bifrost
High-performance enterprise-grade AI gateway supporting 23+ providers, with automatic failover, load balancing, and semantic caching.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 6.0k
- Source
- mcp-github
- Repository
- github.com/maximhq/bifrost
Overview
Bifrost is a high-performance enterprise-grade AI gateway that unifies access to 23+ providers (such as OpenAI, Anthropic, AWS Bedrock, etc.) through a single OpenAI-compatible API. It offers automatic failover, load balancing, semantic caching, and enterprise-grade features. Deploy in seconds with no configuration required. Ideal for enterprise AI applications requiring high availability and performance.
Capabilities
- ▪Unified interface to access multiple AI providers
- ▪Automatic failover and load balancing
- ▪Semantic caching to reduce costs and latency
- ▪Multimodal support (text, image, audio)
- ▪Custom plugin extensions for middleware
Use cases
Setup
npx -y @maximhq/bifrost or docker run -p 8080:8080 maximhq/bifrost
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which AI providers does Bifrost support?
Supports 23+ providers including OpenAI, Anthropic, AWS Bedrock, Google Vertex, and more.
How do I configure Bifrost?
Configuration can be done via the Web UI or using the command-line tool.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.