Aug 2026 - PresentSystems & Remote Automation

LUNAR

An asynchronous remote Windows management agent with modular command routing, Groq LLM tool-calling, multi-key failover, and zero inbound port exposure.

Signature: Win32 low-level hooks · dual-key LLM failover · ephemeral surveillance buffer

Key Verified Performance Metrics

Primary Metric32 Strongly-Typed Tools
Secondary BenchmarkZero Inbound Open Ports

01 System Context & Problem

Traditional remote PC management tools either consume heavy background resources with commercial third-party cloud dependencies (TeamViewer, AnyDesk) or require opening dangerous inbound firewall ports with raw shell exposure (SSH/WinRM).

02 Architecture & Implementation

5-tier topology with an independent supervisor daemon (lunar_host.py) auto-restarting the worker process (main.py) with exponential backoff; multithreaded HTTP MJPEG server (port 8554) with 24-byte cryptographic session tokens; and SQLite databases in WAL mode.

Engineering Approach: Built an edge-native Python agent leveraging Telegram's global encrypted infrastructure for outbound-only long-polling control, combined with Groq LLM tool-calling and two-stage interactive confirmation buttons for state-altering operations.

03 Technical Decisions & Trade-offs

Core Architectural Decision

Enforced zero arbitrary execution by exposing 32 strongly-typed Python functions rather than an open shell. Selected outbound long polling to eliminate router port forwarding, and implemented a thread-safe dual-key Groq pool to seamlessly absorb free-tier rate limits.

Constraints & Incurred Trade-off

Outbound long polling adds slight round-trip latency compared to raw WebSockets, but guarantees zero inbound attack surface and instant operation behind NAT or mobile hotspots.

04 Scalability, Throughput & Security

Designed with decoupled subsystems and thread isolation: camera acquisition runs in a dedicated thread with condition-variable frame signaling, while database writes use SQLite WAL mode and mutex locks to prevent concurrency contention.

Full HD 1080p@30fps MJPEG video delivery with latest-frame zero-backlog queuing; Groq LPU tool-calling loops resolving multi-step queries in under 2 seconds; and 3-second atomic cooldowns on input surveillance triggers.

05 Verified Outcomes

  • Built an asynchronous remote Windows management agent used daily, with modular command routing and Groq LLM tool-calling plus multi-key failover for natural-language system control and automation.
  • Secured it with single-user authentication, two-step confirmation gates for destructive actions, path-traversal-safe file sandboxing, and no arbitrary shell execution; added MJPEG live streaming and OpenCV camera capture.

Technologies & Protocols

Pythonpython-telegram-botGroq APIOpenCVSQLiteWin32 APIspynputpsutilasyncio