# m8tes

> Run agents through the m8tes API. Includes 190+ managed integrations, memory, scheduling, streaming, and human approvals. Set user_id to isolate each customer's data.

## Get started

- [Introduction](https://www.m8tes.ai/docs/introduction): m8tes is a hosted agent SDK: agents as API resources, through a Python SDK, TypeScript SDK, and REST API.
- [Quick start](https://www.m8tes.ai/docs/quickstart): Run your first agent.
- [Use your coding agent](https://www.m8tes.ai/docs/build-with-agents): Your coding agent (Claude Code, Cursor, or anything that reads URLs) can integrate m8tes for you.
- [Use cases](https://www.m8tes.ai/docs/use-cases): Common patterns.
- [vs. frameworks](https://www.m8tes.ai/docs/vs-frameworks): A framework (eve, LangGraph, CrewAI, OpenAI Agents SDK) is code you build, host, and operate.
- [Community](https://www.m8tes.ai/docs/community): Get help with the SDK, CLI, and API.

## Core concepts

- [Agents](https://www.m8tes.ai/docs/agents): An agent is a reusable definition: a persona with instructions and tools.
- [Tasks](https://www.m8tes.ai/docs/tasks): A task is saved work attached to an agent.
- [Runs](https://www.m8tes.ai/docs/runs): A run is one execution of an agent or task.
- [Orchestration](https://www.m8tes.ai/docs/orchestration): Agents on m8tes pick the right primitive.
- [Streaming](https://www.m8tes.ai/docs/streaming): Runs stream Server-Sent Events (SSE) by default.
- [Memories & documents](https://www.m8tes.ai/docs/memories): Memories are short facts about an end-user, injected into every run for that userid.
- [Files](https://www.m8tes.ai/docs/files): Agents generate files during runs (CSV, JSON, Markdown, HTML, code, plain text).
- [Models](https://www.m8tes.ai/docs/models): Every run executes on a model.

## Triggers & inboxes

- [Scheduling](https://www.m8tes.ai/docs/scheduling): A schedule runs a task on a cron, a fixed interval, or once at a future moment.
- [Webhook triggers](https://www.m8tes.ai/docs/webhook-triggers): Webhook triggers let external systems start runs via HTTP POST.
- [Email inbox](https://www.m8tes.ai/docs/email-inbox): An email inbox gives an agent its own address.
- [Slack inbox](https://www.m8tes.ai/docs/slack-inbox): Once Slack is connected, mention @m8tes in a channel or DM it.
- [iMessage inbox (private beta)](https://www.m8tes.ai/docs/imessage-inbox): Text an agent on iMessage.
- [Read-only inbox](https://www.m8tes.ai/docs/fetchmail-inbox): A read-only inbox lets an agent fetch emails during a run: 2FA codes, verification emails, password resets.

## Tools & skills

- [Tools](https://www.m8tes.ai/docs/tools): Tools are the capabilities agents can use.
- [Built-in tools](https://www.m8tes.ai/docs/built-in-tools): Every agent gets built-in tools from the platform (no integration to connect): memory, cross-run history, self-management, and more.
- [Custom tools](https://www.m8tes.ai/docs/custom-tools): Wrap your own REST API as agent tools.
- [Custom skills](https://www.m8tes.ai/docs/custom-skills): Custom skills are reusable playbooks: a short description (when to use it) plus a markdown body (the steps).
- [Computer use](https://www.m8tes.ai/docs/computer-use): Computer use gives the agent a real Linux desktop: click, type, scroll, screenshot.
- [Coding agents](https://www.m8tes.ai/docs/coding-agents): A coding agent works in a real GitHub repo: clone, install, run the repo's tests, push under m8tes/…, open a PR, watch CI.

## Embed in your product

- [Multi-tenancy](https://www.m8tes.ai/docs/users): Pass userid on agents, runs, tasks, memories, and permissions when each end-user needs isolated data.
- [Embed a UI](https://www.m8tes.ai/docs/embed-a-ui): Put a live agent in your React app: streaming replies, tool calls, and inline approvals, themed to your product.
- [Your API as MCP tools](https://www.m8tes.ai/docs/your-api-as-mcp-tools): You give us REST endpoints; we run the MCP server.
- [Take actions](https://www.m8tes.ai/docs/take-actions): An agent that operates your product for one end-user through your REST API.
- [Human-in-the-loop](https://www.m8tes.ai/docs/human-in-the-loop): Three mechanisms pause a run for a human:
- [Plan mode](https://www.m8tes.ai/docs/plan-mode): With permissionmode="plan", the agent proposes a plan and waits for approval before executing.

## Production

- [Testing](https://www.m8tes.ai/docs/testing): Runs have real side effects (Slack, email, ad changes) and every live run costs tokens.
- [Going live](https://www.m8tes.ai/docs/going-live): Production checklist: keep one end user from draining your budget, exhausting compute, or seeing another end user's data.
- [Limits](https://www.m8tes.ai/docs/limits): Two kinds of limits: request rates and field sizes.
- [Errors](https://www.m8tes.ai/docs/api-errors): All errors follow a standard format:
- [Pagination](https://www.m8tes.ai/docs/api-pagination): Paginated resource lists return this envelope:
- [Webhook events](https://www.m8tes.ai/docs/webhooks-guide): Register endpoints for signed HTTP POSTs when runs complete, fail, or need input.
- [Data retention](https://www.m8tes.ai/docs/data-retention): Choose how much run content m8tes stores.
- [Billing & usage](https://www.m8tes.ai/docs/billing-usage): Every account has two billing meters.

## API reference

- [Introduction](https://www.m8tes.ai/docs/api-introduction): Create agents, give them tasks, and stream their results through a REST API.
- [Authentication](https://www.m8tes.ai/docs/authentication): Every request authenticates with an API key in the Authorization header.
- [Endpoints](https://www.m8tes.ai/docs/api-reference): m8tes is the hosted agent platform: agents are API resources with per-user isolation (userid), memory, scheduling, approvals, and 190+ integrations built in.
- [TypeScript SDK](https://www.m8tes.ai/docs/typescript-sdk): Stream runs, schedule tasks, and handle approvals from your backend.
- [CLI](https://www.m8tes.ai/docs/cli): Use the m8tes CLI to inspect agents, run tasks, manage app connections, and debug account state from your terminal.

## Optional

- [Full Documentation](https://www.m8tes.ai/llms-full.txt): Complete documentation as a single markdown file for LLMs
- [Python SDK](https://pypi.org/project/m8tes/): `pip install m8tes` client library