kagent_vision
A KAgent Agent with Vision - Capture photos, transform them with Nano Banana, animate them with Veo3. Supports ASL.
My work as a Google Developer Expert in Cloud AI and Google Cloud: connecting Gemini, agents, and real networks—and sharing what I learn along the way.
I report my community contributions in Advocu: educational videos and podcasts, practical articles, conference talks, hands-on workshops, mentoring, and open-source projects.
Advocu may require a GDE community sign-in. The original work is available through the links here.
Two days of FlowAI workshops with Karan Munalingal: practical agents, inherited workflows, reviewed changes, and lessons from the people doing the work.
Photos, results & reflections →HEAVY NETWORKING / OCTOBER 30, 2026My conversation with Ethan Banks and Drew Conry-Murray about NetClaw, MCP, operational controls, federation, and the community building it.
Watch & read the recap →VIBEOPS LOUNGE 007 / OCTOBER 29, 2026A Containerlab dashboard, an AI network planner, and a troubleshooting game: sharing practical experiments and the lessons behind them.
Explore the episode →OPEN-SOURCE TUTORIALS / OCTOBER 30, 2026A two-part series on dynamic pyATS MCP testbeds and NetClaw source composition, with explicit review, validation, activation, and tested scope.
Read the series →WATCH & LISTENGemini experiments, NetClaw demonstrations, VibeOps Lounge interviews, and community sessions.
Explore the video library →TEACH & SHARETORNOG, AutoCon, Cisco Live, and MCP Dev Summit: talks, workshops, recordings, and slides.
Find talks and workshops →BUILD IN THE OPENNetClaw, pyATS MCP, and kagent_vision connect real tools and infrastructure to AI agents.
Start with NetClaw →28 repositories from my GitHub collection. Forks and archived projects are labeled.
A KAgent Agent with Vision - Capture photos, transform them with Nano Banana, animate them with Veo3. Supports ASL.
A Google Gemini-CLI extension than enables Gemini Computer Use from the CLI
An Extension for Gemini-CLI that enables Webcam access including single frame capture and American Sign Language (ASL) modes
Extending Gemini-CLI with Google Gemini File Search; cloud based RAG
100% vibe coded Google Drone using Google Maps SDK / MCP; Vision Extension; Computer Use extension from just prompts
A /listen feature for Gemini CLI
Share your screen with Gemini-CLI via this extension using MCP and custom slash commands
A Gemini CLI extension that uses RAG and MCP and Custom Slash Commands to analyze packet captures
An MCP Server / Gemini CLI Extension to create modern Infographics for your project - VibeGraphics - Generated with Nano Banana and animated with Veo3
Turn Gemini-CLI into a server with /isten commands packaged as a Gemini-CLI extension
Inspired by Battle Chess for DOS 1988 - Using Gemini3, Nano Banana3, and Veo3 to reimagine Battle Chess
An easy to install pyATS extension for Gemini CLI
An MCP for Gemini CLI to allow voice
Enable your microphone on Windows WSL Ubuntu with this and the corresponding MCP
An Extension for Gemini-CLI that enables voice (input) and audio (output); requires openAI for TTS currently
Add a .pcap(ng); automated reporting; all powered by GitActions, Gemini-CLI, and Packet Copilot MCP
An extension for GeminiCLI that performs subnet calculation
An open protocol enabling communication and interoperability between opaque agentic applications.
A Google-based AI Agent for pyATS
A Gemini-CLI extension that adds GAIT support for context control
An extension that coverts JSON to TOON before sending to Gemini-CLI for tokens savings and better inference!
Integrating the webcam with Gemini-CLI via MCP
Cisco IOS-XE Show Version Command Reimagined as a pyATS job that creates CSV / MD / HTML; sends #chatbot messages; and generates MP3 using Google Cloud TTS #voice
The Google Cloud Run service for the multiplayer
Custom Slash Commands that use Vision MCP to enable webcam access
A registry for A2A AI Agents
Quick listener to test Agent Push Notifications
Transform song lyrics from Shazam API into Google Text to Speech
53 videos
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Recent workshops, open-source releases, AI governance conversations, and practical tutorials, alongside my Gemini and Google experiments. These are my independent contributions; each article states its tested scope.
