# AutoSage

> Build, deploy, and integrate AutoSage agents — the multi-tenant RAG and agent platform.

## Docs

- [Configuring an agent](https://docs.autosage.ai/agents/configuring.md): Set the goal, instructions, model, and the tools, skills, and integrations your agent can use.
- [Delegation & callable agents](https://docs.autosage.ai/agents/delegation.md): Let an agent ask other specialized agents for answers outside its own knowledge base.
- [Deploying & versioning](https://docs.autosage.ai/agents/deploying.md): How deploys create versions, how the knowledge base stays fixed, and how in-flight runs stay stable.
- [Agents](https://docs.autosage.ai/agents/overview.md): Saved, versioned configurations that run consistently every time — interactively, via API, or on a schedule.
- [Running & run history](https://docs.autosage.ai/agents/running.md): Run an agent interactively or via API, follow it live, and review every run it produces.
- [Scheduling](https://docs.autosage.ai/agents/scheduling.md): Run an agent automatically on a cadence — daily, weekly, monthly, or a custom schedule.
- [Long conversations](https://docs.autosage.ai/chat/long-conversations.md): How AutoSage keeps lengthy chats fast, coherent, and true to the details that matter.
- [Quick and Deep modes](https://docs.autosage.ai/chat/modes.md): Two answering modes — a fast single-pass answer or thorough multi-step reasoning — chosen per message.
- [Chat overview](https://docs.autosage.ai/chat/overview.md): How AutoSage turns a question into a grounded, cited answer against your knowledge base.
- [Sharing a chat](https://docs.autosage.ai/chat/sharing.md): Keep a chat private, share it with your organization, or make it public with a read-only link.
- [Streaming responses](https://docs.autosage.ai/chat/streaming.md): Follow live progress, sources, tool activity, and final answer content as a response runs.
- [Agents](https://docs.autosage.ai/developers/api/agents.md): Create, version, schedule, run, copy, and archive agents.
- [API keys](https://docs.autosage.ai/developers/api/api-keys.md): Create, inspect, and revoke environment-bound API keys.
- [Artifacts](https://docs.autosage.ai/developers/api/artifacts.md): Create, edit, version, archive, and publish generated documents and pages.
- [Billing & usage](https://docs.autosage.ai/developers/api/billing.md): Inspect credit balances and usage, then fund organizations and tenants.
- [Chats](https://docs.autosage.ai/developers/api/chats.md): Create grounded conversations, send messages, stream responses, and manage chat access.
- [Connectors](https://docs.autosage.ai/developers/api/connectors.md): Discover connected-app integrations and manage account connections.
- [Documents](https://docs.autosage.ai/developers/api/documents.md): Upload, inspect, download, reprocess, and remove knowledge-base documents.
- [Environments](https://docs.autosage.ai/developers/api/environments.md): Isolate dev, staging, and production workloads inside an organization.
- [Invites](https://docs.autosage.ai/developers/api/invites.md): Inspect and accept organization invitations.
- [Knowledge Bases](https://docs.autosage.ai/developers/api/knowledge-bases.md): Create and manage knowledge bases, their prompt settings, external A2A agents, and memory.
- [MCP Servers](https://docs.autosage.ai/developers/api/mcp.md): Register MCP tool servers, inspect discovered tools, configure OAuth, and remove registrations.
- [Organizations](https://docs.autosage.ai/developers/api/organizations.md): Create organizations and manage members, roles, and invitations.
- [API Reference](https://docs.autosage.ai/developers/api/overview.md): Base URL, conventions, errors, and the resource groups that make up the AutoSage API.
- [Shared Chats](https://docs.autosage.ai/developers/api/shared-chats.md): Read the safe, read-only transcript for an organization or public chat.
- [Skills](https://docs.autosage.ai/developers/api/skills.md): Create reusable agent procedures and install skills from the catalog.
- [Tenants](https://docs.autosage.ai/developers/api/tenants.md): Provision isolated customer resources, quotas, credits, and durable memory.
- [Current caller](https://docs.autosage.ai/developers/api/users.md): Discover the organizations, environments, tenants, and knowledge bases available to the current caller.
- [Voice](https://docs.autosage.ai/developers/api/voice.md): Open a real-time voice conversation over WebSocket.
- [Authentication](https://docs.autosage.ai/developers/authentication.md): How to authenticate to the AutoSage API with API keys and sessions.
- [Access & scopes](https://docs.autosage.ai/developers/concepts/access-scopes.md): Understand API-key scopes, resource access lists, and organization roles.
- [Prompt assembly](https://docs.autosage.ai/developers/concepts/prompt-assembly.md): How AutoSage layers answering behavior, operator prompts, tools, memory, and conversation context.
- [Agent runtime](https://docs.autosage.ai/developers/concepts/runtime.md): How Quick chats, Deep chats, and agents use the shared grounded-answer runtime.
