ZeroID: Autonomous Agent Identity Management System (AAIMS)

Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual API keys, and end-to-end encryption via OpenZiti

The IAM layer for AI agents: cryptographic identity, capability authorization, and audit trails for non-human identities. Open source.

Zero trust gateway for MCP servers. Aggregate, filter, and securely access MCP tools from anywhere without VPNs, open ports, or exposed endpoints. Built on OpenZiti, zrok, and Agora with cryptographic identity, mTLS, per-client isolation, and tool-level permission control.

Open-source AI agent identity & compliance platform — X.509 certificates via AWS KMS, behavioral risk scoring, auto-revocation, and MiCA / EU AI Act audit trails.

TypeScript SDK for AI agent identity & compliance — issue X.509 certificates, verify scope, and enforce them with drop-in middleware. Apache-2.0.

NHInsight — Open-source security tool to find risky non-human identities, tokens, and CI/CD access paths across AWS, Azure, GCP, GitHub, Kubernetes, and GitHub Actions.

Voluntary behavioral baseline + conformance testing for transparent AI voice agents in healthcare. Open proposal with cryptographic authorization layer.

Runtime identity for AI agents. Short-lived attested credentials with capability tokens that agents narrow as tasks change and verify offline.

Read-only NHI risk scanner (GitHub Actions, K8s, IaC). Offline-first. No telemetry

Passport & visa system for AI agent credentials. Detect, classify, and govern API keys, tokens, and secrets across MCP, OpenAI, Anthropic, LangChain, and more. Encrypted vault, policy engine, audit trails, delegation chains. Drop-in MCP server replaces plaintext credential storage.

AI agent credential broker — temporary, task-scoped tokens with automatic revocation. Free for internal use

Identity registry and lifecycle management for fleets of AI agents. Zero-dependency TypeScript IAM: cryptographic agent identity (Ed25519), declared capabilities with fail-closed authorization, an enforced lifecycle (provision, activate, suspend, revoke, expire, archive), A2A Signed Agent Cards, and a hash-chained audit trail.

Non-Human Identity governance framework — Entra ID sandbox · Service Principals · Workload Federation · AI Agent Identity

Python SDK for AgentWrit — AI agent credential broker. Temporary, task-scoped tokens with automatic revocation. pip install agentwrit

AWS non-human identity governance engine: discovers, risk-scores, and produces audit evidence for IAM roles, access keys, secrets, and workload identities. Mapped to OWASP NHI Top 10 and NIST 800-53

Blast radius modeling framework for agentic systems — 5 axes (action class, chain depth, external reach, reversibility window, identity scope), OSI cross-walk, and standards alignment.

Essays on agentic AI security, decision-rights, reversibility-graded authority, manifest-declared action class, deterministic gates, and standards contribution method.

Secretless, identity-aware credential broker for agents & automations (non-human identities) — acts on behalf of a verified caller against any service, including the un-API'd web.

Identity & compliance middleware for AI agent frameworks — Express, Fastify & Next.js gateways plus LangChain, Mastra & Vercel AI SDK tools.