OSS TanbouOn this page
Overview
LLM Gateway exposes an OpenAI-compatible interface while routing requests to providers such as OpenAI, Anthropic, and Google Vertex AI. It centralizes provider credentials, token and cost analytics, and performance monitoring.
Features and best fit
Based on official documentation; not hands-on tested · Content checked:
Key features
Route an OpenAI-compatible API to multiple providers
Applications can keep a common request format while the gateway sends traffic to different LLM providers and models.
Sources: [2]
Centralize token, cost, latency, and provider-key management
The gateway tracks requests, token usage, response time, and cost while consolidating provider credentials.
Sources: [2]
Best fit
Fits teams separating provider choice and observability from application code
It is useful when multiple applications should share provider routing, credential management, and monitoring.
Sources: [2]
Before adoption
Self-hosting operates several persistent services
The unified and development setups include PostgreSQL, Redis, dashboards, APIs, and gateway processes, requiring secret and volume management.
Sources: [2]
Official sources
- [1]theopenco/llmgateway repository(2026-09-30)
- [2]LLM Gateway README(2026-09-30)
- [3]LLM Gateway core license(2026-09-30)
- [4]LLM Gateway Enterprise license(2026-09-30)
- [5]LLM Gateway v1.19.0 release(2026-09-30)
Supplemental curator note
LLM Gateway places OpenAI, Anthropic, Vertex AI, and other providers behind a unified API. Core functionality is AGPLv3, while the ee/ directory uses a separate Enterprise License for commercial features such as multi-organization administration, so the repository should not be treated as uniformly open-source licensed.
Try it in 3 steps
- 1
Clone v1.19.0
Check out the pinned stable release tag.
git clone --depth 1 --branch v1.19.0 https://github.com/theopenco/llmgateway.git && cd llmgateway - 2
Generate gateway secrets
Create secrets for authentication and API-key hashing in the self-hosted instance.
export LLM_GATEWAY_SECRET="$(openssl rand -base64 32 | tr -d "\n")" export GATEWAY_API_KEY_HASH_SECRET="$(openssl rand -base64 32 | tr -d "\n")" - 3
Start the unified container
Launch the unified stack including PostgreSQL and Redis, using Docker named volumes for persistent data.
./scripts/run-unified-container.sh
Growth
Growth trends · Last 30 days
1,666 Stars
Trend data is still being collected.
Built with
Categories and tags
GitHub data
GitHub dataView detailed GitHub data
GitHub Topics
- ai
- ai-gateway
- analytics
- anthropic
- api-key-management
- claude
- codex
- enterprise
- guardrails
- inference
- llm
- llm-gateway
- Stars
- 1,666
- Forks
- 190
- Watchers
- 3
- Open issues
- 74
- Owner type
- Organization
- Primary language
- TypeScript
- License
- Not determined
- Repository last updated
- Sep 29, 2026
Related information
Write a related articleShare a guide or use case for this OSS in Markdown. Articles are published after administrator approval.
Explore next
- PostHog40,022 Stars
2 shared tag(s) · 2 shared category(s)
Unify product analytics, session replay, feature flags, experiments, errors, logs, and AI observability in one data platform
Python - OpenSERP1,427 Stars
2 shared tag(s) · 2 shared category(s)
combine multiple search services and content extraction behind one API
Go - n8n206,322 Stars
2 shared tag(s) · 1 shared category(s) · Same language
Connect visual workflows, code, AI agents, and human approvals in one automation runtime
TypeScript - Firecrawl186,787 Stars
2 shared tag(s) · 1 shared category(s) · Same language
a web context API for search, scraping, crawling, and browser interaction
TypeScript - Bifrost8,459 Stars
3 shared tag(s) · 4 shared category(s)
centralize multiple LLM providers behind one high-performance gateway
Go - Dify157,552 Stars
3 shared tag(s) · 2 shared category(s) · Same language
design and publish AI workflows, retrieval, and agents on one platform
TypeScript
Report incorrect information
Tell us if any listing information is incorrect or outdated.