Documentation
Welcome to the Admina documentation. Admina is an open source governance framework (Apache 2.0) for AI agents and LLM systems. It provides governed AI development through an SDK, transparent proxy, plugin system, CLI, and real-time dashboard.
What is Admina?
Admina is an open framework for governed AI development. It works as both an SDK (in-process GovernedModel, GovernedData, GovernedAgent, ComplianceKit) and a transparent proxy (network). Every AI interaction is automatically governed: PII redacted, injections blocked, loops broken, actions audited, and EU AI Act compliance tracked.
Key properties:
- OISG adequate by default โ Open ยท Intelligent ยท Secure ยท Governed, scored automatically from live runtime state
- Bidirectional โ both requests and responses are governed
- Dual mode โ SDK (in-process) and proxy (network)
- Hybrid runtime โ Rust core (~6µs median) with automatic Python fallback
- Plugin system โ 9 interfaces, 14 built-in implementations
- 5 framework integrations โ OpenClaw, LangChain, CrewAI, n8n, Cheshire Cat
- EU AI Act compliant โ risk classification and gap analysis built in
- Apache 2.0 โ free to use, modify, and distribute forever
Architecture at a glance
Admina runs as a Docker Compose stack of 9 containers covering 4 governance domains: proxy, dashboard, ClickHouse, MinIO, Redis, OpenTelemetry collector, Grafana, mock MCP server, and mock agent.
# The full stack in one command docker compose up --build # Services started: # proxy โ :8080 (governance proxy + REST API) # dashboard โ :3000 (real-time governance UI) # otel โ :4317 (OpenTelemetry collector gRPC) # grafana โ :3001 (metrics and traces) # minio โ :9000 (forensic black box storage)