https://localai.io/docs/administration/index.htmlRun, monitor and govern a LocalAI instance.Hugoen-GBhttps://localai.io/docs/administration/overview/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/overview/index.htmlThe Operate console: one page that shows if anything is wrong with your LocalAI instance.https://localai.io/docs/administration/authentication/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/authentication/index.htmlTurn on accounts, roles, API keys and OAuth login for LocalAI.https://localai.io/docs/administration/runtime-settings/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/runtime-settings/index.htmlChange LocalAI settings in the web interface without a restart.https://localai.io/docs/administration/traffic/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/traffic/index.htmlThe Traffic tab of the Administration console answers three questions: how much is the server used, what failed, and how are the machine and the models doing. It opens on an overview and has a second row of links: Overview, Usage, Models, GPU and host, Traces, Middleware and Prometheus. One time window (24 hours, 7 days, 30 days or all time) is shared by the Overview, Usage and Models pages.https://localai.io/docs/administration/activity/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/activity/index.htmlWatch, cancel and retry model and backend installs from the WebUIhttps://localai.io/docs/administration/backend-monitor/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/backend-monitor/index.htmlLocalAI provides endpoints to monitor and manage running backends. The /backend/monitor endpoint reports the status and resource usage of loaded models, /backend/load pre-loads a model into memory, and /backend/shutdown allows stopping a model’s backend processes. In distributed mode, a named shutdown stops both a process local to the controller and every placement registered on workers. All three are admin-only. Monitor API Method: GET Endpoints: /backend/monitor, /v1/backend/monitor Request The model to monitor is passed as a query parameter:https://localai.io/docs/administration/tracing/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/tracing/index.htmlLocalAI can retain recent API exchanges and backend operations for inspection on the Traces page in the management interface. Enable tracing in runtime settings or with the existing tracing configuration. API requests appear while they are still running. Their elapsed duration updates when the page refreshes, and the result column marks them as in progress until the response completes. In-flight requests live only in memory; the completed exchange is what LocalAI adds to the bounded, persistent history.https://localai.io/docs/administration/diagnostics/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/diagnostics/index.htmlLocalAI provides two independently opt-in diagnostics: a private Go profiling listener and structured phase timing events. Both default to disabled. Debug logging alone enables neither feature. Scope and configuration These options apply to local-ai run, including a distributed frontend. They do not enable diagnostics in separately launched workers or provide backend-native llama.cpp profiling. Diagnostics has no MCP, admin, or public API surface and no UI controls. State is per-instance, not shared between replicas. Profiles describe the frontend Go process, not the whole cluster.https://localai.io/docs/administration/middleware/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/middleware/index.htmlPer-model PII redaction and policy-based request routinghttps://localai.io/docs/administration/cloud-proxy/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/cloud-proxy/index.htmlForward requests to OpenAI, Anthropic, OrcaRouter, or any compatible providerhttps://localai.io/docs/administration/mitm-proxy/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/mitm-proxy/index.htmlRedact PII from cloud-AI traffic without LocalAI holding API keyshttps://localai.io/docs/administration/distributed-mode/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/distributed-mode/index.htmlRun several LocalAI frontends and worker nodes with PostgreSQL and NATS.https://localai.io/docs/administration/p2p-federated-inference/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/p2p-federated-inference/index.htmlTip Looking for production-grade horizontal scaling with PostgreSQL and NATS? See Distributed Mode. Choosing a distributed mode LocalAI can spread inference across multiple machines in three ways. Pick the one that matches your setup:https://localai.io/docs/administration/p2p-api/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/p2p-api/index.htmlLocalAI supports peer-to-peer (P2P) networking for distributed inference. The P2P API endpoints allow you to monitor connected worker and federated nodes, retrieve the P2P network token, and get cluster statistics. For an overview of distributed inference setup, see Distributed Inference. Endpoints List all P2P nodes Method: GET Endpoint: /api/p2p Returns all worker and federated nodes in the P2P network.https://localai.io/docs/administration/mlx-distributed/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/mlx-distributed/index.htmlMLX distributed inference allows you to split large language models across multiple Apple Silicon Macs (or other devices) for joint inference. Unlike federation (which distributes whole requests), MLX distributed splits a single model’s layers across machines so they all participate in every forward pass.https://localai.io/docs/administration/reverse-proxy-tls/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/reverse-proxy-tls/index.htmlConfigure LocalAI behind a TLS termination reverse proxy (HAProxy, Apache, Nginx, APISIX)https://localai.io/docs/administration/embedded-routing-log/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/embedded-routing-log/index.htmlGo applications that embed LocalAI can retain the bounded in-memory router decision log without enabling billing statistics: config.WithDisableStats(true), config.WithRouterDecisionLog(true), The explicit routing-log option retains classifier, selected-model, cache and score diagnostics. It does not create a billing recorder or record token usage. Without that opt-in, disabling stats still disables both logs as before. config.DisableMetricsEndpoint also prevents failover health-gauge registration; failover routing itself continues to run.https://localai.io/docs/administration/troubleshooting/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://localai.io/docs/administration/troubleshooting/index.htmlFind the cause of common LocalAI problems: startup, models, GPUs and downloads.