Directory

Agents and platforms, as they actually stand today

Grouped by what each thing is, not by how it's marketed. Every entry links to a primary source. The status tag is a rough, honest read on maturity: whether it's a shipping product, something actively evolving, or an early community or research project. Vendor claims are their own; treat the status tags as this site's best judgment, not a guarantee.

Full-stack vendor platforms

The deepest integrations come from vendors who control the hardware and telemetry pipeline end to end. These agents are built into the router, switch, and wireless operating systems themselves, which gives them access to signal a third-party tool doesn't get.

NA-001shipping

Marvis Virtual Network Assistant

HPE Juniper Networks

One of the earliest and most mature entries in this space. Marvis sits on top of Juniper's Mist AI telemetry and answers plain-language questions about wired, wireless, and SD-WAN health. "Marvis Actions" goes further and proactively remediates common issues: bad cables, missing VLANs, DHCP and 802.1X failures. "Marvis Minis" continuously simulate client connections in the background so problems surface before a real user hits them.

wired · wireless · SD-WAN verified Jul 2026 visit →
NA-002shipping

Cisco AI Assistant for Networking

Cisco Systems

A conversational layer across Catalyst Center and the Meraki dashboard, built on retrieval-augmented generation against Cisco's own documentation and telemetry, with filters aimed at catching hallucinated answers. The more interesting pieces are narrower: AI-RRM schedules radio channel changes during actual quiet hours instead of reacting to every blip, and an AI-driven packet analyzer can trigger its own captures and hand back a root cause instead of a raw pcap.

wireless · assurance · WAN verified Jul 2026 visit →
NA-003shipping

AVA (Autonomous Virtual Assist)

Arista Networks

Built on Arista's Network Data Lake, AVA's core trick is learning what "normal" looks like across a fleet so it can narrow in on the small residue of anomalous behavior rather than every deviation. That same approach has been extended into AI data center fabrics, watching ECN marks, PFC pause frames, and buffer utilization on GPU clusters. In the campus and SD-WAN side, "Ask AVA" translates zero-trust segmentation policy into plain language.

data center · campus · SD-WAN verified Jul 2026 visit →
NA-004shipping

Extreme AI Expert

Extreme Networks

Part of Extreme Platform ONE, positioned as a multimodal conversational agent spanning both networking and security tasks instead of staying in one lane. Newer to market than Marvis or AVA, so the feature set is worth watching mature before taking the launch materials at face value.

networking · security verified Jul 2026 visit →

Observability & overlay platforms

Vendor-agnostic tools that sit above a mixed-vendor environment, pulling in telemetry through open APIs and correlating across gear the vendor platforms above can't see into.

NA-005shipping

FlowAI & Intelligent Agents

Itential

The interesting design choice here is architectural: the AI never gets to actually touch the network. It proposes a workflow, and a separate deterministic orchestration layer enforces approvals, schedules the change into a maintenance window, executes it, validates the result, and rolls back automatically if something fails. It's one of the clearer answers to "how do you let a language model near production without losing control."

orchestration · governance verified Jul 2026 visit →
NA-006shipping

IP Fabric

IP Fabric

Discovers a network read-only over SSH and APIs and builds a mathematically accurate digital twin of its actual, current state. The agent angle is an Enterprise MCP Server that lets tools like Claude or Copilot query that twin directly (end-to-end path lookups, shadow firewall rules, missing segmentation) instead of guessing from general networking knowledge.

digital twin · assurance verified Jul 2026 visit →
NA-007shipping

Forward Networks

Forward Networks

Similar territory to IP Fabric: a digital twin used to verify proposed changes deterministically before they touch production. It's here for a different reason than most agents on this page: a reminder that "verify before you act" doesn't always need an LLM in the loop, just good math and a reliable model of the network.

digital twin · verification verified Jul 2026 visit →
NA-008shipping

Selector Copilot

Selector AI

A multi-domain observability platform with a "network language model" front end, ingesting SNMP, gRPC, NetFlow, BGP, and syslog data. Engineers query across all of it in plain language instead of a proprietary query syntax.

observability · NLM verified Jul 2026 visit →
NA-009shipping

Edwin AI

LogicMonitor

A narrower, ITOps-focused agent aimed squarely at alert fatigue: consolidating and reasoning across infrastructure alarms so a human sees one correlated incident instead of forty related pages.

AIOps · alerting verified Jul 2026 visit →
NA-010actively developed

AI Control Tower

ServiceNow

Aimed at telecom operators rather than enterprise networks: a control plane concept meant to connect business intent, risk, and network execution across OSS, BSS, and CRM systems. More of an emerging architecture than a single deployable product today.

telecom · OSS/BSS verified Jul 2026 visit →
NA-026shipping

Fabrix.ai Network Observability

Fabrix.ai

A vendor-agnostic observability layer, not a single-purpose agent: it ingests network, application, and infrastructure telemetry through more than a thousand pre-built connectors (Cisco, Juniper, Arista, Prometheus, Datadog, and more), correlates events across domains to find root cause, and can trigger closed-loop remediation through Ansible, Python, or Cisco NSO playbooks.

multi-vendor · telemetry verified Jul 2026 visit →

Security-centric agents

Agents built specifically for threat detection and policy enforcement, where the tolerance for error is lower and the models involved are often purpose-trained rather than a general-purpose LLM.

