# Opper

## Docs

- [Installation](https://docs.opper.ai/agents/installation.md): Install the unified opperai SDK for Python or TypeScript
- [Migration & legacy SDKs](https://docs.opper.ai/agents/migration.md): Coming from the standalone agent SDKs? Here's where to look
- [Agent SDK Overview](https://docs.opper.ai/agents/overview.md): Build AI agents with tools, streaming, multi-agent composition, and MCP integration
- [Conversation](https://docs.opper.ai/agents/patterns/conversation.md): Multi-turn stateful interactions with an agent
- [Hooks](https://docs.opper.ai/agents/patterns/hooks.md): Observe every lifecycle event during an agent run
- [MCP Integration](https://docs.opper.ai/agents/patterns/mcp.md): Connect to Model Context Protocol servers and use their tools
- [Multi-Agent](https://docs.opper.ai/agents/patterns/multi-agent.md): Compose specialists by exposing one agent as a tool to another
- [Streaming](https://docs.opper.ai/agents/patterns/streaming.md): Observe an agent's work in real time
- [Structured Output](https://docs.opper.ai/agents/patterns/structured-output.md): Return validated, typed data from an agent run
- [Tools](https://docs.opper.ai/agents/patterns/tools.md): Define functions an agent can call during its loop
- [Quickstart](https://docs.opper.ai/agents/quickstart.md): Install, set your API key, and run your first agent
- [Models](https://docs.opper.ai/capabilities/models.md): The Opper platform integrates with most LLM providers and models, with the ability to add custom models and aliases
- [Guard](https://docs.opper.ai/control-plane/guard.md): Protect your AI systems with safety guardrails and content filters.
- [Memory](https://docs.opper.ai/control-plane/memory.md): Store and retrieve custom knowledge for AI tasks
- [Observe](https://docs.opper.ai/control-plane/observe.md): Monitor, trace, and evaluate your AI system's behavior.
- [Route](https://docs.opper.ai/control-plane/route.md): Intelligently route requests across models and providers.
- [Steer](https://docs.opper.ai/control-plane/steer.md): Guide AI behavior through in-context learning and feedback loops
- [Migrating to v2 API](https://docs.opper.ai/guides/migration-to-v2.md): Guide to migrating code to use version 2 api
- [Agent lifecycle](https://docs.opper.ai/opperator/agent-lifecycle.md): Understanding agent lifecycle, initialization, and core methods
- [Agents.yaml reference](https://docs.opper.ai/opperator/agents-yaml-reference.md): Complete configuration reference for Opperator agents
- [Building your first agent](https://docs.opper.ai/opperator/building-your-first-agent.md)
- [CLI reference](https://docs.opper.ai/opperator/cli-reference.md): Complete reference for the Opperator CLI commands and flags.
- [Cloud deployment](https://docs.opper.ai/opperator/cloud-deployment.md): Deploy Opperator to the cloud for 24/7 agent availability
- [Commands and tools](https://docs.opper.ai/opperator/commands-and-tools.md): Understanding the difference between AgentTool and SlashCommand
- [Custom sidebars](https://docs.opper.ai/opperator/custom-sidebars.md): Display agent information and progress updates in the TUI sidebar
- [Sora video creator agent](https://docs.opper.ai/opperator/guides/generating-videos-with-sora.md): Build an Opperator agent to generate videos using OpenAI Sora API
- [How Opperator works](https://docs.opper.ai/opperator/how-opperator-works.md): Understanding Opperator's architecture and how agents work
- [Installation](https://docs.opper.ai/opperator/installation.md)
- [Lifecycle events](https://docs.opper.ai/opperator/lifecycle-events.md): React to conversation changes, agent activation, and lifecycle events
- [Overview](https://docs.opper.ai/opperator/overview.md)
- [State management](https://docs.opper.ai/opperator/state-management.md): Persist agent state across conversations, restarts, and configuration changes
- [System prompts](https://docs.opper.ai/opperator/system-prompts.md): Guide the LLM with dynamic agent state and capabilities
- [TUI reference](https://docs.opper.ai/opperator/tui-reference.md): Complete reference for keyboard shortcuts, navigation, and interactive features in Opperator.
- [About](https://docs.opper.ai/overview/about.md): Why Opper exists and how it works as a gateway and control plane for AI
- [Quickstart](https://docs.opper.ai/overview/getting-started.md): Start building with Opper in minutes
- [Integrations](https://docs.opper.ai/overview/integrations.md): Use Opper as an inference provider to AI agents, editors and CLIs
- [Chat Completions API](https://docs.opper.ai/v3-api-reference/compatibility/chat-completions.md): OpenAI-compatible chat completions endpoint. Supports streaming via the stream parameter.
- [Embeddings API](https://docs.opper.ai/v3-api-reference/compatibility/create-embeddings.md): OpenAI-compatible embeddings endpoint.
- [Interactions API](https://docs.opper.ai/v3-api-reference/compatibility/create-interaction.md): Google Interactions API compatible endpoint. Supports streaming via the stream parameter.
