# SAALT > Documentation files for Large Language Models ## Documentation - [Introduction](/introduction.md): SAALT is an AI platform for building, running, and managing Agents. Start here — whether you use SAALT, build an App, call the API, or are an LLM reading these docs. - [Changelog](/changelog.md): Release notes for SAALT packages and APIs. - [Spaces](/user-guide/spaces.md): How Spaces work in SAALT — creating one, switching between them, and managing the Agents inside. - [Skills](/user-guide/skills.md): Teach an Agent a repeatable way of working — reusable instruction bundles with optional reference files, shared across a Space or scoped to a single Agent. - [Profile](/user-guide/profile.md): Managing your personal SAALT account — name, password, language preference, and account deletion. - [Memory](/user-guide/memory.md): How an Agent remembers durable facts about you across conversations — personal vs shared memories, when it's active, and how to manage or turn it off. - [Knowledge](/user-guide/knowledge.md): Managing Knowledge Documents for an Agent — uploading, tagging, monitoring embedding status, reviewing ingestion logs, and inspecting the RAPTOR section-summary index. - [Getting started](/user-guide/getting-started.md): A quick tour of SAALT for new users and Agent builders — what Spaces, Agents, Knowledge, and Apps are, and where to find them in the app. - [Embed a chat](/user-guide/embed.md): Place a SAALT Agent's chat on your own website — iframe, inline JavaScript, or floating chat bubble. Covers prerequisites, configuration, and customisation options. - [Code execution](/user-guide/code-execution.md): Let an Agent run code over your files in an isolated sandbox and hand back the result as a table, chart, or report — how to enable it, what it can reach, and how long it lasts. - [Chat](/user-guide/chat.md): Talking to an Agent in SAALT — sending messages, conversation history, feedback, incognito mode, picking a model, and what happens when an App runs. - [Apps](/user-guide/apps.md): Enabling and configuring Apps on an Agent — installed Apps, MCP servers, and how Apps surface in chat. - [Agents](/user-guide/agents.md): Creating and configuring an Agent in SAALT — model selection, system prompt, chat parameters, knowledge, tools, feedback, and history. - [Views](/apps/views.md): Apps can render admin and user views inside SAALT — iframed React pages that talk back to the platform through the Bridge. - [Tools](/apps/tools.md): Give an Agent new abilities by defining Tools your App exposes — plus optional React components to render their results in chat. - [Standalone apps](/apps/standalone.md): Full-page Apps that run outside any Agent or chat, rendered at a top-level /app/{id} route. - [Apps overview](/apps/overview.md): Apps extend SAALT with views, Knowledge, and Tools — or run as full-page standalone apps. Start here, then follow the track. - [Local development](/apps/local-development.md): Develop an App locally by exposing your dev server with a public URL and registering it in SAALT. - [Knowledge](/apps/knowledge.md): Implement the two knowledge-provider routes so your App can feed documents into an Agent's Knowledge base. - [Bridge](/apps/bridge.md): The TypeScript SDK Apps use to talk to SAALT — read/write config and data, call the platform LLM, manage files and Knowledge, and register Tools. - [Architecture](/apps/architecture.md): An App is a small microservice that exposes a few required routes; SAALT proxies to it and renders its views inside the platform. - [1.2 Migration guide](/apps/1-2-migration.md): Migrate an existing App to @open-agent-kit/bridge 1.2 — move your routes under the /app/{id}/ prefix so it can run alongside other installed Apps without collisions. - [Postman collection](/api/postman.md): A ready-made Postman collection for the SAALT Core REST API, so you can start making calls quickly. - [API overview](/api/overview.md): The SAALT REST API surface — base URLs, authentication, and a map of every endpoint group, linking to the full OpenAPI reference. - [OpenAI-compatible API](/api/openai-compatible.md): Call SAALT's configured models through an OpenAI-compatible endpoint with any OpenAI SDK.