Weekly digestOne email a week: top 5 new tools + trending stars. Unsubscribe anytime.

Bifrost

maximhq/bifrost
Open source (free)
Needs setup You need your own server plus database, environment variables, domain or mail configuration. Read the official deployment docs first.

Bifrost is an open-source AI gateway for teams running LLM and agent workloads, giving one OpenAI-compatible API for 10,000+ models with failover, caching and budgets. Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

agent-gatewayai-gatewayai-governanceapi-gateway
Bifrost website screenshot

Pricing

Open source (free)

Update history

Last updated 2026-11-22;Listed 2026-11-15

Author

maximhq

Trust info

Listed on 2026-11-15; Last updated 2026-11-22; Data synced on 2026-11-22

Trial feedback

Like it? Vote to help it rank higher.

Deploy command

# Install and run locally
npx -y @maximhq/bifrost

# Or use Docker
docker run -p 8080:8080 maximhq/bifrost

Taken from the project README. You need a server with Docker; you may still need to add environment variables.

From the README

Bifrost is a high-performance AI gateway that unifies access to 23+ providers (OpenAI, Anthropic, AWS Bedrock, Google Vertex, and more) through a single OpenAI-compatible API. Deploy in seconds with zero configuration and get automatic failover, load balancing, semantic caching, and enterprise-grade…

Stars
★ 9.9k
Category rank
#466
Language
Go
License
Apache-2.0
Last updated
2026-11-22
Category
AI assistants & agents
Section
General