On AI Lounge since Nov 2026
Fabio Marcello Salvadori
Member #3,879DeveloperL2AI Agent Architect, Independent
I build infra for agentic AI systems with a focus on auditable execution, provenance, and fail-closed controls at the action boundary.
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.
No posts yet
Fabio Marcello Salvadori hasn't posted yet.
Pinned projects
Neural Computation Protocol (NCP): composable, sandboxed Bricks + graphs for auditable, replayable agentic systems.
agent-frameworkai-agentai-workflowdeclarativegraph
Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.
agent-governanceagent-safetyagent-securityagentic-aiai-agents
Rollback and safety for AI coding agents and vibe coders: flag risky changes and restore project files, including uncommitted work, to their pre-session state.
agent-safetyagenticai-agentsai-codingclaude-code
Trace what an agent's actions depended on, and what becomes affected when those dependencies fail.
agent-safetyai-agentscausal-graphledgerprovenance
Token-frugal web reader for AI agents. Staged extraction (raw HTML → embedded framework JSON → browser fallback) cuts agent input tokens by ~20× vs browser-everything approaches.
agentic-aiai-agents
fastapillm-tools
playwright
About
I build infrastructure for agentic AI systems with a focus on auditable execution, provenance, and fail-closed controls at the action boundary.
Stack
Experience
Creator & Maintainer · Pic-Standard
AI Agent Architect · Wallafan
AI Agent Architect · MadeInPluto
Principal AI Architect | Custom Agent Deployment · Madeinpluto
Founder & Product Architect · Wallafan
Founder · Wallafan
CEO · Madeinpluto
F
Software and Web Developer, Media Editor, Talent Agent · Freelance/Self-employed
