Agent frameworks and the m8tes API solve different problems. A framework (eve, LangGraph, CrewAI, the OpenAI Agents SDK) is code: you build, host, and operate your own agent application, with full control over every part. The m8tes API is a managed platform: agents are API resources, and the infrastructure they run on is operated for you.
A framework gives you a codebase to build an agent. m8tes gives you an API to give every customer one.
Choose a framework
Use a framework when you want full customization: the agent's behavior is your core product, you want to own the code, run your own agent infrastructure, and build and maintain the add-ons you need. eve (Vercel's open-source "Next.js for agents"), LangGraph, and the OpenAI Agents SDK are strong choices.
Choose m8tes
Use m8tes when you want agents in your product without building or maintaining agent infrastructure. You write the prompt and pick the tools. m8tes manages:
| |
|---|
| Multi-tenancy | Every end user gets an isolated agent: memory, history, files, tool access, and spend scoped by user_id. Users |
| Hosted runtime | Each run executes in an isolated sandbox. Nothing to deploy or scale. |
| Integrations | 150+ managed integrations with OAuth handled, including end users connecting their own accounts. Tools |
| Custom tools | Bring your own MCP servers, custom tools, and skills. Custom Tools |
| Model choice | Model-agnostic: pick the model per agent or per run. Models |
| Memory | Persistent per-user memory across runs. Memories |
| Scheduling and triggers | Cron schedules, webhooks, email inboxes, Slack, and iMessage. Scheduling |
| Human-in-the-loop | Three permission modes; approvals answered in email or Slack. Human-in-the-Loop |
| Streaming | Real-time run events over SSE. Streaming |
| Webhook events | Your product is notified when runs complete or need approval. Webhook Events |
| Files and reports | Agents generate files, data exports, and reports. Files |
| Computer use | Agents operate a full desktop for apps without an API. Computer Use |
| Embedded UI | Drop-in React chat component, @m8tes/react. Embed a UI |
| Billing and limits | Per-token billing, per-user spend caps, zero-data-retention option. Billing & Usage, Data Retention |
Both
The two compose: some teams build a bespoke core agent on a framework and use m8tes for the per-customer fleet.
Next: Quick Start · Users · Embed a UI
