tools](https://docs.reilabs.org/api-reference/agent/get-reigent-units-tools.md): Retrieve the tools available for a Reigent Unit.
- [Update Reigent Unit's Tools](https://docs.reilabs.org/api-reference/agent/update-reigent-units-tools.md): Update the activation status of a tool for a Reigent Unit.
- [Chat Completion](https://docs.reilabs.org/api-reference/chat/chat-completion.md): OpenAI-compatible chat completion. The request body follows the OpenAI Chat Completions API.
- [Chat completions (OpenAI-compatible)](https://docs.reilabs.org/api-reference/chat/chat-completions-openai-compatible.md): LLM-style compatibility route. Use only when you explicitly want the chat pipeline; the /api/v1/memory/* and /memz/* routes are the non-LLM memory/reasoning path. `session_id` is overwritten by the proxy with the agent ID.
- [Create Response](https://docs.reilabs.org/api-reference/chat/create-response.md): OpenAI-compatible response generation. The request body follows the OpenAI Responses API.
- [Clear domain](https://docs.reilabs.org/api-reference/domains/clear-domain.md)
- [Create domain](https://docs.reilabs.org/api-reference/domains/create-domain.md)
- [Domain Delete](https://docs.reilabs.org/api-reference/domains/domain-delete.md)
- [Domain feedback](https://docs.reilabs.org/api-reference/domains/domain-feedback.md)
- [Domain Policy Reset](https://docs.reilabs.org/api-reference/domains/domain-policy-reset.md)
- [Explain domain query](https://docs.reilabs.org/api-reference/domains/explain-domain-query.md): Returns schema, ranked hypotheses, supporting memories, missing evidence, predicted observations, and core Neuroadapt reasoning support.
- [Get a domain](https://docs.reilabs.org/api-reference/domains/get-a-domain.md)
- [Ingest domain event](https://docs.reilabs.org/api-reference/domains/ingest-domain-event.md)
- [List domains](https://docs.reilabs.org/api-reference/domains/list-domains.md)
- [Query domain](https://docs.reilabs.org/api-reference/domains/query-domain.md)
- [Update domain rules](https://docs.reilabs.org/api-reference/domains/update-domain-rules.md)
- [Update domain schema](https://docs.reilabs.org/api-reference/domains/update-domain-schema.md)
- [Clear session](https://docs.reilabs.org/api-reference/memory/clear-session.md)
- [Delete a memory](https://docs.reilabs.org/api-reference/memory/delete-a-memory.md)
- [Explain memory](https://docs.reilabs.org/api-reference/memory/explain-memory.md): Returns the structured non-LLM reasoning view: evidence, hypotheses, causal chain, reasoning edges, discovered connections, conflicts, and predicted/missing observations. `score` is a bounded ranking/support score for UI ordering. `confidence` is a capped mechanistic support score, not a calibrated…
- [List memories](https://docs.reilabs.org/api-reference/memory/list-memories.md)
- [Memory Batch Store](https://docs.reilabs.org/api-reference/memory/memory-batch-store.md)
- [Memory Correct](https://docs.reilabs.org/api-reference/memory/memory-correct.md)
- [Memory Prune](https://docs.reilabs.org/api-reference/memory/memory-prune.md)
- [Memory Query](https://docs.reilabs.org/api-reference/memory/memory-query.md)
- [Memory State Summary](https://docs.reilabs.org/api-reference/memory/memory-state-summary.md)
- [Search memory](https://docs.reilabs.org/api-reference/memory/search-memory.md): Returns ranked evidence without the full reasoning payload.
- [Session state](https://docs.reilabs.org/api-reference/memory/session-state.md): Returns the current session memory state without running a query.
- [Store interaction](https://docs.reilabs.org/api-reference/memory/store-interaction.md): Stores one user-facing memory item. `session_id` is overwritten by the proxy with the agent ID.
