delegated-authority

A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.

Open Agent Trust Infrastructure (OATI) — an open standard for verifiable AI agent identity, delegated authority, policy enforcement, and signed action receipts.

Web4: an open standard for verifiable AI presence — LCT identity, T3/V3 trust tensors, MRH context, ATP/ADP. Rust + Python SDKs on crates.io/PyPI. AGPL-3.0-or-later.

Ratify Protocol™. Open cryptographic protocol for delegated authority: prove an AI agent is authorized to act on another party's behalf, verifiable offline. Hybrid Ed25519 + ML-DSA-65 (FIPS 204). SDKs in Go, TypeScript, Python, Rust, and C.

Ephemeral virtual identity and credential proxy sandbox for personal agents with scoped tokens and budget bounds

Ephemeral virtual identity and credential proxy sandbox for personal agents with scoped tokens and budget bounds

Hestia — universal Web4 presence for humans and AI. Local-first cryptographic identity, encrypted vault, delegation authority, witnessed trust record, and device constellation. Cross-platform app + AI plugin + CLI. EUDI-compatible credential issuance. AGPL-3.0.

Governed AI engineering control plane: federated workload identity, delegated least privilege, pre-dispatch MCP/API authorization, human approval, revocation, and cryptographically signed authority receipts with tamper/replay/rollback detection and independent verification. AI proposes. Humans decide.

Watch AI agents get stopped. Runnable references for Ratify Protocol: a principal signs a bounded mandate, and the system carrying the consequence verifies it before acting.

Trust, accountability and provenance for autonomous AI agents — public events, questions, session records and collaboration.

Bounded human-to-agent delegation with checkpointed execution, dual-bond accountability, and a local append-only transparency log.

Open-source classifier.dev and Ratify Protocol reference showing semantic routing separated from receiver-verified delegated authority.

Verifiable authority for consequential WebMCP browser-agent actions.

Profile README — start here

Minimal, non-normative ARC application reference implementations for delegated authority and pre-dispatch authorization of simulated AI agent actions.

Margelis Research: technical research notes and draft benchmark specifications (Rūpestėlis Holding). Note 001: From Mandate to Verified Outcome.

Independent research on trajectory-aware AI-agent evaluation, delegated authority, control integrity, and failure-preserving reproducibility.

Non-normative reference implementation of ARC authority validation and projection for delegated AI agent actions.

An SDK for binding delegated agent authority to mediated, independently attributable execution, with a reference harness demonstrating the architecture.

Web4 Community Hub — single-binary Rust daemon that turns a community into a sovereign Web4 society: signed law, witnessed ledger, sealed member channels. Standalone mirror of web4/hub; development happens in dp-web4/web4.