The API for building autonomous AI teammates
Deploy AI teammates that connect to apps, run on schedules, have memory, and work autonomously.
Stop building agent infrastructure
Hosted runtime with sandboxed execution, human-in-the-loop, 70+ managed integrations, scheduled runs, email triggers, and persistent memory.
Hosted agent runtime
Your teammates run in isolated sandboxes with real-time streaming. No servers to manage, nothing to maintain.
Human-in-the-loop
Teammates ask for approval before taking sensitive actions. You stay in control without micromanaging every step.
70+ managed integrations
Gmail, Slack, Notion, HubSpot, Google Ads, Linear. OAuth and token refresh handled.
Scheduled runs
Set a schedule and teammates run automatically. Daily, weekly, hourly. Completely hands-free.
Email inbox
Forward an email, get work done automatically. Every teammate gets their own inbox.
Agent memory
Teammates remember past conversations and build context over time. Per-user scoping for multi-tenant apps.
File handling
Teammates create reports, spreadsheets, and exports you can download through the API.
Run your first autonomous teammate in 5 lines
Install the SDK, describe what you need done, and your teammate handles the rest.
pip install m8tesIntegrate teammates into any workflow
Run teammates on demand, on a schedule, from an email, or from any external event.
Email inbox
Email your teammate and it goes off to solve the task, give advice, or answer questions.
Schedule
Daily, weekly, or hourly. Set a cadence and your teammate runs automatically.
Webhook
POST when a Stripe charge fails, a GitHub issue opens, or a form submits. Any event, any system.
On demand
Trigger a run from your code or the API whenever you need it.
Works with
Linear
Stripe
Google Adsand 70+ other apps
From weeks of engineering to minutes
Other SDKs give you building blocks. We give you deployed agents.
With OpenAI Agents SDK, Claude Code SDK, etc.
- Build and maintain sandboxed execution
- Implement OAuth for every app you connect
- Write your own scheduling and trigger system
- Build approval flows so agents don't go rogue
- Design memory that persists across executions
- Set up real-time streaming for your UI
- Handle file output and delivery
- Build webhook infrastructure for agent events
- Isolate user data for multi-tenant apps
- Give agents their own email inbox
- Keep up with fast-moving AI models, APIs, and best practices
Weeks of engineering before your first agent runs.
With the m8tes SDK
- Hosted sandbox, no servers to manage
- 70+ integrations with managed OAuth
- Scheduling, webhook triggers, and email inbox built in
- Human-in-the-loop so you stay in control
- Persistent memory across executions
- Real-time streaming out of the box
- Files created and downloadable via the API
- Outbound webhooks for agent events
- Per-user isolation for multi-tenant apps
- Every agent gets its own @m8tes.ai inbox
- Always up to date as AI evolves, zero maintenance on your end
Live in minutes. Not weeks.
Automate your workflows or build AI features for your users
Automate internal workflows
Revenue reporting
Pull MRR from Stripe, update the tracking sheet, post weekly summaries to Slack. Replaces manual Monday morning work.
Support triage
Classify inbound tickets, draft replies, escalate blockers to the right Slack channel. Runs 24/7 on a schedule.
Ad spend monitoring
Check Google Ads weekly. Pause ads burning budget on low-converting keywords. Alert the team.
Build AI features for your users
Customer-facing assistants
Give each user their own AI teammate with isolated memory, tools, and permissions. Multi-tenant by default.
Automated onboarding
New signup triggers a run that provisions accounts, sends welcome emails, and schedules a check-in.
In-app research agent
Users describe what they need. The agent searches, synthesizes, and returns structured results in your UI.
Go deeper on AI agent development
Architecture, patterns, and production setup.
Teammate, task, run
The SDK is built around three concepts. A teammate is a reusable agent with a name, instructions, and connected apps. A task defines what it should do. A run is a single execution of that task.
You configure a teammate once. Then trigger runs on demand, on a schedule, or from a webhook. Each run streams events in real time so you can show progress in your UI or pipe results to downstream systems.
Hosted sandboxed execution
Every run executes in an isolated sandbox with its own filesystem and network. The runtime handles tool calls, OAuth token refresh, rate limiting, and retries. You never touch infrastructure.
Streaming and real-time events
The SDK uses server-sent events (SSE) to stream run progress. You get events for tool calls, text output, file creation, and completion. Build real-time UIs or process events in a backend pipeline.
Set user_id on any run to scope it to a specific end user. Memory, task history, and tool access are strictly isolated. One user never sees another user's data.
User isolation with user_id
Set user_id on any run to scope it to a specific end user. Memory, task history, and tool access are strictly isolated. One user never sees another user's data.
Per-user memory and tool scoping
Each end user gets their own memory context. The agent remembers past interactions with that user and builds on them. Tool permissions can also be scoped per user for fine-grained access control.
Embedding AI agents in your product
Use the SDK to give every user their own AI agent experience inside your app. Each user gets isolated runs, memory, and tool access. You control the agent's instructions and capabilities. Your users just see the results.
Three modes: autonomous (runs and acts without asking), approval (asks before every sensitive action), and plan (proposes a plan, you approve, then it executes). Start with approval. Promote to autonomous when trust is established.
Permission modes for safe execution
Three modes: autonomous (runs and acts without asking), approval (asks before every sensitive action), and plan (proposes a plan, you approve, then it executes). Start with approval. Promote to autonomous when trust is established.
Scheduling, webhooks, and email triggers
Cron schedules handle recurring work. Webhooks let you trigger runs from any external event (Stripe charge failed, GitHub issue opened, form submitted). Email triggers let users forward messages directly to an agent.
Monitoring and output validation
Every run produces structured logs showing each tool call, its inputs, and its outputs. Use these logs to debug, audit, and improve agent behavior over time. Output files (CSV, PDF, reports) are downloadable through the API.
FAQ
Common questions about building AI agents with the SDK.
Explore more
Build your first AI agent today
Free to start. No infrastructure to manage. Deploy in minutes.