Hello NVIDIA Team,
I hope you’re doing well.
I’m an independent software engineer currently developing a personal AI assistant called Hermes. It is a non-commercial research and development project focused on AI agents, browser automation, coding assistance, and system automation.
Hermes integrates several NVIDIA NIM models, including language and vision models, to perform tasks such as:
- Multi-agent reasoning
- Browser automation using Playwright
- Linux and terminal automation
- Image and screenshot understanding
- Tool calling
- Code generation
- Long-running agent workflows
The current free API rate limit is becoming a significant bottleneck during development. A single user request may generate multiple sequential and parallel API calls because the agent plans, reasons, invokes tools, verifies results, and may analyze screenshots before producing a final response.
As a result, I frequently receive HTTP 429 (Too Many Requests) responses even during normal development and testing.
I would like to kindly request an increase in my NVIDIA NIM API rate limit from the default allocation to approximately 200 RPM (or any higher limit that you consider appropriate for development purposes).
Project details:
Project Name:
Hermes
Purpose:
Personal research and development
Commercial Usage:
No
Current Issue:
Frequent HTTP 429 responses due to agentic workflows requiring multiple API requests.
I genuinely enjoy working with NVIDIA NIM and would love to continue building Hermes using your models.
If any additional information about my project or account is required, I would be happy to provide it.
Thank you for your time and consideration.