# Motus

## Docs

- [Motus Cloud](https://docs.motus.lithosai.com/cloud/overview.md): The managed platform that runs your agents. Same code as motus serve, reachable over HTTPS, with observability built in.
- [Cloud Sandbox](https://docs.motus.lithosai.com/cloud/sandbox.md): Where your deployed agent's shell commands actually run. One sandbox per session, managed for you.
- [ReActAgent](https://docs.motus.lithosai.com/concepts/agents.md): The reasoning-and-acting loop: give the model tools, and let it decide what to do next.
- [Memory](https://docs.motus.lithosai.com/concepts/memory.md): Manage conversation context with automatic compaction for long-running agents.
- [Model Clients](https://docs.motus.lithosai.com/concepts/models.md): Connect to any LLM provider through the same `BaseChatClient` interface.
- [Architecture Overview](https://docs.motus.lithosai.com/concepts/overview.md): A map of the Motus library: the two ways you write agents, the runtime they share, and where each concept lives.
- [Sandbox](https://docs.motus.lithosai.com/concepts/sandbox.md): A safe, disposable place for agents to run code, shell commands, and long-lived processes. Same API locally and in the cloud.
- [Skills](https://docs.motus.lithosai.com/concepts/skills.md): Self-contained instruction packs an agent loads on demand, instead of bloating the system prompt with every procedure it might ever need.
- [Tools](https://docs.motus.lithosai.com/concepts/tools.md): Give your agent the ability to do things: call functions, run shell commands, query an MCP server, or delegate to another agent.
- [Workflow](https://docs.motus.lithosai.com/concepts/workflow.md): Turn Python functions into a parallel task graph with `@agent_task` and `AgentFuture`.
- [Code Style](https://docs.motus.lithosai.com/contributing/code-style.md): Code conventions for contributing to Motus.
- [Development Setup](https://docs.motus.lithosai.com/contributing/development-setup.md): Get a local Motus checkout running in a few minutes.
- [Pull Requests](https://docs.motus.lithosai.com/contributing/pull-requests.md): How to submit and review pull requests.
- [Testing](https://docs.motus.lithosai.com/contributing/testing.md): Test tiers, VCR cassettes, and async testing patterns.
- [Configuration](https://docs.motus.lithosai.com/getting-started/configuration.md): Configure Motus using environment variables and an optional motus.toml project file.
- [Installation](https://docs.motus.lithosai.com/getting-started/installation.md): Install the Motus library, CLI, and optional coding agent plugin.
- [Quickstart](https://docs.motus.lithosai.com/getting-started/quickstart.md): Write an agent, serve it locally, and deploy it to Motus Cloud in under 3 minutes.
- [Coding Agent](https://docs.motus.lithosai.com/guides/coding-agent.md): A pre-configured Motus agent for software-engineering tasks. Multi-provider, sandboxed, and customizable.
- [Cloud Deployment](https://docs.motus.lithosai.com/guides/deployment.md): Deploy agents to Motus Cloud with a single command.
- [Guardrails](https://docs.motus.lithosai.com/guides/guardrails.md): Validate, transform, or block the inputs and outputs of agents and tools with plain Python functions.
- [Human in the Loop](https://docs.motus.lithosai.com/guides/human-in-the-loop.md): Pause an agent mid-turn, ask the user for approval or clarification, then resume from exactly where you left off.
- [MCP Integration](https://docs.motus.lithosai.com/guides/mcp-integration.md): Connect any MCP-compatible tool server to a Motus agent with get_mcp().
- [Multi-Agent](https://docs.motus.lithosai.com/guides/multi-agent.md): Compose agents with as_tool() and fork() so a supervisor can delegate to specialists and explore independent conversation branches.
- [Plugin](https://docs.motus.lithosai.com/guides/plugin.md)
- [Self-Managed](https://docs.motus.lithosai.com/guides/serving.md): Serve agents over HTTP with session-based conversations and per-request process isolation with a single command.
- [Tracing](https://docs.motus.lithosai.com/guides/tracing.md): Automatically record every LLM call and tool invocation as a structured span no manual instrumentation required.
- [Anthropic SDK](https://docs.motus.lithosai.com/integrations/anthropic-sdk.md): Use your existing Anthropic SDK code with Motus serving and tracing. Define tools, create a ToolRunner, and deploy.
- [Google ADK](https://docs.motus.lithosai.com/integrations/google-adk.md): Serve Google ADK agents with Motus full session history replay, automatic tracing, and cloud deployment.
- [OpenAI Agents SDK](https://docs.motus.lithosai.com/integrations/openai-agents.md): Run OpenAI Agents SDK code with Motus tracing and deployment.
- [Motus Overview](https://docs.motus.lithosai.com/introduction.md): Higher capability, lower cost, faster agents. Deploy locally or to the cloud in one command.
- [Messages](https://docs.motus.lithosai.com/reference/api/messages.md): REST API reference for sending messages to a session and retrieving conversation history.
- [Overview](https://docs.motus.lithosai.com/reference/api/overview.md): Reference for the Motus agent server REST API. Manage sessions, send messages, and receive results via webhooks.
- [Sessions](https://docs.motus.lithosai.com/reference/api/sessions.md): REST API reference for session management. Sessions represent individual conversations with your agent — each one holds its own state and message history.
- [Webhooks](https://docs.motus.lithosai.com/reference/api/webhooks.md): Receive agent turn results via HTTP callback instead of polling. Include a webhook field in your message request and the server will POST the result to your URL when the turn completes.
- [motus deploy](https://docs.motus.lithosai.com/reference/cli/deploy.md): Package and deploy an agent to Motus Cloud.
- [motus login](https://docs.motus.lithosai.com/reference/cli/login.md): Authenticate with Motus Cloud via browser-based OAuth.
- [motus logout](https://docs.motus.lithosai.com/reference/cli/logout.md): Revoke credentials and clear the local credential file.
- [Overview](https://docs.motus.lithosai.com/reference/cli/overview.md): The Motus CLI. Build, serve, and deploy AI agents from the command line.
- [motus serve chat](https://docs.motus.lithosai.com/reference/cli/serve/chat.md): Send a single message to a running agent or enter an interactive REPL.
- [motus serve create](https://docs.motus.lithosai.com/reference/cli/serve/create.md): Create a new session on a running Motus agent server.
- [motus serve delete](https://docs.motus.lithosai.com/reference/cli/serve/delete.md): Delete a session on a running Motus agent server.
- [motus serve get](https://docs.motus.lithosai.com/reference/cli/serve/get.md): Get details for a session, with optional long-polling.
- [motus serve health](https://docs.motus.lithosai.com/reference/cli/serve/health.md): Check the health of a running Motus agent server.
- [motus serve messages](https://docs.motus.lithosai.com/reference/cli/serve/messages.md): Retrieve the full conversation history for a session.
- [Overview](https://docs.motus.lithosai.com/reference/cli/serve/overview.md): CLI reference for the motus serve command group. Start an agent HTTP server and interact with it from the terminal.
- [motus serve send](https://docs.motus.lithosai.com/reference/cli/serve/send.md): Send a message to an existing session on a running Motus agent server.
- [motus serve sessions](https://docs.motus.lithosai.com/reference/cli/serve/sessions.md): List all active sessions on a running Motus agent server.
- [motus serve start](https://docs.motus.lithosai.com/reference/cli/serve/start.md): Start an HTTP server that wraps an agent at a given import path.
- [motus whoami](https://docs.motus.lithosai.com/reference/cli/whoami.md): Print the identity associated with your current Motus Cloud credentials.