agent-trust

Open-source reference implementation of the Agent Name Service (ANS) based on the IETF draft — registry, transparency log, and offline verifier in Go.

An Agent Name Service (ANS) registry, based on https://datatracker.ietf.org/doc/html/draft-narajala-ans-00

Trust infrastructure for million-agent economies on Solana - identity, reputation, and validation designed for continuous feedback at scale.

The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-native.

The open root-of-trust for agent identity on the internet. A public, federated registry of trusted attestation issuers — the agent runtimes authorized to vouch for agents acting on behalf of humans. Services verify agent attestations against this registry to determine if the issuing runtime is legitimate.

Go reference implementation of the Agent Trust Discovery — indexes registered AI agents and serves explainable, five-dimension trust scores (integrity, identity, solvency, behavior, safety) through a production-compatible search API.

Observability and guardrails for your ai agents. AgentTrail Guard traces your agent's execution and automatically compiles repeat failures into permanent guardrails.

Agent Name Service SDK written in rust.

Agent Name Service SDK written in go (golang).

Agent Name Service SDK written in java.

Cryptographic verification for AI agent actions — ECDSA-secp256k1 + RFC 6979 signed Action Receipts (v0.1), multi-dimensional Trust Vector, capability tokens (JWT-shaped + Biscuit-style attenuation), UETA §10(b) undo. 29 MCP tools. A2A v1.0 + ERC-8004 format compatible. Receipt-batch Merkle roots anchored on Base mainnet. Starting with code.

Official SDKs and MCP server for VeriSwarm — trust infrastructure for AI agents

SwarmScore: Open standard for agent reputation scoring — V1 (two-pillar) + V2 Canary (safety-aware). IETF drafts, API reference, SDKs.

Awesome list of open-source AI agent identity, trust, governance, security, and naming projects. Protocols, standards, tools for agent verification, permissions, attestation, reputation, and policy enforcement.

ANS identity for agents running in NVIDIA OpenShell

Spec for the trust index

MCP server for AI agents to report infrastructure needs. What do agents actually need? Let them tell you.

Python client for the VACRA Score API — calibration attestation for AI agents

MCP server for the DYOE Agent Tools — pay-per-call trust, due-diligence & data tools for AI agents, settled in USDC on Base via x402. Includes human-verified Guardian approval.

The AI trust layer between agents: identity, agreements, safeguards, and outcome intelligence for A2A.