convez.ai
PluginIntegração & APIsIntermediário
stdapi-ai

stdapi.ai - Gateway de API Compatível com OpenAI e Anthropic

stdapi-ai/stdapi.ai

Rode qualquer app OpenAI/Anthropic no AWS Bedrock com 80+ modelos

Ver no GitHub
InicialPluginScore · de 0 a 100

Gateway de API que permite executar aplicações compatíveis com OpenAI e Anthropic no AWS Bedrock, acessando 80+ modelos (Claude, Kimi K2, MiniMax, Qwen) com privacidade empresarial e preços pay-per-use. Funciona como camada de compatibilidade para unificar acesso a múltiplos provedores de IA sob uma interface padronizada.

Instalação

$npx convez-ai stdapi-ai/stdapi.ai

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
27
Forks
3
Acompanhando
0
Saúde
37%
Último commit
há 2 dias
Versão
v1.19.1
Issues abertas
9
Contribuidores
1

Casos de uso

  • Migrar aplicações existentes de OpenAI para AWS Bedrock sem refatoração
  • Unificar acesso a múltiplos modelos de IA sob interface compatível
  • Implementar conformidade e privacidade empresarial com modelos de terceiros

Veredito

Solução robusta de compatibilidade de APIs que resolve o problema real de lock-in com provedores de IA. Adequada para times que querem flexibilidade de modelos mantendo código e arquitetura existentes.

README

A tradução para o português deste README ainda está na fila.

stdapi.ai

OpenAI & Anthropic Compatible API Gateway for AWS Bedrock and AI Services

Run your favorite OpenAI and Anthropic-compatible applications on AWS Bedrock. Access 80+ models including Claude, Kimi K2, MiniMax, Qwen with enterprise privacy, compliance controls, and pay-per-use AWS pricing.


AWS Marketplace Terraform Module OpenTofu Module

14-day free trial on AWS Marketplace · $0.10/container-hour


Community Edition Docker image Community Edition TrueNAS App Community Edition License

Free for local development · Try Locally with Docker


Documentation Samples Lint Code quality


⚡ Try It Locally with Docker

Run stdapi.ai locally with the free community image. Requires AWS credentials configured (run aws sso login first).

docker run --rm -p 8000:8000 \
  -v ~/.aws:/home/nonroot/.aws:ro \
  -e AWS_BEDROCK_REGIONS=us-east-1,us-west-2 \
  -e ENABLE_DOCS=true \
  ghcr.io/stdapi-ai/stdapi.ai-community:latest

Podman on Fedora/RHEL (SELinux): Add --userns=keep-id and use :ro,z instead of :ro

Open http://localhost:8000/docs in your browser — Swagger UI lets you explore all endpoints and send live requests without writing any code.

Or test from the terminal with curl:

List available models:

# All discovered models with capabilities, modalities, and supported routes
curl http://localhost:8000/search_models

# Filter — e.g. vision-capable chat models only
curl "http://localhost:8000/search_models?route=/v1/chat/completions&input_modalities=IMAGE"

# OpenAI-compatible model list
curl http://localhost:8000/v1/models

OpenAI-compatible chat:

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "amazon.nova-micro-v1:0",
    "messages": [{"role": "user", "content": "Hello from AWS Bedrock!"}]
  }'

Anthropic-compatible chat:

curl http://localhost:8000/anthropic/v1/messages \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "amazon.nova-micro-v1:0",
    "max_tokens": 1000,
    "messages": [{"role": "user", "content": "Hello from AWS Bedrock!"}]
  }'

Using the official SDKs? Point base_url at http://localhost:8000/v1 (OpenAI SDK) or http://localhost:8000/anthropic (Anthropic SDK) — no other code changes.

Local development guide →


🚀 Production Deployment

Deploy to AWS in minutes with Terraform. The AWS Marketplace subscription includes a 14-day free trial.

module "stdapi_ai" {
  source  = "stdapi-ai/stdapi-ai/aws"
  version = "~> 1.0"
}

That's it. You get a production-grade ECS Fargate deployment with HTTPS, WAF, auto-scaling, and monitoring.

Full deployment guide → · Advanced deployment →

Prefer a hands-off setup? A managed deployment service is available.


