Skip to content
Back to search

llmgateway

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/theopenco/llmgateway with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/theopenco/llmgateway'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/theopenco--llmgateway/badge.svg)](/listings/theopenco--llmgateway)

HTML

<a href="/listings/theopenco--llmgateway"><img src="/api/listings/theopenco--llmgateway/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

You can use LLM Gateway in two ways:

- **Hosted Version**: For immediate use without setup, visit [llmgateway.io](https://llmgateway.io) to create an account and get an API key. - **Self-Hosted**: Deploy LLM Gateway on your own infrastructure for complete control over your data and configuration.

Self-Hosted With Docker

Use Docker-managed volumes for the unified image. Do not bind-mount a host directory directly to `/var/lib/postgresql/data`, because PostgreSQL initialization inside the container needs to set permissions on that directory and that can fail depending on the host filesystem and ownership.

export LLM_GATEWAY_SECRET="$(openssl rand -base64 32 | tr -d '\n')"
export GATEWAY_API_KEY_HASH_SECRET="$(openssl rand -base64 32 | tr -d '\n')"
./scripts/run-unified-container.sh

If you prefer a one-off `docker run`, use named volumes instead of `~/some-host-dir`:

docker volume create llmgateway_postgres
docker volume create llmgateway_redis

docker run -d \
  --name llmgateway \
  --restart unless-stopped \
  -p 3002:3002 \
  -p 3003:3003 \
  -p 3005:3005 \
  -p 3006:3006 \
  -p 3007:3007 \
  -p 4001:4001 \
  -p 4002:4002 \
  -v llmgateway_postgres:/var/lib/postgresql/data \
  -v llmgateway_redis:/var/lib/redis \
  -e AUTH_SECRET="$LLM_GATEWAY_SECRET" \
  -e GATEWAY_API_KEY_HASH_SECRET="$GATEWAY_API_KEY_HASH_SECRET" \
  ghcr.io/theopenco/llmgateway-unified:latest

Using LLM Gateway API

curl -X POST https://api.llmgateway.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
  -d '{
  "model": "gpt-4o",
  "messages": [
    {"role": "user", "content": "Hello, how are you?"}
  ]
}'

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 128 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # LLM Gateway
  2. LLM Gateway is an open-source API gateway for Large Language Models (LLMs). It acts as a middleware between your applications and various LLM providers, allowing you to:
  3. - Route requests to multiple LLM providers (OpenAI, Anthropic, Google Vertex AI, and others)
  4. - Manage API keys for different providers in one place
  5. - Track token usage and costs across all your LLM interactions
  6. - Analyze performance metrics to optimize your LLM usage
  7. ## Features
  8. - **Unified API Interface**: Compatible with the OpenAI API format for seamless migration
  9. - **Usage Analytics**: Track requests, tokens used, response times, and costs
  10. - **Multi-provider Support**: Connect to various LLM providers through a single gateway
  11. - **Performance Monitoring**: Compare different models' performance and cost-effectiveness
  12. ## Getting Started
  13. You can use LLM Gateway in two ways:
  14. - **Hosted Version**: For immediate use without setup, visit [llmgateway.io](https://llmgateway.io) to create an account and get an API key.
  15. - **Self-Hosted**: Deploy LLM Gateway on your own infrastructure for complete control over your data and configuration.
  16. ### Self-Hosted With Docker
  17. Use Docker-managed volumes for the unified image. Do not bind-mount a host directory directly to `/var/lib/postgresql/data`, because PostgreSQL initialization inside the container needs to set permissions on that directory and that can fail depending on the host filesystem and ownership.
  18. ```bash
  19. export LLM_GATEWAY_SECRET="$(openssl rand -base64 32 | tr -d '\n')"
  20. export GATEWAY_API_KEY_HASH_SECRET="$(openssl rand -base64 32 | tr -d '\n')"
  21. ./scripts/run-unified-container.sh
  22. ```
  23. If you prefer a one-off `docker run`, use named volumes instead of `~/some-host-dir`:
  24. ```bash
  25. docker volume create llmgateway_postgres
  26. docker volume create llmgateway_redis
  27. docker run -d \
  28. --name llmgateway \
  29. --restart unless-stopped \
  30. -p 3002:3002 \
  31. -p 3003:3003 \
  32. -p 3005:3005 \
  33. -p 3006:3006 \
  34. -p 3007:3007 \
  35. -p 4001:4001 \
  36. -p 4002:4002 \
  37. -v llmgateway_postgres:/var/lib/postgresql/data \
  38. -v llmgateway_redis:/var/lib/redis \
  39. -e AUTH_SECRET="$LLM_GATEWAY_SECRET" \
  40. -e GATEWAY_API_KEY_HASH_SECRET="$GATEWAY_API_KEY_HASH_SECRET" \
  41. ghcr.io/theopenco/llmgateway-unified:latest
  42. ```
  43. ### Using LLM Gateway API
  44. ```bash
  45. curl -X POST https://api.llmgateway.io/v1/chat/completions \
  46. -H "Content-Type: application/json" \
  47. -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
  48. -d '{
  49. "model": "gpt-4o",
  50. "messages": [
  51. {"role": "user", "content": "Hello, how are you?"}
  52. ]
  53. }'
  54. ```
  55. ## Development Setup
  56. 1. Install dependencies and set up the development environment:
  57. ```bash
  58. pnpm i && pnpm run setup
  59. ```
  60. This will install all dependencies, start Docker services, sync the database schema, and seed initial data.
  61. **Note for WSL2 users**: Ensure Docker Desktop is running with WSL integration enabled.
  62. 2. Start development servers:
  63. ```bash
  64. pnpm dev
  65. ```
  66. 3. Build for production:
  67. ```bash
  68. pnpm build
  69. ```
  70. ## Folder Structure
  71. - `apps/ui`: Next.js dashboard frontend
  72. - `apps/playground`: Lounge — consumer AI chat app (Next.js)
  73. - `apps/code`: Next.js Dev Plans + coding tools landing & dashboard
  74. - `apps/airside`: Airside — self-serve provider portal (Next.js)
  75. - `apps/api`: Hono backend
  76. - `apps/gateway`: API gateway for routing LLM requests
  77. - `apps/docs`: Documentation site
  78. - `ee/admin`: Internal admin dashboard
  79. - `packages/db`: Drizzle ORM schema and migrations
  80. - `packages/models`: Model and provider definitions
  81. - `packages/shared`: Shared types and utilities
  82. ## Adding a provider
  83. We do not accept pull requests that add new providers. Inference providers onboard through [Airside](https://airside.llmgateway.io), our self-serve provider portal, where you register and manage your model listings.
  84. ## License
  85. LLMGateway is available under a dual license:
  86. - **Open Source**: Core functionality is licensed under AGPLv3 - see the [LICENSE](LICENSE) file for details.
  87. - **Enterprise**: Commercial features in the `ee/` directory require an Enterprise license; multi-organization administration requires a white-label license. See [ee/LICENSE](ee/LICENSE) for details.
  88. ### Enterprise features include:
  89. - Advanced billing and subscription management
  90. - Full request and response payload retention (Retain All Data); other plans are metadata only
  91. - Custom provider key configurations
  92. - Team and organization management
  93. - Priority support
  94. - And more to be defined
  95. For enterprise licensing, please contact us at contact@llmgateway.io

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.