Summary

AIHelms is an enterprise-grade AI resource management platform designed to provide businesses with centralized control over their AI assets, costs, and value generation. It targets decision-makers, administrators, and end-users, offering benefits such as transparent cost tracking, unified access to AI models, and quantifiable AI value metrics. The platform aims to alleviate common enterprise anxieties around AI spending and utilization by providing robust management and reporting capabilities.

How It Works

The platform employs a modern stack with Python/FastAPI for the backend, Vue.js/TypeScript for the frontend, PostgreSQL for data persistence, and Redis for caching. It acts as a unified gateway, enabling administrators to manage diverse AI resources, including multi-vendor models and internal AI tools (Skills/MCPs). Key architectural choices focus on granular cost attribution down to the token level, multi-dimensional budget control (per user, department, project, model) with configurable soft and hard limits, and a unified identity system for employees accessing AI resources.

Quick Start & Requirements

• Primary Install: Docker Compose.
• Prerequisites: Docker 20.10+, Docker Compose v2+. Minimum 4-core CPU, 8GB RAM recommended.
• Setup: Clone the repository, copy .env.example to .env, configure environment variables (especially database password, JWT secret, admin password), and run docker compose up -d.
• Access: User client at http://your-host, Admin backend at http://your-host/admin, API docs at http://your-host/api/docs.
• Default Admin: admin / password specified in .env (SUPER_ADMIN_PASSWORD).

Highlighted Details

• Cost Management: Features dual-track cost accounting (external provider fees vs. internal settlement prices) and real-time, token-level cost attribution.
• Budget Control: Supports multi-dimensional budget allocation (per person, department, project, model) with configurable soft (warning) and hard (cutoff) limits.
• Unified Access: Provides a single AI identity and API key for each employee to access all approved AI resources.
• Resource Management: Enables centralized model onboarding from multiple vendors, load balancing across deployments, and management of internal AI tools (Skills/MCPs).
• Value Metrics: Quantifies AI value through coverage rates, user activity, cost-effectiveness analysis, and automated reporting.

Maintenance & Community

The project is at release v0.1.0, indicating early development. A roadmap includes features like AI health monitoring, sensitive information detection, inter-agent collaboration (A2A), and context caching. Community interaction is facilitated via a WeChat group and GitHub Issues for feedback and bug reporting.

Licensing & Compatibility

The project is licensed under GPL-3.0. This is a strong copyleft license, meaning any derivative works or modifications distributed must also be made available under the GPL-3.0 license. This may impose restrictions on integration into closed-source commercial products.

Limitations & Caveats

The platform is in its early stages (v0.1.0). Features like "AI Employee" and "A2A" are marked as "in progress" or are part of the future roadmap, suggesting they are not yet fully implemented. The GPL-3.0 license requires careful consideration for commercial adoption, particularly regarding the distribution of modified versions.