Bifrost (Maxim AI)
https://www.getmaxim.ai/bifrost
Open-source Go AI gateway from Maxim AI with one OpenAI-compatible API for many models, failover, load balancing, semantic caching, virtual keys and budgets, and a built-in MCP gateway for agents.
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 19 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Tier
- T3
- Section
- Inference platforms & gateways
- Created
- 2025-03-19 repo fix
- Latest release
- last commit 2026-10-29 repo fix
- License
- Apache-2.0 vendor fix
- GitHub
- https://github.com/maximhq/bifrost (9198★) repo fix
- Pricing
- searched not found fix
- Funding
- searched not found fix
- Freshness
- 2026-10-29 fix
- Layer
- model-infra repo fix
- Licensing
- open-source vendor fix
- Protocols
- mcp-client, openai-compatible repo fix
- Compliance
- gdpr, hipaa, iso27001 vendor fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
Try Bifrost Enterprise free for 14 days. Try Bifrost Enterprise free for 14 days.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- searched not found
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- yes
Similar systems
Other inference platforms & gateways in the catalog, ranked by inbound references.
- LiteLLM T1
BerriAI's open-source LLM gateway — unified OpenAI-format API for 100+ providers; LiteLLM Proxy adds budgets, fallbacks, observability, rate-limiting.
- OpenRouter T1
Unified API + marketplace for 300+ models — pay-as-you-go credits, automatic fallback, model arena. Used as default LLM router by many JS/TS agents.
- Together AI T1
Cloud platform for OSS LLM inference and fine-tuning — serverless inference, dedicated endpoints, fine-tuning API, training cluster.
- Fireworks AI T1
Fast inference platform for OSS LLMs — custom Cuda kernels, speculative decoding, multi-LoRA serving. Targets latency-sensitive production use cases.
- vLLM T1
Open-source LLM inference engine with PagedAttention — high-throughput batching, paged KV-cache. UC Berkeley origin; de-facto OSS inference stack.
- Portkey AI T2
AI gateway + observability — load balancing across 200+ LLMs, retries, caching, eval, prompts. Open-source Gateway + commercial Portkey Cloud. Acquired by Palo Alto Networks (closed about 2026-06); now sold as Prisma AIRS AI Gateway (GA 2026-07-16).
Sources (18 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Framework vendor
- What it does & what's distinct Open-source Go AI gateway from Maxim AI with one OpenAI-compatible API for many models, … vendor
- Claims / benefits Try Bifrost Enterprise free for 14 days. Try Bifrost Enterprise free for 14 days. vendor
- Created 2025-03-19 repo
- Latest release last commit 2026-10-29 repo
- License Apache-2.0 vendor
- GitHub https://github.com/maximhq/bifrost (9198★) repo
- Mindshare 9198 GitHub stars repo
- OTel yes vendor
- Project & sources https://www.getmaxim.ai/bifrost ; https://github.com/maximhq/bifrost vendor
- obs-opentelemetry yes vendor
- cost-semantic-caching yes vendor
- licensing-bucket open-source vendor
- taxonomy-three-layer-rollup model-infra repo
- compliance-certifications gdpr,hipaa,iso27001 vendor
- sdk-languages go,rest repo
- protocol-support mcp-client,openai-compatible repo
- maturity ga repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-30 Added to the catalog #347
Related systems
References (32)
- Amazon Bedrock Guardrails integrates with — Bifrost guardrails integrations include AWS Bedrock Guardrails. (verified 2026-10-29)
- Anthropic Claude (foundation models) integrates with — Bifrost supported-providers docs have a provider page for Anthropic. (verified 2026-10-29)
- Azure AI Content Safety Prompt Shields integrates with — Bifrost guardrails integrations include Azure Content Safety. (verified 2026-10-29)
- Claude Code (Anthropic) integrates with — Bifrost docs have a CLI-agent integration page for Claude Code. (verified 2026-10-29)
- Cohere Command R+ / Command A integrates with — Bifrost supported-providers docs have a provider page for Cohere. (verified 2026-10-29)
- CrowdStrike Falcon Guardian (formerly Pangea AI Guard) integrates with — Bifrost guardrails integrations include CrowdStrike AIDR. (verified 2026-10-29)
- Cursor (IDE) integrates with — Bifrost docs have a CLI-agent integration page for Cursor. (verified 2026-10-29)
- Datadog Agent Observability (LLM Observability) integrates with — Bifrost docs have a native Datadog integration page (APM traces, LLM Observability, metrics). (verified 2026-10-29)
- DeepSeek R1 / V3 family integrates with — Bifrost supported-providers docs have a provider page for DeepSeek. (verified 2026-10-29)
- Fireworks AI integrates with — Bifrost supported-providers docs have a provider page for Fireworks. (verified 2026-10-29)
- GitHub Copilot (Agent Mode) integrates with — Bifrost docs have a CLI-agent integration page for GitHub Copilot. (verified 2026-10-29)
- Google Cloud Model Armor integrates with — Bifrost guardrails integrations include Google Model Armor. (verified 2026-10-29)
- Google Gemini 3 family integrates with — Bifrost supported-providers docs have a provider page for Google Gemini. (verified 2026-10-29)
- LangChain (framework) integrates with — Bifrost SDK integrations include a drop-in proxy page for the LangChain SDK. (verified 2026-10-29)
- LiteLLM integrates with — Bifrost SDK integrations include a drop-in proxy page for the LiteLLM SDK. (verified 2026-10-29)
- Mistral Large 2 / Mixtral family integrates with — Bifrost supported-providers docs have a provider page for Mistral. (verified 2026-10-29)
- OpenAI Codex CLI integrates with — Bifrost docs have a CLI-agent integration page for Codex CLI. (verified 2026-10-29)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — Open-source Go AI gateway from Maxim AI with one OpenAI-compatible API for many models, failover, load balancing, semantic caching, virtual keys and budgets, and a built-in MCP gateway for agents.
- Opencode (SST) integrates with — Bifrost docs have a CLI-agent integration page for OpenCode. (verified 2026-10-29)
- OpenRouter integrates with — Bifrost supported-providers docs have a provider page for OpenRouter. (verified 2026-10-29)
- Patronus AI integrates with — Bifrost guardrails integrations include Patronus AI. (verified 2026-10-29)
- Pinecone integrates with — Bifrost docs have a Pinecone vector-database integration page for semantic caching. (verified 2026-10-29)
- Presidio integrates with — Bifrost guardrails integrations include Microsoft Presidio. (verified 2026-10-29)
- Pydantic-AI integrates with — Bifrost SDK integrations include a drop-in proxy page for Pydantic AI. (verified 2026-10-29)
- Qdrant integrates with — Bifrost docs have a Qdrant vector-database integration page for semantic caching. (verified 2026-10-29)
- Replicate integrates with — Bifrost supported-providers docs have a provider page for Replicate. (verified 2026-10-29)
- Roo Code integrates with — Bifrost docs have a CLI-agent integration page for Roo Code. (verified 2026-10-29)
- SGLang integrates with — Bifrost supported-providers docs have a provider page for SGLang. (verified 2026-10-29)
- vLLM integrates with — Bifrost supported-providers docs have a provider page for vLLM. (verified 2026-10-29)
- Weaviate integrates with — Bifrost docs have a Weaviate vector-database integration page for semantic caching. (verified 2026-10-29)
- xAI Grok 4 integrates with — Bifrost supported-providers docs have a provider page for xAI. (verified 2026-10-29)
- Zed (Agentic Editing) integrates with — Bifrost docs have a CLI-agent integration page for Zed Editor. (verified 2026-10-29)