netclaw  by automateyournetwork

AI network engineering coworker automating complex operations

Created 1 month ago
408 stars

Top 71.4% on SourcePulse

GitHubView on GitHub
Project Summary

NetClaw: AI-Powered Network Automation and Operations

NetClaw positions itself as a CCIE-level AI network engineering coworker, designed to automate complex network tasks through natural language interaction. It targets network engineers, researchers, and power users seeking comprehensive network automation, ITSM-gated change management, and immutable audit trails. The primary benefit is an AI assistant capable of handling a vast array of network operations, from monitoring and troubleshooting to configuration and compliance.

How It Works

NetClaw is built upon the OpenClaw framework and powered by Anthropic Claude, functioning as an autonomous AI agent. Its architecture involves a human interface (Slack/WebChat) interacting with the NetClaw agent, which then orchestrates actions through a multitude of specialized Microservice Communication Protocol (MCP) servers. These MCP servers provide standardized interfaces to diverse network devices, cloud platforms (AWS, GCP), observability tools (Grafana, Prometheus), security systems, and orchestration engines. The agent's behavior, expertise, and operational context are defined by workspace files like SOUL.md and AGENTS.md, ensuring consistent and auditable operations.

Quick Start & Requirements

  • Installation: Clone the repository, then run ./scripts/install.sh for a comprehensive bootstrap process (45 steps), followed by ./scripts/setup.sh for interactive configuration of credentials and integrations.
  • Execution: Start the gateway with openclaw gateway and initiate a chat session with openclaw chat --new.
  • Prerequisites: Node.js (>= 18, >= 22 recommended), Python 3.x with pip3, git. Additional requirements include Docker, tshark/Wireshark, GitHub PAT, specific cloud provider accounts (AWS, GCP), Cisco CML/NSO/FMC/Meraki/ThousandEyes/RADKit access, Juniper devices with NETCONF, Arista CVP, Grafana/Prometheus servers, Kubernetes cluster with Kubeshark, Slack workspace, and potentially NetBox, ServiceNow, APIC, ISE, NVD API keys, F5 BIG-IP, Catalyst Center, graphviz, and sudo access for GRE tunnels.

Highlighted Details

  • Extensive Integration Ecosystem: Features 92 skills and 43 MCP integrations, covering major network vendors (Cisco, Juniper, Arista, F5), cloud platforms (AWS, GCP), observability (Grafana, Prometheus), security (FMC, ISE), orchestration (NSO, Itential), simulation (CML, ContainerLab), and more.
  • AI-Driven Network Coworker: Leverages Anthropic Claude for natural language understanding, enabling CCIE-level assistance for complex network tasks.
  • Immutable Audit Trail (GAIT): Provides a mandatory, Git-based audit trail for all actions, ensuring transparency and accountability.
  • ITSM Gating: Integrates with ServiceNow for formal change request workflows, ensuring approved and documented changes.
  • Comprehensive Network Operations: Encompasses monitoring, troubleshooting, configuration management, security auditing, topology discovery, packet capture analysis, and live protocol participation (BGP/OSPF).

Maintenance & Community

The project is hosted by the automateyournetwork organization on GitHub, indicating active development. Specific community channels or contributor details are not explicitly listed in the README.

Licensing & Compatibility

The project's primary license is not explicitly stated in the README. While some underlying components may have their own licenses, the overall licensing for NetClaw requires clarification for adoption.

Limitations & Caveats

The setup process is complex, requiring numerous prerequisites and careful credential management for many integrated services. Running the full suite may demand significant computational resources. Usage of cloud APIs (AWS, GCP) may incur costs. The project currently lacks MCP tools for GCP VPC fabric management. The absence of a clearly stated project license is a notable caveat for due diligence.

Health Check
Last Commit

2 days ago

Responsiveness

Inactive

Pull Requests (30d)
27
Issues (30d)
9
Star History
164 stars in the last 30 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Vasek Mlejnsky Vasek Mlejnsky(Cofounder of E2B), and
1 more.

pezzo by pezzolabs

0.1%
3k
Open-source LLMOps platform for streamlining AI workflows
Created 3 years ago
Updated 1 week ago
Feedback? Help us improve.