- [Messages API](https://docs.opper.ai/v3-api-reference/compatibility/create-message.md): Anthropic Messages API compatible endpoint. Supports streaming via the stream parameter.
- [Responses API](https://docs.opper.ai/v3-api-reference/compatibility/create-response.md): OpenAI Responses API compatible endpoint. Supports streaming via the stream parameter.
- [OpenResponses API](https://docs.opper.ai/v3-api-reference/compatibility/openresponses.md): OpenResponses-compatible endpoint with multi-provider support and opper: extension items.
- [Batch create examples](https://docs.opper.ai/v3-api-reference/examples/batch-create-examples.md): Upload multiple few-shot examples for a function.
- [Create example](https://docs.opper.ai/v3-api-reference/examples/create-example.md): Create a single few-shot example for a function.
- [Delete example](https://docs.opper.ai/v3-api-reference/examples/delete-example.md): Delete a single few-shot example by UUID.
- [List examples](https://docs.opper.ai/v3-api-reference/examples/list-examples.md): List few-shot examples for a function with optional tag filter.
- [Call function](https://docs.opper.ai/v3-api-reference/functions/call-function.md): Execute a function with the given input. If no cached script exists, one is generated automatically.
- [Call](https://docs.opper.ai/v3-api-reference/functions/call-function-by-name.md): Execute a function by name (passed in the request body). If no cached script exists, one is generated automatically.
- [Create realtime function](https://docs.opper.ai/v3-api-reference/functions/create-realtime-function.md): Generate a realtime voice agent function.
- [Delete function](https://docs.opper.ai/v3-api-reference/functions/delete-function.md): Delete a cached function.
- [Get function](https://docs.opper.ai/v3-api-reference/functions/get-function.md): Get details of a specific function including its script source.
- [Get revision](https://docs.opper.ai/v3-api-reference/functions/get-revision.md): Get a specific revision of a function.
- [List functions](https://docs.opper.ai/v3-api-reference/functions/list-functions.md): List all cached functions for the authenticated project.
- [List revisions](https://docs.opper.ai/v3-api-reference/functions/list-revisions.md): List all revisions of a function.
- [Realtime WebSocket](https://docs.opper.ai/v3-api-reference/functions/realtime-websocket.md): WebSocket endpoint for realtime voice agent communication. The client must send an HTTP Upgrade request; a successful connection returns 101 Switching Protocols. OpenAPI 3.1 does not natively support WebSocket, so this is documented descriptively.
- [Revert to revision](https://docs.opper.ai/v3-api-reference/functions/revert-to-revision.md): Revert a function to a previous revision.
- [Stream function](https://docs.opper.ai/v3-api-reference/functions/stream-function.md): Execute a function with SSE streaming output.
- [Stream](https://docs.opper.ai/v3-api-reference/functions/stream-function-by-name.md): Execute a function by name (passed in the request body) with SSE streaming output.
- [Update function](https://docs.opper.ai/v3-api-reference/functions/update-function.md): Update the source code of a function.
- [Delete generation](https://docs.opper.ai/v3-api-reference/generations/delete-generation.md): Delete a specific recorded generation.
- [Get generation](https://docs.opper.ai/v3-api-reference/generations/get-generation.md): Get a specific recorded generation by ID.
- [List generations](https://docs.opper.ai/v3-api-reference/generations/list-generations.md): List recorded HTTP request/response generations with pagination.
- [List models](https://docs.opper.ai/v3-api-reference/models/list-models.md): List all available models with their capabilities and parameters.
- [Roundtable](https://docs.opper.ai/v3-api-reference/roundtable/create-roundtable.md): Send a query to multiple models in parallel and combine results using a configurable resolution strategy (summary, fast, multiple_choice).
- [Create span](https://docs.opper.ai/v3-api-reference/spans/create-span.md): Create a new trace span.
- [Update span](https://docs.opper.ai/v3-api-reference/spans/update-span.md): Update an existing trace span.
- [Health check](https://docs.opper.ai/v3-api-reference/system/health-check.md): Returns server health status.
- [OpenAPI spec (JSON)](https://docs.opper.ai/v3-api-reference/system/openapi-spec-json.md): Returns the OpenAPI specification in JSON format.
- [OpenAPI spec (YAML)](https://docs.opper.ai/v3-api-reference/system/openapi-spec-yaml.md): Returns the OpenAPI specification in YAML format.
- [Web fetch](https://docs.opper.ai/v3-api-reference/tools/web-fetch.md): Fetch a URL and return its content as markdown.
- [Web search](https://docs.opper.ai/v3-api-reference/tools/web-search.md): Search the web and return results with title, URL, and snippet.

## OpenAPI Specs

- [openapi](https://docs.opper.ai/openapi.json)
- [openapi-v3](https://docs.opper.ai/openapi-v3.json)

## Optional

- [Cookbook](https://github.com/opper-ai/opper-cookbook)