- [Tenancy](https://docs.autosage.ai/developers/concepts/tenancy.md): Design secure multi-customer integrations with environments, tenants, knowledge bases, and external subjects.
- [Integration best practices](https://docs.autosage.ai/developers/guides/best-practices.md): A production checklist for secure, isolated, reliable, and cost-aware AutoSage integrations.
- [Build an agent](https://docs.autosage.ai/developers/guides/build-an-agent.md): Create, configure, deploy, and run a knowledge-grounded agent end to end with the API.
- [Chat & streaming](https://docs.autosage.ai/developers/guides/chat-and-stream.md): Consume the streaming chat endpoint over Server-Sent Events, or use the non-streaming alternative.
- [Upload documents](https://docs.autosage.ai/developers/guides/upload-documents.md): Upload files through a presigned URL and wait for them to become searchable.
- [Introduction](https://docs.autosage.ai/developers/introduction.md): The AutoSage API — architecture, conventions, and how to integrate.
- [Agent lifecycle](https://docs.autosage.ai/developers/lifecycles/agent-lifecycle.md): How an agent goes from creation to deployment, execution, scheduling, and termination.
- [Chat lifecycle](https://docs.autosage.ai/developers/lifecycles/chat-lifecycle.md): How a chat is created, how messages are grounded and streamed, and how conversations stay within context.
- [Document ingestion](https://docs.autosage.ai/developers/lifecycles/ingestion.md): Upload documents, understand the processing pipeline, and track status through to indexing.
- [Memory system](https://docs.autosage.ai/developers/lifecycles/memory-system.md): How conversation context, compaction, and durable memory are scoped and used.
- [RAG lifecycle](https://docs.autosage.ai/developers/lifecycles/rag.md): How AutoSage retrieves private knowledge-base content and returns cited answers.
- [Quickstart](https://docs.autosage.ai/developers/quickstart.md): Provision a knowledge base, upload a document, and run a grounded chat in minutes.
- [Rate limits & credits](https://docs.autosage.ai/developers/rate-limits.md): How request rate limits and credit consumption work, and how to build a resilient integration around them.
- [Build an agent in two minutes](https://docs.autosage.ai/guides/agent-in-two-minutes.md): Create version 1, run it, and continue its agent chat with the shortest valid workflow.
- [Chat vs. agent runs](https://docs.autosage.ai/guides/chat-vs-agent-runs.md): Understand the difference between chats, agents, runs, and agent-run chats.
- [KB prompts vs. agents](https://docs.autosage.ai/guides/kb-prompts-vs-agents.md): Decide whether behavior belongs in knowledge-base prompts, a saved agent, or both.
- [Share context between knowledge bases](https://docs.autosage.ai/guides/share-context-between-kbs.md): Compose isolated knowledge bases through agent delegation without merging their documents.
- [Welcome to AutoSage](https://docs.autosage.ai/index.md): Build grounded AI agents on top of your own knowledge, data, and tools.
- [Agent sharing](https://docs.autosage.ai/knowledge-bases/agent-sharing.md): Let agents delegate to agents in other knowledge bases — without sharing raw documents.
- [Documents & ingestion](https://docs.autosage.ai/knowledge-bases/documents.md): Upload files, ingest URLs, and crawl websites — then let AutoSage make them searchable.
- [Memory modes](https://docs.autosage.ai/knowledge-bases/memory-modes.md): Choose whether and how a knowledge base remembers durable facts across conversations.
- [Knowledge bases](https://docs.autosage.ai/knowledge-bases/overview.md): The workspace that ties your documents, data, prompts, and agents together.
- [Prompts](https://docs.autosage.ai/knowledge-bases/prompts.md): Shape the assistant's voice and rules with a persona, instructions, and custom prompts.
- [Memory commands](https://docs.autosage.ai/memory/commands.md): Store facts to durable memory conversationally, right from the chat.
- [Set up durable memory](https://docs.autosage.ai/memory/durable-memory.md): Enable durable memory and tune how the assistant captures and recalls facts across conversations.
- [Manage memories](https://docs.autosage.ai/memory/managing.md): View, search, and delete durable memories, and explore what the assistant has remembered.
- [Memory](https://docs.autosage.ai/memory/overview.md): How AutoSage remembers context — within a conversation and durably across conversations.
- [Core concepts](https://docs.autosage.ai/product/concepts.md): The building blocks of AutoSage and how they relate to each other.
- [Invitations](https://docs.autosage.ai/teams/invites.md): Invite people to your organization by email and assign their role.
- [Members & roles](https://docs.autosage.ai/teams/members-roles.md): The roles in an AutoSage organization and exactly what each one can do.
- [Teams overview](https://docs.autosage.ai/teams/overview.md): How organizations, environments, and tenants fit together when you manage your AutoSage account.