Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Bifrost is an AI gateway that gives applications one OpenAI-compatible API for accessing models from more than 23 providers. It is used to route model requests, handle provider failover and load balancing, and apply features such as caching, guardrails, and MCP gateway support.
Latest release helm-chart-v2.1.38 — Helm Chart v2.1.38 · 4 Sept 2026
These files are maximhq/bifrost's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 12,300 tok .claude/skills/add-pricing-field/SKILL.md A 123 tok .claude/skills/api-validator/SKILL.md A 78 tok .claude/skills/changelog-writer/SKILL.md A 73 tok .claude/skills/docs-writer/SKILL.md A 83 tok .claude/skills/e2e-test/SKILL.md A — .claude/skills/harness-test-writer/SKILL.md A 133 tok .claude/skills/helm-update/SKILL.md A 97 tok .claude/skills/investigate-issue/SKILL.md A 78 tok .claude/skills/release-checklist/SKILL.md A 82 tok .claude/skills/resolve-pr-comments-stack/SKILL.md A 99 tok .claude/skills/resolve-pr-comments/SKILL.md A — .claude/skills/review-pr/SKILL.md A 60 tok .claude/skills/stack-absorb/SKILL.md A 125 tok .claude/skills/split-commit-into-stack/SKILL.md A 96 tok