# aws-samples/bedrock-access-gateway

OpenAI-Compatible RESTful APIs for Amazon Bedrock

Repository: https://github.com/aws-samples/bedrock-access-gateway
Canonical: https://ross.abutalabs.com/products/bedrock-access-gateway
Language: Python
License: MIT-0
License Family: permissive
Topics: bedrock, genai, openai, openai-api, openai-proxy, proxy
Last push: 2026-06-18T11:55:59+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 88, release rhythm 35, longevity 63
- inputs: {"age_days": 889, "days_push": 76, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1005, forks 308 (observed 2026-09-03T02:15:09.421735+00:00)

## What it is
A proxy service that exposes Amazon Bedrock foundation models through OpenAI-compatible RESTful APIs. It lets existing applications built on OpenAI SDKs use Bedrock models like Claude, Nova, and DeepSeek without code changes.

## Use cases
- use OpenAI SDKs with Amazon Bedrock models
- switch an app from OpenAI API to Bedrock without code changes
- test Bedrock models in tools that expect OpenAI endpoints like AutoGen
- serve Claude or Nova models behind an OpenAI-compatible chat completions API
- get streaming chat responses from Bedrock via SSE
- use Bedrock embeddings through the OpenAI embeddings API

## When to choose
- you have OpenAI-based code or third-party tools and want to point them at Bedrock
- you want OpenAI-style chat completions, tool calls, and embeddings backed by Bedrock
- you need streaming responses, reasoning support, or prompt caching with Bedrock models

## When to avoid
- you are already using the native Bedrock SDK and don't need OpenAI compatibility
- you need an OpenAI-compatible gateway for providers other than AWS Bedrock
- you want a fully managed service rather than self-deploying on AWS

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, api-framework, http-server, proxy, chatbot
- domain: large-language-models, artificial-intelligence, apis, cloud-computing, self-hosted
- platform: python, cloud, self-hosted
- tags: openai-compatible-api, amazon-bedrock, api-gateway, streaming, chat-completions, embeddings, aws-samples, docker

## Member repositories
- aws-samples/bedrock-access-gateway (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:09.421735+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:13:08.691476+00:00, confidence not recorded.
  - readme: https://github.com/aws-samples/bedrock-access-gateway (fetched 2026-09-03T02:15:09.421735+00:00, sha 3758456e3dde)
- Data as of 2026-08-30T08:39:29.467469+00:00.