gateway
A high-performance AI Gateway connecting to over 1,600 LLMs with guardrails.
GraphCanon updated 1w · GitHub synced 1w · 43 views this month
Decision brief
A high-performance AI Gateway named 'gateway', supporting over 1,600 LLM connections and featuring various guardrail mechanisms for safer utilization.
Good fit when
- Use gateway when you need a versatile platform capable of connecting to more than 1,600 LLM providers.
- Utilize it if cost management is crucial as it provides smart caching and usage analytics tools.
Avoid when
- Avoid using gateway if your application only requires connection to a limited number of LLM providers, as its extensive provider support might introduce unnecessary complexity.
- If you don't require sophisticated cost management features such as smart caching or usage analytics provided by the tool, consider simpler alternatives.
- Pricing:
- unknown - The service is open source and MIT licensed; specific pricing for related services (if any) not detailed in repository.
- Requirements:
- Developed using TypeScript; no Docker requirement specified for operation or development.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (12,668) are secondary evidence.
- npm downloads (30d)
- 3,981·npm downloads API·1w
Maintenance and security
Full trust report- Maintenance
- Steady (74d since push)
- As of 1w
- Provenance
- Not a fork · Organization account
- As of 1w
- Security (OSV)
- No MCP manifest
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install gatewayHow it fits your stack(11)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Related
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Portkey-AI/gateway is a platform that routes requests to multiple LLM providers while incorporating various guardrail mechanisms. It offers smart caching and usage analytics for cost management and efficient operations.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 7, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 7, 2026
- CLI
- CLI entrypoint
Source: package.json:bin|scripts · Aug 7, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Aug 7, 2026
- Languages
- typescript, javascript
Source: github.language+package.json · Aug 7, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 7, 2026)
# pip install -qU portkey-aiSource link
Tags
README
pip install -qU portkey-ai
from portkey_ai import Portkey
Cost Management
- Smart caching: Cache responses from LLMs to reduce costs and improve latency. Supports simple and semantic* caching.
- Usage analytics: Monitor and analyze your AI and LLM usage, including request volume, latency, costs and error rates.
- Provider optimization*: Automatically switch to the most cost-effective provider based on usage patterns and pricing models.
Getting Started with the Community
Join our weekly AI Engineering Hours every Friday (8 AM PT) to:
- Meet other contributors and community members
- Learn advanced Gateway features and implementation patterns
- Share your experiences and get help
- Stay updated with the latest development priorities
Join the next session → | Meeting notes
For agents
This page has a .md twin and JSON over the API.