# Gvnr (gvnr.dev)

Enforces per-agent USD spend caps and provider rate limits before each LLM call, then reconciles actual cost afterward.

- Atlas card: https://inite.ai/en/atlas/gvnr.dev
- Site: https://gvnr.dev
- For: developers running autonomous AI agents who need per-agent spend caps and rate limits
- Categories: agents
- Use 0/100 · alive 100/100

## Used for

- cap each agent's daily spend before every LLM call
- share one provider's requests-per-minute across several agents
- route denied or sensitive agent actions to a human for approval

## Price

- from 1 USD/usage, no free plan (read 2026-10-26 on https://gvnr.dev/#pricing)

## For developers

- OpenAPI: https://gvnr.dev/openapi.json (21 paths)
- MCP server: dev.gvnr/gvnr (namespace; auth on 2026-10-26)
- Status page: https://gvnr.dev/status
- Read 2026-10-26

## MCP server, measured daily

Server: https://gvnr.dev/mcp, checked every day since 2026-10-26 (1 checks).

- Answered: measuring, 1 daily checks so far
- Median first answer: 245 ms
- Sign-in: a pasted key
- Method: https://inite.ai/en/atlas/mcp/report

## Your data

- Certifications stated: none
- Read 2026-10-26

---

Source: INITE Atlas, https://inite.ai/en/atlas/gvnr.dev. JSON: https://inite.ai/api/atlas/gvnr.dev. MCP: https://inite.ai/api/mcp (atlas_lookup).