Home/Inference & Serving/gateway

gateway

adaline/gateway

Super SDK for calling over 300 LLMs with a unified interface

GitHub Website

GraphCanon updated Sep 30, 2026 · GitHub synced Sep 20, 2026

71views this month

607 stars26 forksLast push Jul 29, 2026 TypeScript MIT

Decision brief

Adaline Gateway is a production-grade, fully local Super SDK that supports over 300 LLMs with a unified interface, including features like batching, retries, caching, and OpenTelemetry integration.

Good fit when

When you need a fully local SDK that supports more than 300 LLMs with a unified interface.
If you require built-in support for batching, retries, caching, and OpenTelemetry integration.

Avoid when

If you are looking for a cloud-based service, as Adaline Gateway is fully local and not a proxy.
When you need support for a specific LLM that is not among the 300+ supported by Adaline Gateway.

Observed Sep 30, 2026 · Source: enrich:decision_facts

gateway alternatives Trust report

gateway vs ollama gateway vs litellm gateway vs 9router

Verify the decision

Adoption

Package downloads where a registry match exists. GitHub stars (607) are secondary evidence.

npm downloads (30d): 3,676·npm downloads API·Sep 20, 2026

Maintenance and security

Full trust report

Maintenance: Steady (52d since push); As of Sep 20, 2026
Provenance: Not a fork · Organization account; As of Sep 20, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install gateway

npm

How it fits your stack(18)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Alternative

ollama

Both ollama and gateway aim to simplify the use of multiple LLMs, but ollama focuses more on getting up and running quickly while Gateway offers a comprehensive toolkit with more features like caching and OpenTelemetry.

alternative

litellm

litellm and Adaline Gateway both provide unified interfaces for interacting with a large number of LLMs, making them alternatives in the space.

alternative

llmfit

adaline-gateway and llmfit both provide access to multiple LLMs, but adaline-gateway seems more focused on direct model calls while llmfit is about finding which models run efficiently.

alternative

Integrates

unsloth

'Unsloth' provides a web UI for handling and training open models locally. Gateway could be used as part of the backend infrastructure to call these local LLMs through its interface.

integrates

LlamaFactory

Gateway has an 'integrates with' relationship to LlamaFactory because Gateway provides a unified interface to call multiple local language models, which can include those fine-tuned using LlamaFactory's repository for 100+ large language and vision-language models.

integrates

CowAgent

Gateway, which provides a unified interface to call multiple language models locally with features like batching and caching, has an 'integrates with' relationship to CowAgent because CowAgent can utilize Gateway's functionality to enhance its capability in executing tasks that require interactions with various language models.

integrates

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

PaddleOCR

PaddleOCR is an OCR toolkit which can potentially use language models for text understanding or improvement. It's adjacent since Gateway connects with LLMs but doesn't specifically support OCR tools.

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

ai-engineering-hub

Tutorials on LLMs, RAGs, and real-world AI agent applications

37k★

llm

Access large language models from the command-line

12k★

oumi

Easily fine-tune, evaluate and deploy open source LLMs/VLMs

9.4k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Adaline Gateway is a production-grade, fully local Super SDK that provides a unified interface for calling more than 300 LLMs. It supports batching, retries, caching, callbacks, and OpenTelemetry integration, and is extensible with custom plugins.

Capability facts

MCP server: No MCP server detected
Source: repo_scan · Sep 20, 2026
Languages: typescript, javascript
Source: github.language+package.json · Sep 20, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Sep 20, 2026)

npm install @adaline/gateway @adaline/types

Source link

OpenAI APIOpenAI API

Source: README excerpt (regex_v1, Sep 20, 2026)

const OPENAI_API_KEY = "your-api-key"; // Replace with your OpenAI API key

Source link

README

Adaline Gateway The only fully local, production grade Super SDK that provides a simple, unified, and powerful interface for calling more than 300+ LLMs. Production ready and trusted by enterprises Fully local and NOT a proxy deploy it anywhere Built in batching, retries, caching...

For agents

This page has a .md twin and JSON over the API.

/tools/adaline-gateway.md GET /api/graphcanon/tools/adaline-gateway GET /api/graphcanon/graph?tool=adaline-gateway

gateway

Decision brief

Good fit when

Avoid when

Verify the decision

Adoption

Maintenance and security

Install

How it fits your stack(18)

Alternative

Integrates

Related

Relationship graph

Similar tools

Evidence and technical details

Overview

Capability facts

Categories

Compatibility

Tags

README

For agents