Open source Docker Compose Local AI
Observe every signal. Investigate with AI.
A composable observability and AIOps platform for Docker hosts,
microservices, and local LLM workloads—with metrics, logs, traces,
MCP endpoints, runbook retrieval, and Generative UI in one stack.
terminal
$ docker compose up -d
$ docker compose ps
prometheus running
grafana running
loki running
tempo running
Unified telemetry Prometheus, Grafana, Loki, Tempo, and OpenTelemetry. AIOps interfaces Grafana and Prometheus MCP endpoints for operational tooling. Local-first copilot Ollama, Chainlit, OpenUI, and pgvector remain on your network.
Architecture overview
Dockprom-AI operates as a coordinated dual-stack architecture communicating across a high-isolation bridge network (monitor-net):
Core observability and AIOps stack: telemetry ingest, time-series storage, tracing, log aggregation, alerting pipelines, and MCP endpoints.
Generative UI and copilot stack (compose-genui.yaml): conversational workflows, vector search over runbooks, and interactive remediation interfaces.
Core observability stack
The core pipeline captures metrics, distributed traces, and container logs with deep Linux kernel and host hardware instrumentation:
DOCKER HOST PLATFORM Linux Ollama Gateway (Envoy) Port :11435 • v1.40.2 OTLP Traces & RPS Metrics Host Native Ollama 0.0.0.0:11434 • Host GPU Llama 3.2 • nomic-embed-text AI Coding Agents Claude Desktop • Cursor Cline • Roo Code • Chainlit SSE Transport (v2.1) Grafana MCP Server Port :8000/sse • v2.1.1 Prometheus MCP Server Port :8080/sse • v0.18.0 Caddy v2 Proxy :3000, :9090, :9093 Bcrypt Basic Auth v2.11.7-alpine Grafana 13.3.0 Port :3000 • Dashboards Explore • LogQL & TraceQL Prometheus v3.15.1 Port :9090 • PromQL TSDB Head Compaction • 200h Ret Alertmanager v0.34.1 Port :9093 • Deduplication Webhooks & Routing Docker Workloads & Hosts Logporter v1.5.0 :9333 • Container CPU/Mem/Logs Node Exporter v1.12.1 :9100 • Linux Kernel/FS/IO OTel Collector Contrib v0.164.0 OTLP Ingest :4317 / :4318 Pipelines: Traces • Logs • Metrics Prom Exp :8889 Tempo v3.1.1 :3200 • Distributed Tracing WAL & Parquet storage Loki v3.7.9 :3100 • TSDB v13 Schema Structured metadata Keep AIOps v0.54.3 UI :8082 • API :8080 Alert Enrichment & Correlation Mattermost Team 12.0.1 Port :8065 • Incident Channels Automated Webhooks & ChatOps PostgreSQL 17 + pgvector (Unified Database) Container: mattermost-db • Port :5432 • pgvector/pgvector:pg17 Keep AIOps Store db: keep • alert events Mattermost Storage db: mattermost • users/chat RAG Vector Embeddings db: rag_storage • vector(768) HNSW postgres-exporter v0.20.1 :9187 • pg_stat_statements Buffer hits • locks • latency
Generative UI and copilot pipeline
The GenUI pipeline connects user prompts to real-time telemetry, semantic runbook embeddings, and streaming React components:
GENUI & AIOPS COPILOT STACK compose-genui SRE Operator "Diagnose CPU load & render remediation tool" Chainlit AIOps Copilot Port :8050 • chainlit-genui Step 1: pgvector RAG Lookup Embedding cosine similarity Step 2: MCP Tool Invocation Query PromQL & Loki logs Step 3: Streaming Reasoning OpenUI Lang component stream Interactive Preview iframe Embed pgvector RAG Store (PostgreSQL 17) Database: rag_storage • Table: operational_runbooks HNSW Cosine Vector Index (<=>) vector(768) • Matches nomic-embed-text Observability MCP Servers HTTP / Server-Sent Events (SSE) Grafana MCP :8000/sse Prometheus MCP :8080/sse Envoy Gateway & Host Ollama http://ollama-gateway:11435 -> 0.0.0.0:11434 32k Context Window (OLLAMA_CONTEXT_LENGTH=32768) Llama 3.2 • nomic-embed-text • Streamed Tokens Open-Intelligent-UI Canvas Port :3001 • Container: open-intelligent-ui • Next.js + @openuidev/react Container CPU Usage 92.4% Threshold Exceeded Suggested SRE Action Restart high-consumer container: ⚡ Restart Container Live PromQL Telemetry rate(container_cpu[1m])
Quickstart
The GenUI stack assumes the core services and external monitor-net network
already exist.
export PGVECTOR_URL='postgresql://<user>:<password>@mattermost-db:5432/rag_storage'
docker compose -f compose-genui.yaml config --quiet
docker compose -f compose-genui.yaml up -d --build
Open Chainlit at http://localhost:8050 and Open-Intelligent-UI at
http://localhost:3001.
Continue with the host prerequisites ,
environment reference , and
GenUI architecture .