- [Admission Stats](https://docs.reilabs.org/api-reference/system/admission-stats.md)
- [Health check (liveness)](https://docs.reilabs.org/api-reference/system/health-check-liveness.md)
- [Health check (readiness)](https://docs.reilabs.org/api-reference/system/health-check-readiness.md)
- [Readyz](https://docs.reilabs.org/api-reference/system/readyz.md)
- [Service version](https://docs.reilabs.org/api-reference/system/service-version.md)
- [Choose an Adapt-1 workflow](https://docs.reilabs.org/docs/adapt-1/getting-started.md): Start from the result your application needs, then follow the shortest Adapt-1 workflow.
- [Adapt-1 foundations](https://docs.reilabs.org/docs/adapt-1/overview.md): A self-contained adaptive learning and reasoning substrate that forms, revises, and applies structure while it operates.
- [Core](https://docs.reilabs.org/docs/agentic-core/index.md): How Core combines declared interface semantics, live evidence, and revisable state to form and apply task structure.
- [Rei Chat API and SDK](https://docs.reilabs.org/docs/api-and-sdk/index.md): Integrate the conversational Rei Chat surface, manage Units, and call its inference APIs.
- [Integrate with existing agents](https://docs.reilabs.org/docs/api-and-sdk/integration-with-existing-agents.md): Connect a Rei Unit to an existing AI agent through function calling, with JavaScript, Python, and OpenAI examples.
- [Integrate with existing services](https://docs.reilabs.org/docs/api-and-sdk/integration-with-existing-services.md): Embed a Rei Unit in web services, webhooks, queues, databases, or containerized microservices.
- [Rei Chat quickstart](https://docs.reilabs.org/docs/api-and-sdk/quickstart.md): Authenticate, choose the correct Rei Chat base URL, and make your first API call.
- [SDK](https://docs.reilabs.org/docs/api-and-sdk/sdk.md): Install the Rei Core SDK, initialize a Unit client, and call common Rei Chat workflows from JavaScript or Python.
- [Building with Core](https://docs.reilabs.org/docs/application-usecases/index.md): Ways to connect Core to products, tools, and applications.
- [Brand assets](https://docs.reilabs.org/docs/brand-assets/index.md): Download official Rei logos, artwork, and character asset packages.
- [//hanabi-1](https://docs.reilabs.org/docs/catalog/hanabi-1.md): Explore Hanabi-1, a compact transformer architecture for financial time-series prediction and calibrated directional signals.
- [Catalog](https://docs.reilabs.org/docs/catalog/index.md)
- [Custom tools](https://docs.reilabs.org/docs/factory/capabilities/custom-tools.md): Expose application functions to a Rei Unit through function calling, with JavaScript and Python examples.
- [Additional Capability (Provided & Custom)](https://docs.reilabs.org/docs/factory/capabilities/index.md)
- [Research](https://docs.reilabs.org/docs/factory/capabilities/research.md): Ask a Rei Unit to research a topic, analyze the results, and return findings with traceable sources.
- [Rei Chat agent setup](https://docs.reilabs.org/docs/factory/index.md): Create and configure a Core-backed conversational agent, then extend it with built-in or custom capabilities.
- [Getting Started with Rei Chat](https://docs.reilabs.org/docs/factory/reigent-factory/reigent-factory.md): Create and configure a Core-backed conversational agent in the Rei Chat interface.
- [Rei Unit API integration guide](https://docs.reilabs.org/docs/guides/unit-api-guide.md): Connect OpenAI-compatible developer tools to Rei Unit with the shared endpoint, API key, and model configuration.
- [Ingest an adaptive observation](https://docs.reilabs.org/docs/neuroadapt/adapt-events.md): Update a domain's adaptive policy with one structured observation and return the current prediction.
- [Read the current adaptive prediction](https://docs.reilabs.org/docs/neuroadapt/adapt-predict.md): Return a domain's current structured adaptive prediction without adding another observation.
- [Reset adaptive policy state](https://docs.reilabs.org/docs/neuroadapt/adapt-reset.md): Start a new adaptive-policy state history or rebuild policy state from a known ordered observation record.
- [Configure an adaptive policy contract](https://docs.reilabs.org/docs/neuroadapt/adaptive-domains-structured-predictions.md): Map ordered observations into a Domain-scoped adaptive policy and consume its structured prediction.