NA-011shipping

Precision AI / Strata Copilot

Palo Alto Networks

Powers Palo Alto's Cloud-Delivered Security Services with purpose-built security models rather than a general-purpose LLM, aimed at automated threat detection, zero-trust enforcement, and DNS/URL filtering at the speed those decisions need to happen.

threat detection · zero trust verified Jul 2026 visit →
NA-012shipping

FortiAI

Fortinet

Embedded in FortiAnalyzer, aimed at incident investigation and response: summarizing security events, estimating impact, and suggesting remediation so SOC analysts spend less time on triage and more on the incidents that matter.

SOC · incident response verified Jul 2026 visit →

Specialized agent catalogs

Rather than one monolithic assistant, some platforms take a modular approach: dozens of narrowly scoped agents, each built for one specific task, that can be combined for a given workflow.

Worth noting

Fabrix.ai is the clearest example of this pattern, with a public agent catalog spanning categories like NetOps, AIOps, SecOps, and Agent Ops. The exact number of agents in the catalog changes as they add more, so treat any specific count as a moving target rather than a fixed spec. A representative sample from the catalog is below.

Disclosure

I work at Fabrix.ai, so the six entries below aren't arm's length. See the full disclosure.

NA-013shipping

Network Change Risk Assessment Agent

Fabrix.ai

Scores the blast radius and rollback safety of a proposed network change before it goes out. Category: NetOps.

NetOps verified Jul 2026 visit →
NA-014shipping

Network Config Compliance Agent

Fabrix.ai

Checks device configurations against vendor guidelines and internal best practices on an ongoing basis. Category: NetOps.

NetOps verified Jul 2026 visit →
NA-015shipping

RCA for Networking Issues Agent

Fabrix.ai

Investigates the likely root cause of a networking issue within a given time window and suggests remediation. Category: NetOps.

NetOps verified Jul 2026 visit →
NA-016shipping

Anomaly Detection Agent

Fabrix.ai

Learns baselines from metrics and logs and surfaces real-time deviations. Category: AIOps.

AIOps verified Jul 2026 visit →
NA-017shipping

SecOps Incident Manager

Fabrix.ai

Automates incident handling: opens tickets, notifies the right people, and keeps the loop closed. Category: SecOps.

SecOps verified Jul 2026 visit →
NA-018shipping

CVE Vulnerability Analyst Agent

Fabrix.ai

Rather than listing every CVE that touches installed software, cross-references known CVEs against the current network topology to estimate real exposure. Category: Cybersecurity.

Cybersecurity verified Jul 2026 visit →

Open source, community & research

The open source layer is where a lot of the experimentation is happening, from official vendor tooling to weekend projects to academic papers on how agents should route work to each other.

NA-019actively developed

Junos MCP Server

Juniper Networks (official)

Juniper's own bridge between MCP clients like Claude Desktop or Copilot and real Junos devices, built on the junos-eznc SDK. Tools range from read-only (device facts, show commands) to a seriously privileged one: apply_config, which pushes configuration changes directly. Worth reading the permissions model closely before pointing it at anything you care about.

MCP · NETCONF verified Jul 2026 visit →
NA-020community project

mcp-server-junos

dpajin (community)

An independent, earlier community implementation of the same idea (an MCP bridge to Junos devices), built before Juniper shipped an official one. A useful example of how quickly community tooling can appear around a new protocol.

MCP · community verified Jul 2026 visit →
NA-021experimental

NetClaw

automateyournetwork (community)

A large, actively updated open source project built around delegating tasks to specialized agents rather than one model trying to know every vendor's syntax. It defines its own federation scheme, NCFED, currently documented as an individual IETF draft rather than an adopted standard. Ambitious and worth watching, but early. Treat it as a research project, not a production dependency, until it settles.

agent federation verified Jul 2026 visit →
NA-022actively developed

cml-mcp

xorrkaz (community)

An MCP server for Cisco Modeling Labs that lets an agent build lab topologies and query node status from plain-language requests. Handy for spinning up test environments without hand-writing topology files, and a good low-stakes way to try agent-driven networking without touching production.

labs · CML verified Jul 2026 visit →
NA-023community project

NetworkOps_Platform

E-Conners-Lab (community)

A community project pairing NetBox with a large set of MCP tools spanning Cisco, Juniper, Nokia, Arista, and Linux devices, plus self-healing agents and drift detection against an intended state. A good snapshot of how far a single motivated maintainer can push multi-vendor agent tooling.

multi-vendor · NetBox verified Jul 2026 visit →
NA-024mature open source

Hubble

Cilium (CNCF)

eBPF-based observability for cloud-native traffic. It isn't an AI agent, but it's increasingly the data source underneath higher-level agentic observability tools looking at Kubernetes networking.

eBPF · observability verified Jul 2026 visit →
NA-025research prototype

ACE-Router

Academic research (arXiv)

Research on how an agent should pick the right tool when it has access to hundreds of MCP servers instead of a dozen. Nothing here is networking-specific, but it's directly relevant: as networking agents accumulate more integrations, this is the kind of problem they'll run into.

research · tool routing verified Jul 2026 visit →

Missing something?

I maintain this directory by hand, so it won't stay complete on its own. If you know of an agent, project, or draft that belongs here, or something above is wrong or out of date, open an issue: it lands as a public, trackable report instead of disappearing into an inbox, and corrections that land get credited above. Prefer not to use GitHub? email works just as well. Being listed isn't an endorsement, and descriptions are summarized from public materials rather than hands-on testing unless noted.