Back to List
Product LaunchAI AgentsIRCSelf-Hosting

Building a Digital Doorman: Deploying an AI Agent on a $7 Monthly VPS Using IRC Transport

Developer George Larson has reimagined the traditional AI resume chatbot by building a 'digital doorman' system that operates over IRC. Moving beyond simple text rephrasing, this architecture utilizes two distinct agents—nullclaw and ironclaw—to provide deep, evidence-based answers about his work. The system is designed with a strict security boundary: a public-facing agent on a minimal $7/month VPS handles initial queries and code analysis, while a private agent on a separate machine manages sensitive data like email and calendars. By choosing IRC as the transport layer and using a lightweight Zig binary, Larson maintains full ownership of the stack while ensuring the system remains resource-efficient and aesthetically aligned with his terminal-based portfolio.

Hacker News
Share

Key Takeaways

  • Beyond Basic Chatbots: The project moves past simple RAG-based resume bots by allowing the agent to clone repositories and analyze actual code to answer technical questions.
  • Dual-Agent Architecture: A two-tier security model separates the public-facing 'nullclaw' agent from the private 'ironclaw' agent via a private IRC channel.
  • IRC as Infrastructure: The system uses IRC (via the Ergo server and Gamja web client) instead of modern APIs like Discord to ensure full stack ownership and low overhead.
  • Extreme Efficiency: The public agent is a 678 KB Zig binary that consumes only 1 MB of RAM, running on a low-cost $7/month VPS.
  • Security Boundaries: Private data (email, calendar) is isolated on a separate box accessible only through a private backoffice channel via Tailscale.

In-Depth Analysis

Rethinking the AI Portfolio Experience

George Larson identifies a common flaw in modern AI portfolio sites: they act as mere mirrors for existing resumes. To solve this, Larson developed a system where the AI doesn't just repeat facts but substantiates them. When queried about technical practices like test coverage, the agent is capable of cloning a GitHub repository, counting tests, and reading CI configurations to provide specific, data-driven responses. This shift from "parlor trick" rephrasing to active repository analysis represents a more functional use of AI agents in professional branding.

The Two-Box Security Model

The architecture is defined by a deliberate security boundary between two agents. nullclaw, the public doorman, resides on a minimal perimeter box. It is a highly optimized Zig binary designed for low resource consumption. Its role is to greet visitors and answer questions using public GitHub data. ironclaw, the private agent, sits on a more powerful, isolated system connected via Tailscale. It handles sensitive tasks involving email and calendar access. Communication between the two occurs over a private IRC channel (#backoffice), ensuring that the public-facing box never has direct access to private context or personal data.

Why IRC and Self-Hosting Matter

Choosing IRC over platforms like Discord or Telegram was a strategic decision based on three factors: aesthetics, ownership, and stability. The IRC interface complements the terminal UI of Larson's portfolio. More importantly, by using the Ergo IRC server and the Gamja web client, Larson owns the entire communication stack. This removes dependency on third-party APIs that are subject to frequent changes or restrictive terms of service, while keeping the infrastructure costs as low as $7 per month.

Industry Impact

This project demonstrates a growing trend toward "Small AI" and self-hosted agentic workflows. By proving that a functional, multi-agent system can run on a $7/month VPS with minimal RAM usage, it challenges the notion that AI agents require heavy, expensive infrastructure. Furthermore, the use of IRC as a transport layer highlights a return to robust, open protocols for internal tool communication, offering a blueprint for developers seeking to build secure, low-cost, and sovereign AI applications without relying on centralized messaging platforms.

Frequently Asked Questions

Question: Why did the developer choose IRC instead of a modern API like Discord?

IRC was chosen to maintain full ownership of the stack, avoid third-party API changes, and match the terminal-based aesthetic of the portfolio site. It allows the developer to run the entire infrastructure, including the server and client, independently.

Question: How does the system protect private data from public users?

The system uses a two-box architecture. The public-facing agent (nullclaw) has no access to private data. Complex or private inquiries are routed through a private IRC channel to a separate, more powerful machine (ironclaw) that is isolated and connected via Tailscale.

Question: What makes this agent different from a standard resume chatbot?

Unlike standard bots that only rephrase resume text, this agent can perform active tasks such as cloning GitHub repositories, analyzing codebases, and checking CI configurations to provide specific evidence for the developer's claims.

Read Original Article

Related News

Meta Unveils Muse Code: A New AI Agent Designed to Manage and Navigate Large-Scale Software Codebases
Product Launch

Meta Unveils Muse Code: A New AI Agent Designed to Manage and Navigate Large-Scale Software Codebases

Meta has officially expanded its portfolio of artificial intelligence tools for developers with the launch of Muse Code, a specialized AI agent engineered for large-scale codebases. According to the announcement, this new agent is designed to handle complex tasks within sophisticated software environments, marking a significant step forward in Meta's AI coding offerings. Muse Code aims to address the inherent difficulties of working with massive and intricate software systems, promising a level of capability that can manage high-level complexity. This launch underscores Meta's commitment to evolving its AI ecosystem, moving beyond basic coding assistants toward more autonomous agents capable of navigating the nuances of enterprise-level software development. The introduction of Muse Code represents a strategic move to empower developers dealing with the scale and density of modern software architectures.

Zed DeltaDB: Transforming Version Control with Real-Time Agent Integration and Granular History
Product Launch

Zed DeltaDB: Transforming Version Control with Real-Time Agent Integration and Granular History

Zed has unveiled DeltaDB, an early-access version control system designed to capture the nuances of software development that occur between traditional commits. Unlike standard systems, DeltaDB records every operation as it unfolds, assigning a stable identity to each change. This allows developers to rewind to any specific edit in the code's evolution. A standout feature is its deep integration with AI agents, where every code change is bi-directionally linked to the conversation that generated it. By virtualizing the worktree, DeltaDB enables instantaneous branching at any point in history and fosters a collaborative environment where teammates can join ongoing tasks, interact with agents, and annotate code in real-time. This shift moves the focus from static Pull Requests to dynamic, shared development threads within the Zed editor.

MiniMax H3: The Emergence of Omni-Modal Video and Audio Generation Technology
Product Launch

MiniMax H3: The Emergence of Omni-Modal Video and Audio Generation Technology

The AI industry has seen the introduction of MiniMax H3, a new model highlighted for its capabilities as an omni-modal video and audio generator. Unlike traditional models that often focus on a single medium, MiniMax H3 is designed to bridge the gap between visual and auditory synthesis. This development marks a significant step in the evolution of generative AI, moving toward 'omni-modal' systems that can handle multiple forms of media simultaneously. The announcement positions MiniMax H3 as a key highlight in the current landscape of AI models, emphasizing a unified approach to content creation where video and audio are generated in tandem rather than as separate, disconnected processes.