Agentic-Ops Control Plane

Agentic-Ops Control Plane

Language / Langue : English (Main Documentation) | [Lire la documentation complète en Français (README_FR.md)](README_FR.md)

Official Anthropic Model Context Protocol Registry: io.github.nolll77/agentic-ops (v0.2.0 Active) | Glama MCP Catalog: glama.ai/mcp/servers/nolll77/agentic-ops

mcp-name: io.github.nolll77/agentic-ops

Agentic-Ops is a personal MLOps control-plane project for exploring how AI agents (LLMs) can help investigate operational signals such as Data Drift, Model Staleness, and OOMKilled Pods.

Unlike frameworks that prioritize agent autonomy, it explores SRE-inspired controls: deterministic policies, observability, fail-closed authorization, asynchronous human review, and cryptographic auditability. These features are engineering work in progress, not a claim of production qualification or EU AI Act compliance.

Current release and honest qualification status

• The Python package is distributed on PyPI; multi-architecture container images (linux/amd64, linux/arm64) are distributed on GHCR (ghcr.io/nolll77/agentic-ops) and Docker Hub (nolll78/agentic-ops).
• A local Docker/kind exercise validated an alert webhook through the worker to a simulated investigation episode, and confirmed that its state survived a pod restart on the same PVC. This is local single-node evidence, not a backup-restore or cluster-loss test.
• Release automation tests and version-checks a GitHub release, publishes Python distributions to PyPI, then builds and publishes the matching AMD64/ARM64 container to both GHCR and Docker Hub. See docs/CONTAINER_IMAGE_PUBLICATION.md.
• Release v0.1.4 adds a fail-closed local inventory, SQLite backup/restore commands, and a synthetic load/crash-recovery benchmark. These tools do not themselves qualify a production deployment.
• Release v0.1.5 improves protected console/LLM-probe authentication UX. Render must still have a private ADMIN_API_KEY configured for these protected actions.
• Release v0.1.6 adds verified multi-database/evidence backup sets, a simulation-only approval continuation on the original episode, expanded worker crash and inventory lifecycle tests, and a size-matrix benchmark. It does not certify an off-host restore or enable live actions.
• Release v0.2.0 implements MCP Roadmaps Phases 1, 2, and 3.1 (docs/MCP_ROADMAP.md): bidirectional HTTP + SSE (GET /mcp/events with bounded drop-oldest backpressure and Last-Event-ID replay), dynamic telemetry streams (mlops://telemetry/live/drift defaulting honestly to source="simulated", mlops://telemetry/live/latency), server-initiated sampling/createMessage (request_client_sampling), memoized $\mathcal{O}(\log N)$ Merkle proof generation (< 0.1 ms at $10^5$ indexed leaves), the HMAC-SHA512-sealed technical evidence resource mlops://compliance/eu-ai-act/article-12/audit-pack (explicitly marked third_party_verifiable: false, not legal certification), and an opt-in independent InspectorAgent (AGENTIC_OPS_INSPECTOR_ENABLED=true) enforcing strict monotonic tightening (288 tests passed).
• Production qualification is not claimed. Entra/SCIM, multi-node HA, deployment-target backup restoration, recovery objectives, synchronization of local inventory with a live source, < 500 ms sovereign local LLM failover, and action-by-action live execution remain unqualified.
• The detailed repository-to-production mapping, missing target-specific values, owners, validation evidence, and promotion gates are documented in docs/INDUSTRIAL_PRODUCTION_BLUEPRINT.md.
• Render console/chat probe setup and the exact ADMIN_API_KEY prerequisite are documented in docs/RENDER_CONSOLE_CHAT_TROUBLESHOOTING.md.
• A solo, single-node observation/simulation profile does not require an Entra tenant. Its scope and remaining self-operated qualification work are in docs/SELF_HOSTED_PRODUCTION_PATH.md. This is distinct from enterprise SSO, HA and independent audit anchoring.

For implemented behavior versus open production gates, see docs/INDUSTRIAL_IMPLEMENTATION_STATUS.md and docs/PRODUCTION_READINESS_ROADMAP_AND_GAPS.md.

---

Project Origin: Extracted from nolll77/car_accident into an MLOps Control Plane

Originally, Agentic-Ops was developed as an SRE governance and self-healing component inside the road-safety MLOps platform [`nolll77/car_accident`](https://github.com/nolll77/car_accident) (BAAC data warehouse, Feast feature store, MLflow, and FastAPI inference).

It was extracted into this standalone repository to explore a reusable MLOps control plane:

• Zero Domain Coupling: All dataset-specific logic (car_accident) was removed in favor of a Hexagonal Architecture (`Ports & Adapters`) driven by declarative YAML policies (autonomy_policy.yaml, action_catalog.yaml, risk_register.yaml).
• Designed for adapters: The core engine (Orchestrator FSM, PolicyEngine, Trust Ledger) uses canonical Signal and SystemFacts contracts. Connecting it to another system still requires a suitable adapter, security review, and qualification for that target.

