General
What is Reminix?
What is Reminix?
Build AI agents with simple code. Define handlers, add tools, and get REST APIs automatically. Already using LangChain or LangGraph? Wrap your existing agents with one line.
What's the difference between invoke and chat?
What's the difference between invoke and chat?
- Invoke: Stateless. Send input, get output. No conversation history.
- Chat: Conversational. Send message history, get a response with updated history.
Which AI frameworks are supported?
Which AI frameworks are supported?
Reminix supports:
- LangChain and LangGraph
- Vercel AI SDK
- OpenAI SDK (including Assistants)
- Anthropic SDK
- LlamaIndex (Python only)
- Native Reminix Agents (lightweight, no framework needed)
Is there a free tier?
Is there a free tier?
Yes! Reminix offers a free tier for development and testing. Check the pricing page for details.
Technical
What are the rate limits?
What are the rate limits?
Default rate limits:
- 60 requests per minute
- 10,000 requests per day
What's the maximum request/response size?
What's the maximum request/response size?
- Request body: 10 MB
- Response body: 50 MB
- Timeout: 30 seconds (use streaming for longer tasks)
Does Reminix support streaming?
Does Reminix support streaming?
Yes! Both
invoke and chat support streaming via Server-Sent Events. Enable with stream: true. See Streaming for details.Can I use my own API keys for LLM providers?
Can I use my own API keys for LLM providers?
Yes. When deploying agents, set your OpenAI, Anthropic, or other API keys as environment variables in the dashboard. Reminix never sees or stores your LLM provider keys in plain text.
Is my data secure?
Is my data secure?
Yes. All data is encrypted in transit (TLS) and at rest. We don’t train on your data or share it with third parties. See our Security page for details.
Which regions are supported?
Which regions are supported?
Reminix currently runs in:
- US East (us-east-1)
- EU West (eu-west-1)
Troubleshooting
I'm getting 'Agent not found' errors
I'm getting 'Agent not found' errors
Check that:
- The agent name is spelled correctly (case-sensitive)
- The agent is deployed successfully (check dashboard)
- You’re using the correct API key for the project
My agent is timing out
My agent is timing out
Default timeout is 30 seconds. For long-running tasks:
- Enable streaming to get partial results
- Break up the task into smaller chunks
- Increase timeout in agent configuration (max 5 minutes)
I'm getting rate limited
I'm getting rate limited
If you hit rate limits:
- Implement exponential backoff
- Cache responses when possible
- Contact us for higher limits
My deployment failed
My deployment failed
Common causes:
- Missing dependencies - Check
requirements.txtorpackage.json - Syntax errors - Test locally before deploying
- Missing environment variables - Ensure API keys are set in Project Settings → Secrets
Streaming isn't working
Streaming isn't working
Ensure:
- You’re passing
stream: truein the request - Your client handles Server-Sent Events
- No proxies are buffering the response
Billing
How is usage calculated?
How is usage calculated?
Usage is based on:
- Executions: Number of invoke/chat calls
- Compute time: Duration of agent execution
- AI credits: If using managed agents (Reminix-hosted models)
Can I set spending limits?
Can I set spending limits?
Yes. In the dashboard, go to Settings → Billing → Spending Limits to set monthly caps.
What happens if I exceed my plan limits?
What happens if I exceed my plan limits?
You’ll receive email warnings at 80% and 100% usage. At 100%, requests may be throttled until the next billing cycle or you upgrade.