OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Bricksllm

BricksLLM is a Go-based AI gateway that routes requests between applications and language-model providers, including OpenAI, Azure OpenAI, Anthropic and vLLM. It provides per-API-key rate and cost limits, access controls, and usage and cost monitoring.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Bricksllm — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use BricksLLM when applications need a shared gateway for supported model providers and teams want per-key limits, access controls or usage monitoring.

Who it is for

  • Teams routing application requests to supported LLM providers.
  • Organizations distributing model access keys with per-key rate or spending limits.
  • Operators who need access controls and usage tracking by user, application or environment.

Documented uses

  • Route LLM requests through a gateway to configured providers.
  • Set rate and cost limits for individual API keys.
  • Restrict model or endpoint access.
  • Track request and cost usage across users or organizations.
  • Apply documented PII detection and masking, retries, caching or failover features.
Before you choose

Requirements & limits

The repository documents a self-hosted Docker Compose setup and says a managed version with a dashboard is also available. The project is MIT-licensed.

  • The documented local deployment uses Docker Compose, PostgreSQL and Redis.
  • A provider API credential is configured separately from the BricksLLM key used by clients.
  • The project supports OpenAI, Azure OpenAI, Anthropic and vLLM; the README also lists Deepinfra, custom deployments and custom models.
  • The README identifies PII masking, retries, caching and failover among its features.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Direct an OpenAI Node SDK client to the gateway

Configure the documented OpenAI Node SDK v4 example to send requests through BricksLLM.

Before you start

  • A running BricksLLM gateway
  • A BricksLLM API key
  • OpenAI Node SDK v4

Steps

  1. Set the SDK apiKey to the BricksLLM key.

  2. Set the SDK baseURL to the gateway's OpenAI provider route, as shown in the README.

Expected outcome

The SDK is configured to address OpenAI requests through BricksLLM's gateway route.

Guide limitations

  • The README gives a configuration example, not a verification of a successful request.
  • The provider setting and gateway key must already be configured.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
bricks-cloud/BricksLLM · Official homepage title · retained in its source language
How we review sourcesSuggest a correction