Photos and reflections from Lumen’s October Innovation Summit: hands-on FlowAI workshops, Greg Freeman’s recap, Marc Montez on trust, and my full Itential write-up.
Part two: NetClaw 1.14.0 brings static/dynamic testbed choice, fourteen source routes and reviewed pyATS activation to its VS Code and terminal installers.
Back with Ethan Banks and Drew Conry-Murray on Packet Pushers to talk NetClaw: MCP, explicit approvals, layered protection, federation, and the community building it.
How NetConverter and NetClaw can connect reviewed conversion artifacts with virtual-target rehearsals, validation and change evidence. Live conversion qualification is pending.
Part one: pyATS MCP can build an in-memory testbed from inventory systems and structured data, then make it available to its existing network automation tools.
VibeOps Lounge 007: Elliot Conner brings a Containerlab operations dashboard, an AI network planner, and a troubleshooting game to a conversation about learning by building.
From Walmart freight to CWNE #521: Eva Santos joins me to talk Wireshark, ChromeOS Wi-Fi Fixer, Claude Code, and building useful tools before the token buffet closes.
My conversation with William Collins on Packet Pushers: MCP in production, NetClaw’s constitution, human oversight, model identity, and specialized decision models.
Twenty-one years after a free Ubuntu CD got me started, the Linux Foundation’s Agentic AI Foundation (AAIF) is publishing my MCP and NetClaw story. A personal honour and a milestone for the project and its community.
A network operations workbench beside your code: NetClaw brings Chat, Canvas, RAG, Testbed management, per-MCP setup and reviewed security controls into Visual Studio Code.
Andy Lapteff and Ryan Booth talk AI, systems thinking, and the future of network engineering—and revisit my Hello World for AI session and our subnetting game.
NetClaw 1.8.0 brings protected Hermes federation and Mobile Ask Border together, following the shared HUD work in 1.7.0. Five diagrams explain the design and its tested boundaries.
86,688 lines of hand-written code, about 550 hours, and the Django detour that helped me build NetworkGPT in two weeks. What Merlin taught me—and permission to build differently now.
NetClaw’s mesh could always tell you who was online. Now it tells you what they can do — and lets you use it. Introducing N2N Federation and NCFED, a new protocol for federating AI network engineers safely.
We Gave a Slack Channel Full of Engineers an AI Network Agent. Here’s What Happened. A live red-team session, a VASI BGP lab, and 30+ social engineering attempts — all in one Friday afternoon. ─── The Setup The premise was simple: drop an A
This next post may seem like science fiction. I woke up this morning and checked that my output files – MP3 files – really did exist and that I actually made my Cisco network “talk” to me! This post is right out of Star Trek so strap yourse
Original articles on Itential, the Agentic AI Foundation, and LinkedIn, with their publication dates and publisher attribution.
John explains why infrastructure agents need scoped tools, current context, enforced approvals, and evidence of completion, and why engineers must own and test the operating environment around the model.
John’s field report from Lumen’s hands-on FlowAI workshops, including session outcomes, inherited workflow documentation, and human-approved agent coordination.
A demonstration of decision gates, scoped tools, human approvals, and recovery: Claude coordinates, Jev evaluates evidence, and Gemma handles reporting.
John follows Andy Lapteff’s public learning journey from initial AI experiments to building an app, with links to their conversations and demonstrations.
John uses the prisoner’s dilemma as a lens for discussing individual incentives, shared learning, and AI adoption among network engineers.
John Capobianco’s MCP and NetClaw story, published October 14, 2026 on the official blog of the Linux Foundation’s Agentic AI Foundation. A personal honour and a milestone for the NetClaw project and community.
Why infrastructure operations need repeatable execution around probabilistic reasoning, and where governed workflows fit into agent-driven changes.
John’s Toronto reflections on tool access, identity, permissions, and the operational controls needed when MCP-connected agents can change infrastructure.