One gateway for every call your agents make.
ACPpotamia is an AI gateway that sits between your agents and model providers. It controls cost, stops runaway loops, and records everything, without changing how you write code.
AI governance and compliance
Govern AI agents across departments: approved-model policies, an organization-wide kill switch, central audit logs with JSONL export, and test keys for safe CI.
Per-customer budgets
Give every customer of your AI product their own monthly budget and rate limit. One customer's runaway agent can no longer use up your shared OpenAI or Claude budget.
Budgets and cost control
Put a hard monthly budget on OpenAI and Anthropic spend. ACPpotamia reserves each AI agent call's cost before it is sent, so agents cannot overspend.
Rate limiting
Rate limit every AI agent's calls to OpenAI and Anthropic per team, at the edge. Requests over the limit get HTTP 429 with Retry-After before they cost money.
Loop detection
Detect and stop AI agents stuck in loops: repeated tool calls, retries and identical prompts. ACPpotamia stops the agent in seconds, before it burns your budget.
Kill switch
Stop one AI agent session or every agent on your team with one click or one API call. The kill switch takes effect on the next call, everywhere.
Audit logs
Every AI agent call logged: model, tokens, cost, outcome and timing, blocked calls included. Searchable for 365 days, with optional request and response logs.
OpenAI gateway
An OpenAI API proxy for chat completions, the Responses API and embeddings, with budgets, rate limits and loop detection. Keep the official OpenAI SDK.
Claude (Anthropic) gateway
A Claude API gateway for the Anthropic Messages API: budgets, rate limits, loop detection and audit logs for Claude Opus, Sonnet and Haiku. Keep the Anthropic SDK.
Self-hosted models
Put budgets, rate limits and loop detection in front of your own model server: vLLM, Ollama, TGI or any OpenAI- or Anthropic-compatible endpoint.