Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
maximhq/bifrost
AI网关,统一接入多家模型,带负载均衡和安全管理。An open-source AI gateway that routes requests to 1000+ models with sub-millisecond overhead, built for teams that need reliability and speed.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
快速启动AI网关
通过网页管理配置
自动平衡AI请求
设置内容安全护栏
监控调用成本
Route requests to any LLM model sources with one config
Balance load across models automatically
Enforce safety rules on every prompt
Monitor costs and usage in real time
Run locally or in Docker in under a minute
上手GET STARTED
npx -y @maximhq/bifrost选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commands.claude/skills/add-pricing-field/SKILL.md
allowed-tools: Bash
02读写本地文件Reads and writes local files.claude/skills/add-pricing-field/SKILL.md
allowed-tools: Edit
03读写本地文件Reads and writes local files.claude/skills/add-pricing-field/SKILL.md
allowed-tools: Write
04执行 Shell 命令Runs shell commands.claude/skills/api-validator/SKILL.md
allowed-tools: Bash
05控制浏览器Controls a browser.claude/skills/e2e-test/SKILL.md
description: Write, run, debug, audit, and auto-update Playwright E2E tests for the Bifrost UI. Use when asked to create new E2E tests, add
06控制浏览器Controls a browser.claude/skills/investigate-issue/SKILL.md
Common libraries: `mark3labs/mcp-go` (MCP protocol), `stretchr/testify` (test assertions), `react` (UI framework), `playwright` (E2E testing
静态扫描发现多个中等风险:允许执行 Shell 命令(Bash)、读写本地文件(Edit、Write)以及控制浏览器(Playwright E2E 测试)。这些权限可能被恶意利用,需要严格限制运行环境和访问控制。The static scan found that Bifrost can execute shell commands and read local files through its allowed tools, and it controls a browser for E2E testing. Review these permissions before deploying in a sensitive environment.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+15.4%+15.4%
8.5k → 9.8k stars · 49 个快照8.5k → 9.8k stars · 49 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
3 条外部提及3 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
近7天有183次提交,项目更新非常频繁,功能迭代快。50x faster than LiteLLM at p99 latency
HN_STORY · 3 points · 0 comments
HN_STORY · 1 points · 0 comments
HN_STORY · 8 points · 1 comments
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
}
],
"apiKey": "Is with real credentials (`OPENAI_API_KEY`, `AWS_SECRET_ACCESS_KEY`, and ~20 othe",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 3,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 3,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "ateway ```bash # Install and run locally npx -y @maximhq/bifrost # Or use Docke",
"skillMdTotal": 15,
"skillMdErrors": [
{
"path": ".claude/skills/e2e-test/SKILL.md",
"error": "no frontmatter"
},
{
"path": ".claude/skills/resolve-pr-comments/SKILL.md",
"error": "no frontmatter"
}
],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 0,
"security": 1,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "13 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 29 markdown files",
"weight": 0.75
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/add-pricing-field/SKILL.md",
".claude/skills/api-validator/SKILL.md",
".claude/skills/changelog-writer/SKILL.md",
".claude/skills/docs-writer/SKILL.md",
".claude/skills/e2e-test/SKILL.md",
".claude/skills/harness-test-writer/SKILL.md",
".claude/skills/helm-update/SKILL.md",
".claude/skills/investigate-issue/SKILL.md",
".claude/skills/release-checklist/SKILL.md",
".claude/skills/resolve-pr-comments-stack/SKILL.md",
".claude/skills/resolve-pr-comments/SKILL.md",
".claude/skills/review-pr/SKILL.md",
".claude/skills/security-audit/SKILL.md",
".claude/skills/split-commit-into-stack/SKILL.md",
".claude/skills/stack-absorb/SKILL.md"
],
"skillMdFetched": 15
}