🎯 Why stdapi.ai?

  • 🔌 Drop-in replacement — Change only the base URL. Works with LangChain, Continue.dev, Open WebUI, n8n, Claude Code, Aider, and 1000+ tools.
  • 🔒 Data stays in your AWS account — All inference runs in your account. Data never shared with model providers or used for training. Configure allowed regions for GDPR, HIPAA, FedRAMP.
  • 🌍 Multiply quota across regions — Each AWS region has independent quota. 3 regions = 3× tokens per minute. Automatic routing and failover—no client changes.
  • 💰 Pay only what you use — AWS Bedrock rates, no markup, no subscriptions or monthly minimums.
  • ⚡ Advanced Bedrock features — Reasoning modes (Claude, Nova), prompt caching, guardrails, service tiers, inference profiles, prompt routers—all through standard OpenAI and Anthropic API parameters.
  • 🧠 80+ models — Claude, Kimi K2, MiniMax, Qwen, GLM, Nova, Llama, Stability AI, and more. Switch instantly—no vendor lock-in.
  • 🎨 Complete multi-modal API — Chat, embeddings, image generation/editing/variations, audio speech/transcription/translation. Amazon Polly, Transcribe, Translate unified under OpenAI-compatible endpoints.
  • 📊 Full observability — OpenTelemetry integration, request/response logging, Swagger and ReDoc API documentation.
  • 🤖 Integrated MCP server — Every API endpoint exposed as a Model Context Protocol tool. AI agents connect directly—no HTTP client code required. Streamable HTTP and SSE transports with configurable tool selection.
  • 🔄 Automatic deprecated model fallback — When AWS retires a model, requests are transparently redirected to its replacement. Applications survive model deprecations without code changes.

See all features →


💼 Use Cases

CategoryWhat You Can BuildToolsGuide
💬 Chat InterfacesPrivate ChatGPT alternative, team chat, knowledge base with RAGOpen WebUI, LibreChatGuide →
💻 Coding AssistantsAI pair programming, code completion, codebase chatContinue.dev, Cline, Cursor, Claude Code, AiderGuide →
🔄 Workflow AutomationAI-powered ticket routing, content creation, data processingn8n, Make, ZapierGuide →
🤖 ChatbotsSlack/Discord/Teams bots, documentation assistantsSlack Bot, Botpress
🧠 Autonomous AgentsPersonal AI assistants, research agents, multi-agent systems, code agentsOpenClaw, LangGraph, CrewAI, AutoGPT

All use cases and integration guides →


🛒 AWS Marketplace — Commercial Edition

The commercial license via AWS Marketplace is for production, internal tools, and proprietary applications:

  • ✅ 14-day free trial — test in your environment risk-free
  • ✅ Commercial license — no AGPL obligations, keep your code private
  • ✅ Hardened containers — security-optimized with regular updates
  • ✅ Terraform module — production-ready infrastructure in minutes
  • ✅ Streamlined AWS billing — consolidated with your existing AWS costs

Start 14-Day Free Trial →


🛠️ Development from Source

For contributors working on stdapi.ai itself:

Prerequisites

  • Python 3.14+
  • uv package manager
  • AWS credentials configured

Setup

git clone https://github.com/stdapi-ai/stdapi.ai.git
cd stdapi.ai
uv sync --frozen --extra uvicorn

aws sso login --profile your-profile-name

export AWS_BEDROCK_REGIONS=us-east-1
export ENABLE_DOCS=true

uv run uvicorn stdapi.main:app --host 0.0.0.0 --port 8000

Development Guidelines

  • Follow existing code style and conventions
  • Add tests for new features
  • Update documentation for user-facing changes
  • Ensure all tests pass before submitting PR

📜 License

Dual-licensed:

Learn more about licensing →


🤝 Contributing

We welcome contributions! Whether it's bug reports, new features, documentation improvements, or ideas — please feel free to open issues or submit pull requests.


💬 Support


Ready to run 80+ AI models securely on AWS?

Start 14-Day Free Trial on AWS Marketplace · Deployment guide · Terraform examples · Try Locally with Docker

Ver o original no GitHub

Bom para

Relacionados