---

Live Demonstration & Validation Reports

The following public Render instance and reports demonstrate selected features. They are not evidence of production qualification or an availability guarantee:

1. Live Serverless Auto-Wake Production Instance (`Render` + `Tailscale` + `cron-job.org`):

• Live Control Plane Status: [`https://agentic-ops-5ebv.onrender.com/`](https://agentic-ops-5ebv.onrender.com/)
• Live Interactive SRE Web Console (`/console`): [`https://agentic-ops-5ebv.onrender.com/console`](https://agentic-ops-5ebv.onrender.com/console)
• 💬 Live Interactive Web Chat Assistant (`/chat`): [`https://agentic-ops-5ebv.onrender.com/chat`](https://agentic-ops-5ebv.onrender.com/chat)
• Live `MCP` (`Model Context Protocol`) Manifest (`/mcp/manifest`): [`https://agentic-ops-5ebv.onrender.com/mcp/manifest`](https://agentic-ops-5ebv.onrender.com/mcp/manifest) *(Full guide: [`docs/MCP_SERVER_GUIDE.md`](docs/MCP_SERVER_GUIDE.md))*
• Live Tailscale Mesh Status (`100.85.*.*` anonymized): [`https://agentic-ops-5ebv.onrender.com/api/tailscale/status`](https://agentic-ops-5ebv.onrender.com/api/tailscale/status)
• Live Read-Only Pull Snapshot (`jakatt/cac_mlops`): [`https://agentic-ops-5ebv.onrender.com/api/cac/snapshot`](https://agentic-ops-5ebv.onrender.com/api/cac/snapshot)

[!TIP]

### 💬 Try the Live SRE Assistant Web Chat (/chat)

Direct Access: [`https://agentic-ops-5ebv.onrender.com/chat`](https://agentic-ops-5ebv.onrender.com/chat)

Ask natural language SRE questions, explore the 435 Failure Modes Taxonomy, simulate the 36 incident scenarios, and inspect the Multi-Agent System (MAS) in real-time with zero tokens consumed.

1. Cloud Sandbox Validation Report (`Docker Agentic Platform`): End-to-end deployment on an isolated micro-VM and line-by-line technical interpretation of all 30 unit, adversarial, and cryptographic security tests: [Read the Cloud Sandbox Deployment & Validation Report (`DOCKER_SANDBOX_VALIDATION.md`)](DOCKER_SANDBOX_VALIDATION.md)
2. Tailscale Pull Interconnection Report with Target Platform [`jakatt/cac_mlops`](https://github.com/jakatt/cac_mlops): Userspace Tailscale tunneling (--tun=userspace-networking / SOCKS5 proxy / DERP relays), strict read-only ingestion across 5 observability sources (Loki, Prometheus, MLflow, Prefect, Evidently), and validation via 13 unit tests: [Read the Tailscale Pull Connector Architecture & Validation Report (`CAC_TAILSCALE_PULL_CONNECTOR.md`)](CAC_TAILSCALE_PULL_CONNECTOR.md)
3. Target Outage & Scaleway/Tailscale Degradation Resilience Guide: Explains why the Control Plane never crashes if the supervised VPS goes down, detailing RemoteServiceStatus.REMOTE_TARGET_OFFLINE error absorption, Fail-Closed governance, autonomous local test execution, and 1-minute self-healing recovery: [Read the Target Outage & Resilience Guide (`docs/TARGET_OUTAGE_AND_RESILIENCE_GUIDE.md`)](docs/TARGET_OUTAGE_AND_RESILIENCE_GUIDE.md)
4. Official Thesis Defense Report (PDF, 40 Pages): Comprehensive SRE & MLOps thesis defense report on governance, multi-layer observability, deterministic FSM, and interconnection with jakatt/cac_mlops: [Read the Official Defense Report (`docs/Rapport_soutenance_Mar25_MLOps_Agentic_Car_Accident.pdf`)](docs/Rapport_soutenance_Mar25_MLOps_Agentic_Car_Accident.pdf)

---

Presentation Slides Explaining this Repository

• Online Google Slides Presentation: [`https://docs.google.com/presentation/d/1fi5rEGww1CexT4OUcDj1d9W8YQhkL5GoXZwWDtCjLA0/edit?usp=sharing`](https://docs.google.com/presentation/d/1fi5rEGww1CexT4OUcDj1d9W8YQhkL5GoXZwWDtCjLA0/edit?usp=sharing)

---

Foundational Knowledge Engineering: The MLOps Failure Taxonomy & Incident War-Room Scenarios Registry

An AI Agent cannot safely diagnose or govern a production MLOps platform without a formal, structured ontology of how machine learning systems fail in the real world. Before writing a single line of orchestration code, Agentic-Ops was grounded in two foundational engineering registries that serve as the cognitive, observability, and decision-m