beizhu-1209/AIHelms
企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治理 AI 资产。 observed · 2026-08-28
Health v2 · maintenance only
81/100
- Activity 99
- Release rhythm 99
- Longevity 8
Flags: young
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: 3.5
- age_days: 116
- days_rel: 8
- days_push: 7
- n_releases_24m: 17
Adoption not part of the score
1022 stars · 102 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
AIHelms is a self-hosted enterprise AI resource governance platform that provides a unified AI gateway for managing models from OpenAI, Azure, Claude, DeepSeek and other providers, with per-employee AI identities (API keys), budget controls, and centralized Skill/MCP tool registration and distribution. It offers dual internal/external pricing, token-level cost attribution, security auditing, and efficiency reporting to help enterprises control AI spend and measure ROI.
Use cases
- manage enterprise llm api keys and budgets centrally
- track token costs per team and project across ai providers
- unified gateway for openai claude and deepseek models
- distribute mcp servers and skills to employees with approval
- audit ai usage and generate cost efficiency reports
- set rate limits and hard budget caps on ai spending
- self-host an ai gateway with cost attribution
When to choose
- you need enterprise-wide visibility and cost control over employee AI usage
- you want one gateway managing multiple model vendors with OpenAI and Anthropic API compatibility
- you need per-user API keys with budgets, rate limits, and approval workflows
- you want centralized registration and distribution of MCP servers and Skills
When to avoid
- you are an individual developer who just needs a simple API proxy without governance
- you need fully automated blocking of risky prompts or skills - policies only generate reports for human review
- you require certified compliance tooling - the platform is not OWASP certified
- you want a managed cloud service - this is self-hosted via Docker Compose
Facets
application · maturity active
api-gateway llm-inference monitoring analytics auth rate-limiting security mcp agent-framework self-hosted large-language-models developer-tools self-hosted analytics security erp self-hosted python llm-gateway token-accounting cost-management ai-governance model-management fastapi vue3 litellm enterprise-ai skill-marketplace ai-agents docker web-server linux
6 sources
- readme: https://github.com/beizhu-1209/AIHelms · fetched 2026-08-28 · 9b5e2a0fd99d
- homepage: http://www.aihelms.cn/ · fetched 2026-08-29 · 046d650b18f6
- site_page: http://www.aihelms.cn/docs · fetched 2026-08-29 · 1684b764db4f
- site_page: http://www.aihelms.cn/docs/getting-started/deployment · fetched 2026-08-29 · b2e75234f6fc
- site_page: http://www.aihelms.cn/docs/guide/user · fetched 2026-08-29 · b838432812f7
- site_page: http://www.aihelms.cn/docs/guide/faq · fetched 2026-08-29 · df8e3439ee28
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| beizhu-1209/AIHelms | main | 81 |
For agents
markdown · JSON · MCP: product_card(name="beizhu-1209/AIHelms")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem