menu

Web Agent Bridge v3.6.0 — The Trust & Intelligence Layer for Sovereign AI Agents We just shipped one

Leader ●1 ●8 ●22
calendar_today • schedule1 min read

v3.6.0 introduces a completely new Truth Layer and advanced intelligence capabilities that push WAB from a discovery protocol into a full sovereign trust and reasoning infrastructure for AI agents.
✨ What’s New in v3.6.0:
• Reputation Score — Dynamic 0-100 trust rating for every website based on behavior, stability, and history.
• Temporal Trust — Time-aware trust that detects sudden suspicious changes in sites.
• Semantic Memory Network — Secure, anonymized collective intelligence between agents.
• Intent-Aware Routing — Websites can now respond intelligently to high-level agent intents.
• Privacy Budget System — Granular, machine-readable privacy controls respected by agents.
• Reality Anchor — Helps agents verify real-world state through trusted WAB sources.
• Offline Mode + Smart Cache — Agents can operate with cached manifests and sync when online.
• Enhanced Extended Trust combining DNS, Ed25519, and SSL thumbprints.
WAB is no longer just about discovery — it’s becoming the decentralized trust and memory layer that sovereign AI agents desperately need.
No centralized directories.
No vendor lock-in.
Full cryptographic verification.
This is infrastructure for the post-API web.
Links:
• GitHub: https://github.com/abokenan444/web-agent-bridge
• Live Demo & Docs: https://www.webagentbridge.com
• Latest Release: https://github.com/abokenan444/web-agent-bridge/releases/tag/v3.6.0
We’re actively looking for feedback, integrations, and collaborators — especially from teams building sovereign agents.
What do you think? Which feature excites you the most?

AIAgents #WebAgents #SovereignAI #OpenSource #DNS #AIInfrastructure

3 Comments

•

Nice read. Trust intelligence layer sounds buzzwordy at first but the examples helped. Any plans to open source parts of it?

1 vote
•

@[Aulia Ika Savitri] Thank you Aulia, glad the examples helped clarify the concept
You’re right — “Trust Intelligence Layer” can sound like marketing buzz at first. The goal is actually quite practical: giving AI agents a standardized, cryptographically verifiable way to discover what a website can do and how much they can trust it, without relying on centralized APIs or blind scraping.
Regarding open source:
Yes — the core of Web Agent Bridge (WAB) is already open source:
→ https://github.com/abokenan444/web-agent-bridge
We follow an Open Core approach:
• The protocol, DNS discovery, basic trust layer, and most APIs are fully open.
• Some advanced parts of the Truth Layer (e.g. certain Reputation Score algorithms and Semantic Memory implementation details) are currently selective-release for security reasons, but the specifications and integration docs are public.
The aim is to balance transparency with responsible disclosure, especially since we’re dealing with trust and agent capabilities.
Would love to hear your thoughts — are you working on AI agents or sovereign infrastructure yourself?

0
•

@[Aulia Ika Savitri] Thank you Aulia, great question!
Yes, we are committed to Open Source, and the core of Web Agent Bridge is already fully open:
• The protocol specification
• DNS-based discovery
• Cryptographic trust layer (Ed25519)
• Most of the Truth Layer and Advanced Features
You can find it here:
https://github.com/abokenan444/web-agent-bridge
However, we follow an Open Core model. Some advanced components (particularly parts of the Reputation Score algorithm, certain Semantic Memory implementations, and Enterprise-tier features) are not fully open-sourced yet.
Why?
Because WAB deals with trust and agent capabilities inside websites. Releasing everything immediately could allow bad actors to reverse-engineer and abuse the system before proper safeguards are in place. We prefer responsible disclosure — opening what benefits the community while protecting critical parts until they are mature and secure.
We regularly open more parts as the project matures and as we implement stronger security measures. The direction is toward increasing openness, not the opposite.
If you’re interested in specific modules or want to contribute/review certain parts, feel free to let me know. We’re always open to serious collaboration.
Appreciate your interest!

0
🔥 Join developers growing publicly
Share your knowledge, build in public, and grow your developer presence with a global community.
Join CoderLegion

More Posts

Sovereign Intelligence: The Complete 25,000 Word Blueprint (Download)

Pocket Portfolio - Apr 1

Architecting a Local-First Hybrid RAG for Finance

Pocket Portfolio - Feb 25

The Privacy Gap: Why sending financial ledgers to OpenAI is broken

Pocket Portfolio - Feb 23

The Sovereign Vault — A Comprehensive Guide to Protocol-Driven AI

Ken W. Algerverified - Jun 4

Your AI Doesn't Just Write Tests. It Runs Them Too.

Kevin Martinez - May 12
chevron_left
Yasser Ab
1.7k Points • 31 Badges
Netherlands • webagentbridge.com
10Posts
19Comments
6Connections
Active developer and follower of AI Agents technologies. I focus on open-source solutions that solve... Show more

More From WAB

Can AI agents prove what they did?

WAB protocol

WAB web agent bridge

Related Jobs

View all jobs →

Commenters (This Week)

2 comments
1 comment
1 comment

Contribute meaningful comments to climb the leaderboard and earn badges!