- [Build domain-aware behavior](https://docs.reilabs.org/docs/neuroadapt/build-a-domain-aware-assistant.md): Define a Domain from the public task interface, then let live evidence determine episode-specific behavior.
- [Build continuity across calls](https://docs.reilabs.org/docs/neuroadapt/build-an-assistant-with-persistent-context.md): Preserve useful evidence and constraints so later Adapt-1 calls can reason with them.
- [Design a transition Domain](https://docs.reilabs.org/docs/neuroadapt/design-transition-domains.md): Map observable inputs and outcomes for structured transition learning, then verify event admission and support.
- [Errors and reliability](https://docs.reilabs.org/docs/neuroadapt/errors-and-reliability.md): Handle authentication, permanent client errors, transient gateway failures, and ambiguous stateful writes.
- [Verify feedback-driven adaptation](https://docs.reilabs.org/docs/neuroadapt/evaluate-adaptation.md): Confirm that scoped feedback changes the intended learned signal and later application behavior.
- [Explain a result](https://docs.reilabs.org/docs/neuroadapt/explain-and-audit-responses.md): Inspect evidence, support, conflicts, abstention, and learner state without changing Domain state.
- [Ways to use Adapt-1](https://docs.reilabs.org/docs/neuroadapt/goals.md): Compare Adapt-1 workflows by the structured result, continuity, feedback loop, or audit view your application needs.
- [Explore Domain learning patterns](https://docs.reilabs.org/docs/neuroadapt/learning-patterns-for-domains.md): Compare explored ways to organize observations, outcomes, feedback, and evaluation inside a Domain.
- [Learn from feedback and outcomes](https://docs.reilabs.org/docs/neuroadapt/make-behavior-improve-from-feedback.md): Bind observed outcomes to the decisions that produced them so later Adapt-1 results can improve.
- [Monitor adaptation in production](https://docs.reilabs.org/docs/neuroadapt/measure-online-adaptation.md): Track Adapt-1 inputs, results, application actions, outcomes, feedback, and learner-state changes over time.
- [Operate stateful and adaptive workflows](https://docs.reilabs.org/docs/neuroadapt/operational-behavior-and-retries.md): Keep ordered, stateful Adapt-1 workflows isolated, retryable, and auditable.
- [Adapt-1 API overview](https://docs.reilabs.org/docs/neuroadapt/overview.md): Use Core directly through structured APIs that retain, revise, and expose task-relevant state.
- [Adapt-1 quickstart](https://docs.reilabs.org/docs/neuroadapt/quickstart.md): Make a first direct Core call, then choose the Adapt-1 gateway that matches the required outcome.
- [Use a structured adaptive result](https://docs.reilabs.org/docs/neuroadapt/return-structured-adaptive-outputs.md): Update a documented adaptive policy from ordered observations and consume its current result directly in application code.
- [Run an inspectable stateful workflow](https://docs.reilabs.org/docs/neuroadapt/run-a-reproducible-goal-workflow.md): Define the state lifecycle and preserve an ordered record of Adapt-1 results and observable consequences.
- [Spatial Vision](https://docs.reilabs.org/docs/neuroadapt/spatial-vision.md): Use non-LLM spatial VQA and grounded pointing with explicit degradation checks.
- [Rei Chat conversational interface](https://docs.reilabs.org/docs/rei-chat/overview.md): A conversational demo surface where Core performs the reasoning and a language model articulates the result.
- [Ecosystem operations (Legacy)](https://docs.reilabs.org/docs/tokenomics/ecosystem-operations-and-business-model.md)
- [$REI](https://docs.reilabs.org/docs/tokenomics/index.md): The operational role of $REI in the ecosystem.
- [Welcome to Rei Labs](https://docs.reilabs.org/docs/welcome.md): Build with Core through Adapt-1 or Rei Chat, and explore the research behind adaptive intelligence.

## OpenAPI Specs

- [neuroadapt-openapi](https://docs.reilabs.org/neuroadapt-openapi.json)
- [openapi](https://docs.reilabs.org/openapi.json)