On AI Lounge since Nov 2026
Igor Ganapolsky
Member #3,901DeveloperL2Founder, Production AI Reliability
Forward Deploy AI Engineer. Automation specialist.
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×3Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 3 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×3Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Igor Ganapolsky hasn't posted yet.
Pinned projects
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
ai-safetydeveloper-toolsai-agentsguardrailsthompson-sampling
OS-level safeguards layer for AI agent loops — runaway-kill, timeouts & resource limits so coding agents (Claude Code, Cursor, Codex, Antigravity) in YOLO mode can't burn tokens or freeze your Mac
ai-agentsclaude-code
cursordeveloper-toolslaunchd
LiteLLM gateway + LLM eval gate (golden set, LLM-as-judge, RAG faithfulness, regression, CI gate) for a self-hosted Ollama agent fleet
OpenClaw/Codex/Computer Use Mac setup. $19 quick read, $49 triage, $99 diagnostic, $497 setup.
ai-agents
codexcomputer-usemacosopenclaw
Dayglass v2.1 for macOS: Private Screen & Meeting Memory (AirPods + ScreenCaptureKit + Local SQLite + MCP). 3 Free AI Previews; Pro ($19/mo) & Ultra ($249/mo Managed Google AI Ultra).
apple-silicongraphraglocal-aimacos
mcp
Agentic ad-creative & landing-page analyzer for performance media buyers. Local-LLM (Ollama). Built for It's Today Media Build Challenge.
About
Forward Deploy AI Engineer. Automation specialist.
