Enterprise DNA Enterprise DNA
O Open Source Observability medium

Inferrail

by Community

Self-hosted OpenAI/Anthropic-compatible gateway: give each AI agent run a dollar budget, enforced before the provider, with a payload-free per-run cost record.

OSS

Inferrail

Added 5 Oct 2026

#agent-budget #ai-agents #ai-cost #ai-gateway #cost-control #llm-budget #llm-cost #llm-gateway

Overview

Inferrail is a self-hosted gateway that is compatible with OpenAI and Anthropic APIs. It assigns a dollar budget to each AI agent run and enforces that budget before the request reaches the provider. It records a payload-free cost record for each run, allowing cost tracking without storing request data.

Best for

Best for
Developers who need simple, self-hosted cost controls for AI agent runs.

Use cases

  • Set per-run dollar budgets for AI agents
  • Enforce spending limits before provider calls
  • Track AI agent costs with lightweight per-run records

Notes

Inferrail is a self-hosted gateway that is compatible with OpenAI and Anthropic APIs. It assigns a dollar budget to each AI agent run and enforces that budget before the request reaches the provider. It records a payload-free cost record for each run, allowing cost tracking without storing request data.

0 stars on GitHub. Last updated 2026-10-04. Licensed Apache-2.0.

Use cases

  • Set per-run dollar budgets for AI agents
  • Enforce spending limits before provider calls
  • Track AI agent costs with lightweight per-run records

Pros

  • Self-hosted for full control
  • OpenAI and Anthropic compatible
  • Enforces budgets before hitting the provider

Cons

  • Community project with no stars or track record
  • Python only
  • No built-in UI or advanced analytics mentioned

Indexed from awesome-llmops and enriched against its public facts.

Pros

  • Self-hosted for full control
  • OpenAI and Anthropic compatible
  • Enforces budgets before hitting the provider

Cons

  • Community project with no stars or track record
  • Python only
  • No built-in UI or advanced analytics mentioned
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.